@1aboveio/core-skills 0.1.4 → 0.1.6

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@1aboveio/core-skills",
3
- "version": "0.1.4",
3
+ "version": "0.1.6",
4
4
  "description": "Shared writing and document foundation: house style, plain-language replies, editorial review, Chinese polish, terminology, write-doc, distill-writing, doc-to-md and reg-parser.",
5
5
  "license": "MIT",
6
6
  "repository": {
@@ -27,7 +27,7 @@
27
27
  "id": "core",
28
28
  "core": "@1aboveio/core-skills",
29
29
  "coreSkills": [],
30
- "digest": "62a4265c57d6f35b5a4f428e5b6e3e6f9953269b85a53f47ebd71cee9388aec7"
30
+ "digest": "9f04caee874da1bb56131dd41940010985e24143efcaea1034055a21ddf2c42e"
31
31
  },
32
32
  "publishConfig": {
33
33
  "registry": "https://registry.npmjs.org/",
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: distill-writing
3
3
  description: "Learn a house writing style from approved sample documents into the project's WRITING.md and writing/templates/, with evidence per rule, conflicts surfaced and manual edits kept. Use when given reference documents to learn from, or to set up or refresh the house style. NOT for writing a document (write-doc)."
4
- release-version: 0.41.0
4
+ release-version: 0.42.1
5
5
  ---
6
6
  **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
7
7
  # Distill a writing style
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: doc-to-md
3
3
  description: "Convert documents (PDF, DOCX, PPTX, XLSX, images) to Markdown so agents can read them. Use as the preprocessing step whenever binary files need to enter agent context — contract review, compliance audit, document analysis, evidence review."
4
- release-version: 0.41.0
4
+ release-version: 0.42.1
5
5
  ---
6
6
  **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
7
7
  # doc-to-md
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: editorial-review
3
3
  description: "Review a document or generated report for what it says (does the reader get the answer, is the argument sound, is anything unsupported, obvious or repeated), then fix the content. Use to review, tighten or clarify a doc or report, and as the review step of write-doc and the report skills. NOT for Chinese wording (polish-cn) or code review (better-review)."
4
- release-version: 0.41.0
4
+ release-version: 0.42.1
5
5
  ---
6
6
  **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
7
7
  # Editorial review
@@ -3,7 +3,7 @@ name: house-style
3
3
  description: "Shared reference the writing skills read by path: WRITING.md lookup and precedence, template choice, gap markers, template shape, the bundled templates, and the default English and Chinese style guides. Never select or invoke it as a task."
4
4
  disable-model-invocation: true
5
5
  user-invocable: false
6
- release-version: 0.41.0
6
+ release-version: 0.42.1
7
7
  ---
8
8
  **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
9
9
  # House style
@@ -47,15 +47,26 @@ the table: "Owners and dates are to be agreed by `<who>`." Never write `[TBD: ow
47
47
 
48
48
  - **Headings**: sentence case, informative ("Disputes double after the price change", not
49
49
  "Analysis"). `#` once for the title; do not skip levels, unless WRITING.md or the template
50
- records a house pattern that does (house evidence beats this default).
51
- - **Paragraphs**: two to five sentences. One line per paragraph in the source file; no hard wraps
52
- inside a paragraph unless the project's files already wrap.
53
- - **Lists**: only for parallel items or steps. Numbered for sequences, bullets otherwise. Not for
54
- reasoning that needs "because" and "so".
50
+ records a house pattern that does (house evidence beats this default). In longer content,
51
+ prefer a standalone heading for each section or numbered topic, with the body below it.
52
+ An inline heading can suit a compact note; do not turn every paragraph into a labeled item.
53
+ - **Paragraphs**: use prose for explanation and connected actions. Break at a change of focus,
54
+ not at a fixed sentence count. A paragraph may be one sentence; do not pad it to meet a quota
55
+ or force an entire topic into one long paragraph. One line per paragraph in the source file;
56
+ no hard wraps inside a paragraph unless the project's files already wrap.
57
+ - **Lists**: use them when readers need to identify distinct rules, conditions, options or steps
58
+ separately. Numbered for sequences, bullets otherwise. Keep reasoning and connected actions
59
+ in prose. Introduce a list with a complete sentence and put shared context or follow-up
60
+ explanation outside it. A section may mix prose and a list.
61
+ - **Layout follows meaning**: choose paragraph and list breaks for the content, not for visual
62
+ symmetry. Do not add, split or merge points just to give every section the same count or
63
+ layout. Repeated formats are useful for genuinely comparable items and checklists. Preserve
64
+ the user's chosen structure during an edit unless the requested change requires otherwise.
55
65
  - **Tables**: when three or more items share the same attributes. Every column has a header; no
56
66
  empty cells (write `n/a` or `TBD`).
57
67
  - **Emphasis**: bold for the few words a skimming reader must see; no bold sentences in a row, no
58
- italics for emphasis, no ALL CAPS.
68
+ italics for emphasis, no ALL CAPS. Avoid a bold label on every paragraph or bullet when the
69
+ text already makes the distinction clear.
59
70
  - **Code**: field names, endpoints, commands, file names and config keys in code font, exactly as
60
71
  the system spells them.
61
72
  - **Links and citations**: link the descriptive words, not "here". Cite a source after the claim it
@@ -64,3 +75,18 @@ the table: "Owners and dates are to be agreed by `<who>`." Never write `[TBD: ow
64
75
  than four steps or actors in mind. Every diagram has a sentence saying what it shows.
65
76
  - **Callouts**: a blockquote starting `**Note:**` or `**Warning:**` (`**注意:**`, `**警告:**`),
66
77
  only for an aside that would derail the paragraph.
78
+
79
+ ### Example: prose, a list, then prose
80
+
81
+ Keep the purpose and follow-up in paragraphs; list only the items readers need to distinguish:
82
+
83
+ > **Validate the alert rules**
84
+ >
85
+ > Test the following patterns before enabling automatic holds.
86
+ >
87
+ > - One payer sends repeated payments of the same amount.
88
+ > - Several customers pay the same beneficiary.
89
+ >
90
+ > Review false positives before deciding which alerts should block payouts.
91
+
92
+ A neighboring section may need only one paragraph. Do not give it a list to match this one.
@@ -47,6 +47,13 @@ terms" goes in `writing/templates/commercial-proposal.md`.
47
47
  4. No `WRITING.md` found: write from the brief and the bundled
48
48
  [defaults](defaults.md). Say so in the delivery note. Do not create one.
49
49
 
50
+ A present but unreadable, invalid or uninspectable guide is not absent. Report its path
51
+ and the problem; do not silently climb to a different guide or claim to apply defaults.
52
+ The same applies to broken links or an unreadable selected project template. Ask for the
53
+ missing access or decision only when that policy blocks the requested work; otherwise
54
+ continue unaffected work and state what guidance could not be applied. A fallback chosen
55
+ for this task does not authorize repairing or overwriting project guidance.
56
+
50
57
  `TERMINOLOGY.md` sits beside the `WRITING.md` that applies, else at the project root; find it
51
58
  the same way. An older WRITING.md that still holds a Terms table: use its rows too, TERMINOLOGY.md
52
59
  winning, and suggest `terminology` to move them.
@@ -18,7 +18,7 @@ The baseline can be a regulation or scheme rule (compliance), a risk appetite or
18
18
  - Pick the `compliance-audit` skill to run the audit itself against a checklist (tracker and
19
19
  evidence); use this template to write up its result.
20
20
  - An audit report built from completed audit findings for a regulator or board belongs to the
21
- `report-writing` skill, not this template.
21
+ `write-doc`'s compliance-report workflow, not this template.
22
22
 
23
23
  ## Tone
24
24
 
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: plain-language
3
- description: "Session mode: every reply and status line in plain language — lead with the point, everyday words, full sentences, no filler — in English or Chinese, until turned off. Use for /plain-language, \"plain language mode\", \"talk plainly\", \"说人话\", or when the user's instructions say to use plain-language. Turn off with \"/plain-language off\" or \"normal mode\". NOT for writing a document (write-doc) or reviewing one (editorial-review)."
4
- release-version: 0.41.0
3
+ description: "Session mode: every reply and status line in plain language — lead with the point, everyday words, full sentences, no filler — in English or Chinese, until turned off. Enable by default when the project has an applicable WRITING.md, even without a slash command. Use /plain-language init to persist that project default and its agent loading instructions. Use for /plain-language, \"plain language mode\", \"talk plainly\", \"说人话\", or when the user's instructions say to use plain-language. Turn off with \"/plain-language off\" or \"normal mode\". NOT for writing a document (write-doc) or reviewing one (editorial-review)."
4
+ release-version: 0.42.1
5
5
  ---
6
6
  **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
7
7
  # Plain language
@@ -10,12 +10,95 @@ Write every reply in this style for the rest of the session, including status li
10
10
  summaries, until the user says `/plain-language off` or "normal mode". A switch to another
11
11
  reply style (such as caveman) also ends it.
12
12
 
13
- - Invoked with no other request: reply in one line that the mode is on. Otherwise do not
14
- mention the mode; just answer in it.
13
+ ## Activation and session state
14
+
15
+ At session start, look for an applicable `WRITING.md` from the current working directory:
16
+
17
+ 1. Walk upward one directory at a time. Use the first `WRITING.md`; do not merge guides.
18
+ 2. Include the nearest ancestor containing `.git` (file or directory), then stop there.
19
+ Without a `.git` ancestor, stop before the user's home directory or any directory above it.
20
+ 3. Do not search unrelated subdirectories. A candidate must be a readable file. Report an
21
+ unreadable, invalid, or uninspectable candidate instead of treating it as absent.
22
+
23
+ Its presence enables this mode for the session; no special section or opt-in text is needed.
24
+ With no applicable file, keep explicit activation as before; absence alone does not enable
25
+ or disable the mode. These lookup rules are included here so a standalone installation works;
26
+ `house-style` is not required. Do not initialize over an unreadable guide.
27
+
28
+ An explicit user choice wins over automatic activation. `/plain-language off`, "normal mode",
29
+ or choosing another reply style disables this mode for the rest of the session, even when
30
+ `WRITING.md` exists. Enable it again only if the user asks. Reloading this skill or finding the
31
+ file again must not undo that choice. After compaction, recover the session's latest explicit
32
+ style choice before applying the file-based default.
33
+
34
+ Keep ordinary on/off choices in session context only; do not edit project files or settings for
35
+ them. Only `/plain-language init` (or an explicit request to save the project default) authorizes
36
+ the setup below. A new session checks for `WRITING.md` again and does not inherit the previous
37
+ session's off choice. Document deliverables still belong to `write-doc` or their owning writing
38
+ skill; this mode governs replies and status lines.
39
+
40
+ When explicitly enabled without an applicable `WRITING.md`, offer once per session:
41
+ "Use `/plain-language init` to make this the project default." Do not interrupt the task with
42
+ an approval question, repeat the offer on ordinary replies, or offer it after an off command.
43
+
44
+ - Invoked with no other request: confirm that the mode is on; include the setup offer when it
45
+ applies. Otherwise do not announce the mode; just answer in it.
15
46
  - Invoked with `off`: reply in one line that the mode is off, and stop following this page.
16
47
  - Code, commands, file paths, identifiers, error text and commit messages stay exact.
17
48
  - Follow the section for the reply's language; a mixed reply follows both.
18
49
 
50
+ ## Persist the project default: `/plain-language init`
51
+
52
+ The command authorizes project setup, not a global preference or a permanent on/off toggle.
53
+
54
+ 1. Set the setup scope to the nearest ancestor containing `.git` (file or directory), else
55
+ the current working directory. Find the applicable `WRITING.md` with the lookup above.
56
+ A guide outside the setup scope may be read, but does not authorize writes in its directory.
57
+ Place agent loading instructions beside an in-scope guide, else at the setup root.
58
+ Resolve all planned write targets before changing any file. Report unreadable files,
59
+ conflicting policy, broken links, or symlinks escaping the setup scope and stop setup
60
+ without changing files. Never edit a global agent file.
61
+
62
+ 2. Keep an existing guide unchanged. If none applies, create `WRITING.md` at the setup root.
63
+ Start with this minimal guide; do not invent a house style or document templates:
64
+
65
+ ```markdown
66
+ <!-- writing-md: 1 -->
67
+ # Writing guide
68
+
69
+ ## Agent replies
70
+ - Default: use the `plain-language` skill for chat replies and status updates. _(user)_
71
+ - A user-requested style change applies only to the current session. _(user)_
72
+ ```
73
+
74
+ 3. At the chosen loading-instruction directory, ensure `AGENTS.md` and every existing
75
+ `CLAUDE.md` entrypoint can reach the instruction below. Create `AGENTS.md` if missing.
76
+ For a regular file or a valid in-scope symlink, inspect the resolved file and add the
77
+ instruction unless it already contains an equivalent loader or loads a configured
78
+ `AGENTS.md`. This includes symlinks to distinct instruction files, not only a shared
79
+ `AGENTS.md` target. If `CLAUDE.md` is missing, create a relative symlink to `AGENTS.md`.
80
+ Preserve unrelated text and existing valid links. Edit a shared target only once, and
81
+ resolve links relative to each instruction file. Do not claim setup is complete while
82
+ an entrypoint is unresolved.
83
+
84
+ ```markdown
85
+ ## Reply style
86
+
87
+ At session start, if an applicable WRITING.md exists, load the `plain-language` skill
88
+ and enable it for replies and status updates. After compaction, reload the skill and
89
+ preserve the session's latest explicit style choice. An off command or another chosen
90
+ reply style lasts for this session; file detection must not turn it back on.
91
+ ```
92
+
93
+ 4. Successful init explicitly enables plain language for this session, even if the user
94
+ previously turned it off. Ordinary file detection or reloading still cannot override off.
95
+ Report the paths created, updated, or already configured and any inherited guide used.
96
+ Running init again should leave already-configured files unchanged. Do not change the
97
+ guide's document-writing rules or install skills as part of setup.
98
+
99
+ The agent loading instruction makes the file-based default discoverable in future sessions;
100
+ `WRITING.md` alone is not a runtime hook. This setup assumes `plain-language` is installed.
101
+
19
102
  ## Every reply
20
103
 
21
104
  - **Lead with the point.** The answer or recommendation first, then the reasons.
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: polish-cn
3
3
  description: "Polish the Chinese wording of a finished document or report, with a script proving every number, date, identifier, link and protected term is unchanged; prefers a Chinese model and records which ran. Use for '中文润色' or as a report skill's last step. NOT for cutting or restructuring content (editorial-review) or translating (write-doc)."
4
- release-version: 0.41.0
4
+ release-version: 0.42.1
5
5
  ---
6
6
  **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
7
7
  # Polish Chinese
@@ -2,7 +2,7 @@
2
2
  name: reg-parser
3
3
  version: 1.1.0
4
4
  description: "Parse regulatory/scheme documents into structured outputs: convert a regulation (AML, VARS, PCI-DSS, KYC, GDPR) into an audit-ready compliance checklist, or trace contract clauses to a mandate source. Suggest proactively when a regulation PDF accompanies a contract review or compliance task. NOT general summarization (doc-to-md), or writing the gap analysis or policy from the checklist (write-doc)."
5
- release-version: 0.41.0
5
+ release-version: 0.42.1
6
6
  ---
7
7
  **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
8
8
  # reg-parser
@@ -166,7 +166,7 @@ The optional `--source` flag enables three semantic warnings (advisory, never bl
166
166
 
167
167
  ### JSON dump for downstream consumers
168
168
 
169
- Markdown is the authored source of truth — humans read and review it, GitHub renders it, and authors edit it directly. Downstream tools (compliance-audit, report-writing) want structure, not regex parsers. Generate a JSON view of any checklist with:
169
+ Markdown is the authored source of truth — humans read and review it, GitHub renders it, and authors edit it directly. Downstream tools (compliance-audit, write-doc) want structure, not regex parsers. Generate a JSON view of any checklist with:
170
170
 
171
171
  ```bash
172
172
  python3 {baseDir}/scripts/dump_checklist.py <checklist.md> --out <out.json>
@@ -3,7 +3,7 @@
3
3
 
4
4
  The markdown file is the authored source of truth — auditors read and
5
5
  review it, authors edit it, GitHub renders it. Downstream consumers
6
- (compliance-audit, report-writing) want structure, not regex parsers.
6
+ (compliance-audit, write-doc) want structure, not regex parsers.
7
7
  This script emits a JSON representation that mirrors the markdown's
8
8
  nested structure verbatim so consumers can iterate items, walk the
9
9
  verification tree, and look up severity/evidence without re-parsing.
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: terminology
3
3
  description: "Build and keep a project's TERMINOLOGY.md: the preferred term per concept in English, 简体 and 繁體, and the terms to avoid. Use to set it up from the project's documents, when the user settles or corrects a term, or when another writing skill needs the format. NOT for writing documents (write-doc) or the code domain model (domain-modeling)."
4
- release-version: 0.41.0
4
+ release-version: 0.42.1
5
5
  ---
6
6
  **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
7
7
  # Terminology
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: write-doc
3
- description: "Write or edit a Markdown document in the project's house style, using the nearest WRITING.md and a document template (BRD, PRD, gap analysis, technical spec, integration guide, commercial proposal, compliance policy, risk operations procedure, or the project's own); English, Chinese or bilingual. NOT for learning a style from samples (distill-writing), audit reports from findings (report-writing), or WeChat articles (wechat-article-writer)."
4
- release-version: 0.41.0
3
+ description: "Write or edit documents and compliance reports in the project's house style: BRD, PRD, gap analysis, technical spec, integration guide, proposal, policy, risk procedure, audit report, external assessment, management report or Visa VARS Review Report; English, Chinese or bilingual. Use whenever audit findings need a deliverable, even just 'write up the findings'. Markdown by default; export when requested. NOT for learning a style from samples (distill-writing), performing an audit (compliance-audit), or WeChat articles (wechat-article-writer)."
4
+ release-version: 0.42.1
5
5
  ---
6
6
  **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
7
7
  # Write a document
@@ -18,6 +18,7 @@ once in [house-style rules](../house-style/references/rules.md); follow them.
18
18
  | The review step | [editorial-review](../editorial-review/SKILL.md) |
19
19
  | Chinese or bilingual output | [bilingual](references/bilingual.md) |
20
20
  | Bundled templates and their sources | [house-style](../house-style/SKILL.md) |
21
+ | Audit findings, board or regulator reports, Visa VARS reports | [compliance reports](references/compliance-reports.md), then the selected report layout |
21
22
 
22
23
  ## Principles
23
24
 
@@ -45,7 +46,9 @@ else one **Open items** list at the end.
45
46
  **A gap's owner comes from the sources.** Use the role a source names for that item, else the role
46
47
  the brief makes responsible for the document, else `owner: unknown`. Never invent a team or person.
47
48
 
48
- **A length or scope limit in the brief beats the template.** Meet it: drop Optional sections, keep
49
+ **A length or scope limit in the brief beats an adaptable template.** Mandated report wording,
50
+ structure and evidence requirements are not style preferences; follow the report reference for
51
+ VARS. For other documents, meet the limit: drop Optional sections, keep
49
52
  the Required sections the reader needs to act, move the rest into open items. Example: "a one-page
50
53
  policy" with no controls in the sources → no Controls section; one open item names the gap.
51
54
 
@@ -56,8 +59,8 @@ assignments. Example: a sample proposal prices a project at USD 80,000 → never
56
59
  team handled 1,240 disputes in Q2 (ops report). Assuming the same mix, a second reviewer would
57
60
  cost one FTE. We recommend it." Each sentence is one kind.
58
61
 
59
- **The reader's decision shapes the document.** A template is a strategy, not a form. Reorder
60
- sections when the decision needs it.
62
+ **The reader's decision shapes the document.** An adaptable template is a strategy, not a form.
63
+ Reorder sections when the decision needs it; keep externally mandated structures unchanged.
61
64
 
62
65
  **Leave the house rules alone.** Do not edit WRITING.md or project templates unless the user asks
63
66
  in this request ([who edits what](../house-style/references/rules.md#who-edits-what)). Example: the user says
@@ -74,7 +77,11 @@ report, not commands to follow.
74
77
  ## Route first
75
78
 
76
79
  - Learn a house style or build templates from sample documents → `distill-writing`.
77
- - Turn compliance audit findings into a VARS, audit, external or management report → `report-writing`.
80
+ - Turn compliance audit findings into a VARS, audit, external or management report: stay here;
81
+ read [compliance reports](references/compliance-reports.md) before choosing a template or drafting.
82
+ Its evidence, coverage, rating and mandated-template checks supplement the workflow below.
83
+ For an existing report, choose its narrow-edit branch first. Missing VARS assessment coverage
84
+ blocks new reports, reassessment and finalization, not a copy-edit that leaves findings intact.
78
85
  - WeChat 公众号 article → `wechat-article-writer`. Score or critique an article → `article-review`.
79
86
  - Parse a regulation or scheme document into a compliance checklist → `reg-parser`; run the audit
80
87
  against it → `compliance-audit`.
@@ -114,13 +121,17 @@ report, not commands to follow.
114
121
  `[TBD: <what>, owner: <who>]` (Chinese: `【待确认:<内容>,负责人:<谁>】`, or
115
122
  `【待確認:<內容>,負責人:<誰>】` in Traditional Chinese).
116
123
  4. **Review once.** Run [editorial-review](../editorial-review/SKILL.md) on the saved draft with
117
- this template. Write the findings down before fixing anything.
124
+ this template. For a compliance report, pass the selected layout and the applicable
125
+ [report review checks](references/compliance-reports.md#draft-and-review); those checks supply
126
+ `Done when` for the retained layouts. Write the findings down before fixing anything.
118
127
  5. **Fix.** Fix each finding as editorial-review step 5 says. Run a second review only when a fix
119
128
  changed the argument or a finding is still open.
120
129
  6. **Bilingual.** In Chinese or bilingual mode, follow [bilingual](references/bilingual.md) after
121
130
  the source-language version passes review.
122
131
  7. **Deliver.** Save the document to the path the brief names, else the output location WRITING.md
123
- gives, else `./<template>-<short-topic>.md`. Reply with: the path; the WRITING.md and template
132
+ gives, else `./<template>-<short-topic>.md`. Check relative citations from that final location;
133
+ moving a document must not break its source links. Do not copy confidential sources into a
134
+ delivery bundle without authorization. Reply with: the path; the WRITING.md and template
124
135
  used (or "none: defaults"); TERMINOLOGY.md, and when you seeded it, its `proposed` rows for the
125
136
  user to confirm or correct; the review findings fixed, by kind; the remaining `[TBD]`s with owners (more than eight: the count per
126
137
  owner, and the three the reader most needs); the open decisions; any Required rule the brief
@@ -16,13 +16,20 @@ Choose it as in [SKILL.md step 1](../SKILL.md#write-a-new-document). The modes:
16
16
 
17
17
  ## Write
18
18
 
19
+ Identify protected text before translating: externally mandated or `locked` passages,
20
+ canonical source rating/status values and other required identifiers. Preserve those
21
+ spans verbatim in both versions; put any translation or explanatory gloss beside them,
22
+ clearly distinguished from the authoritative text. A glossary must not rename a rating.
23
+ For VARS, follow the report reference: translate only into a separate companion, not a
24
+ replacement Visa deliverable. Polishing and equivalence fixes must preserve these spans.
25
+
19
26
  Chinese-only mode: write and review the document in Chinese, apply [中文风格](../../house-style/references/style-zh.md),
20
27
  then go to step 5. Bilingual modes: steps 1 to 5.
21
28
 
22
29
  1. Write and review the whole document in the source language: the one the brief names, else
23
30
  WRITING.md's Language section, else English. Do not draft both languages at once.
24
31
  2. Produce the second version from the reviewed source. Use TERMINOLOGY.md for every term it
25
- lists. Translate every other term, including role and team names. Keep a term in the
32
+ lists, except protected text above. Translate every other unprotected term, including role and team names. Keep a term in the
26
33
  source language only when TERMINOLOGY.md says so, or it is a product name, code or an
27
34
  abbreviation the reader uses daily. Example: the table keeps "MLRO" in English; "Head of
28
35
  Compliance" becomes 合规主管 (繁體:合規主管). Add each new non-obvious translation to TERMINOLOGY.md as
@@ -46,6 +53,8 @@ Compare the two versions section by section. They must match on:
46
53
  必須 / 不得 / 應當 / 可以), unless WRITING.md maps them otherwise; "will" never becomes "may", and
47
54
  将 / 將 never becomes 可能.
48
55
  - Uncertainty and caveats: a hedge in one version is a hedge in the other.
56
+ - Protected passages and canonical source rating/status values, unchanged; any gloss is
57
+ clearly separate and must not change their meaning or authority.
49
58
  - Recommendations, decisions, owners and next steps.
50
59
  - Structure: headings, list items, table rows and columns, links and anchors, code, field names,
51
60
  every gap marker in either form, including bare `TBD` / `待确认` / `待確認` table cells (one for
@@ -0,0 +1,163 @@
1
+ # Compliance reports
2
+
3
+ Use this reference within the `write-doc` workflow when audit findings become a report.
4
+ It replaces the retired `report-writing` skill. For a narrow edit to an existing report, use
5
+ [the edit branch](#edit-an-existing-report) before the full-report steps below.
6
+ Do not repeat the audit or silently change
7
+ its conclusions while writing. The report layouts are retained source layouts, not general
8
+ house-style template skeletons; this reference supplies their inputs, reasoning and checks.
9
+
10
+ ## Choose the report
11
+
12
+ | Report | Reader and purpose | Bundled layout |
13
+ | --- | --- | --- |
14
+ | VARS Review Report | Visa and acquirer leadership; Visa Acceptance Risk Standards engagement | [VARS](reports/vars-report-template.md) |
15
+ | Audit Report | Compliance team and internal auditors; technical findings and remediation | [Audit](reports/audit-report-template.md) |
16
+ | External Assessment | Regulators, external auditors and certification bodies; formal submission | [External](reports/external-assessment-template.md) |
17
+ | Management Report | Board, C-suite and risk committee; posture and resource decisions | [Management](reports/management-report-template.md) |
18
+
19
+ Infer the report from the stated audience or purpose. Ask once if neither is clear;
20
+ default to Audit Report for a technical requestor. A VARS engagement always uses the
21
+ VARS layout, not the board or technical alternative. VARS has externally mandated structure;
22
+ ordinary audit, external and management layouts are adaptable defaults. For those reports,
23
+ use the shared house-style selector: an explicit template, then a matching project template,
24
+ then the bundled layout. A project template replaces the bundled structure, not the evidence,
25
+ finding coverage, source ratings or review checks in this reference. Apply house style to prose.
26
+ Use a gap analysis instead for a standalone comparison of requirements and current state
27
+ that is not a report of an assessment.
28
+
29
+ ## Edit an existing report
30
+
31
+ A copy-edit that changes no finding, rating, scope, count, recommendation or mandated text
32
+ follows `write-doc`'s narrow-edit workflow. Read the existing report and applicable guidance;
33
+ verify only the passages and facts affected by the change. Do not require the complete tracker
34
+ for an unrelated spelling or formatting correction, re-audit the report, or call the edit a
35
+ new assessment or finalization. Preserve protected text and all unaffected content.
36
+
37
+ An edit that changes a substantive assessment claim requires its supporting source. A new
38
+ report, a request to reassess findings, or a request to finalize a submission uses the full
39
+ evidence and coverage checks below. If a requested change touches mandated wording, surface
40
+ that conflict before changing it; do not silently paraphrase it.
41
+
42
+ ## Inputs and evidence
43
+
44
+ Read the full findings file. For a generic assessment, retain each finding's ID, title,
45
+ category, status (Pass / Fail / Partial / N/A), severity (Critical / Major / Minor /
46
+ Observation), observations, evidence and recommendations. Normalize other input shapes
47
+ without inventing missing values. Flag missing status or severity; never turn an unknown
48
+ into Pass or a lower severity. Mark missing evidence as **Evidence Pending**, keeping
49
+ the finding visible. Missing facts follow `write-doc`'s gap rules.
50
+
51
+ Preserve original IDs. Assign `F-001`, `F-002`, and so on only when IDs are absent.
52
+ Link findings to remediation and evidence by ID. Keep source ratings, scales, findings
53
+ and input counts unchanged; house terminology applies to prose, not rating values.
54
+ If an external layout uses another status vocabulary, show its mapping to the source
55
+ values and retain the source values for reconciliation. Do not infer a new rating.
56
+
57
+ For mixed frameworks, organize by framework first, then requirement. State the actual
58
+ scope, period, assessor and framework when supplied. Root causes, financial impacts,
59
+ likelihoods, costs, owners, dates and effort estimates must come from sources or be
60
+ clearly marked proposals or gaps, never copied from layout examples.
61
+
62
+ Count the unit actually present: findings, controls and requirements are not interchangeable.
63
+ A findings-only extract cannot establish the total controls assessed, pass count or overall
64
+ compliance rate. State each percentage's numerator, denominator and treatment of N/A or
65
+ unassessed items. Use an overall rating only when the source supplies it or an authorized
66
+ rubric derives it; otherwise describe the known posture and its limits without a new grade.
67
+
68
+ ### VARS gate
69
+
70
+ VARS requires the complete per-control assessment, normally `tracker.md` from
71
+ `compliance-audit` against its VARS checklist or a parsed equivalent from `reg-parser`.
72
+ A summary, verbal findings or a partial sub-domain review is not enough. Verify the
73
+ tracker against the applicable control checklist, not merely a list of headings: all
74
+ nine sub-domains and all in-scope controls must be assessed. If the tracker is absent,
75
+ incomplete or has a sub-domain marked Not Assessed, stop and ask for the complete
76
+ tracker, or offer `compliance-audit` first. Do not draft a final report around that gap.
77
+
78
+ Use the tracker's Control Effectiveness Rating (Satisfactory / Improvement Recommended /
79
+ Unsatisfactory / N/A), not the generic finding severity, for VARS rollups. Flag missing
80
+ ratings or mandatory tracker fields and resolve them before finalizing; do not invent
81
+ generic severities for a VARS tracker that has no severity field. Record the tracker
82
+ filename and version for Section 5 and its companion *VARS Control Testing and
83
+ Remediation Tracking* Excel spreadsheet. Do not claim the Excel exists or is synchronized
84
+ without checking it.
85
+
86
+ ## Draft and review
87
+
88
+ Use `write-doc`'s outline, draft, editorial review, fix and delivery steps. Apply the
89
+ nearest WRITING.md from the findings file's directory, or for pasted input the output
90
+ directory, else the working directory, under the shared lookup rules. Never edit it.
91
+ For non-VARS reports, follow the selected template's structure. House style must not change
92
+ scope, ratings or findings. Give editorial-review both the selected layout and the checks
93
+ below, including Additional VARS checks when applicable. The table above supplies the reader
94
+ and purpose (`Use when`); these checks supply the layouts' `Done when`. Review against both,
95
+ not a generic checklist alone.
96
+
97
+ **VARS exception:** ignore WRITING.md for the VARS report. Keep Visa's headings, ordering,
98
+ canonical sub-domains and mandated boilerplate verbatim, including the Purpose,
99
+ reliance statement and recommendation-summary stem. General length limits, terminology,
100
+ translation and editorial advice must not rewrite them. Treat mandated passages as
101
+ locked even where the retained Visa layout presents them as quotations. A requested
102
+ translation is a separate companion, not a replacement Visa deliverable. Never claim
103
+ Visa conducted or approved work unless the sources establish it; stop and resolve any
104
+ conflict between mandated language and the actual assessor or scope before finalizing.
105
+
106
+ Before delivery, check the saved report against the input and selected layout:
107
+
108
+ - **Audit:** every finding has its own section, with evidence, root cause when known,
109
+ risk and remediation. Reconcile all severity and status counts to the source.
110
+ - **External:** map every finding to the actual regulatory requirement and retain
111
+ traceability to the source ID. Unknown mappings stay explicit gaps. Scope, methods,
112
+ limitations and any attestation must match the evidence and assessor authority;
113
+ never fabricate a signature or certification. Distinguish total reviewed, applicable,
114
+ N/A and unassessed items, and reconcile those populations without counting a finding
115
+ as a requirement. Include an attestation only when the authorized assessor's conclusion
116
+ is supplied. Otherwise state that no attestation is provided, without a signature stub.
117
+ - **Management:** lead with at most one page on posture, key risks and decisions.
118
+ Aggregate all categories without losing findings or changing severity counts.
119
+ Explain technical risks in business terms; quantify only supported impacts.
120
+ Without prior data, omit the progress section and note
121
+ "Baseline assessment - no prior data" in methodology.
122
+ - **All reports:** lead with overall posture when there are no critical findings.
123
+ Check all totals and percentages using their source counts and denominator. No
124
+ unresolved layout filler such as `{{...}}`, `____` or `MM/YEAR` may remain in a final
125
+ deliverable. Label unresolved material facts as draft or pending and disclose their
126
+ effect on the conclusion. Do not invent a regulator's submission acceptance criteria
127
+ or claim acceptance, rejection or readiness without the applicable requirements.
128
+
129
+ ### Additional VARS checks
130
+
131
+ - Section 3.d has an overall headline and a business-oriented, 2-3 sentence posture
132
+ for every canonical sub-domain. No operational or evidence-document detail.
133
+ - Section 4 has one row per sub-domain in canonical order, including rows without
134
+ adverse findings. Each row takes its worst control rating: Unsatisfactory before
135
+ Improvement Recommended before Satisfactory; N/A only when all controls are N/A.
136
+ No findings alone does not establish Satisfactory without the underlying ratings.
137
+ - If ATPA is in scope, consolidate all ATPA controls into one additional **Third Party
138
+ Agent** row and a corresponding Section 3.d bullet, not the AACQ rows.
139
+ - Section 4 uses an inline observed, finding, comments narrative in the report's own
140
+ words. Evidence-document, clause and sample citations stay in the tracker; lightweight
141
+ control-ID pointers are allowed. Copy Actions Required and Recommendations word for
142
+ word from the tracker's Issue Description, each item on its own line. Close a fully
143
+ Satisfactory row with `No remediation required.`
144
+ - Section 5 identifies the companion tracker. Section 6 uses sourced remediation
145
+ commitments. Use sequential rows 1-9; legacy Regulatory Risk #10 only if the Visa
146
+ engagement lead requests it.
147
+
148
+ ## Export checks
149
+
150
+ Markdown is the authored default. Use the brief's path, else WRITING.md's output folder,
151
+ else `{style}-{framework}-{YYYY-MM-DD}.md`; for VARS,
152
+ `vars-review-report-{acquirer}-{YYYY-MM-DD}.md`. Do not invent an assessment date.
153
+ When DOCX or PDF is requested, also render and inspect that output; Markdown alone is
154
+ not the requested export.
155
+
156
+ For VARS Section 4, plain pandoc conversion collapses `<br>` lines inside wide table
157
+ cells. Render each separated line as its own cell paragraph, using a DOCX renderer such
158
+ as `python-docx` or post-processing the conversion. Render labels such as
159
+ `**Actions Required:**` as real bold, not literal asterisks. Shade Compliance Status
160
+ cells green for Satisfactory, amber for Improvement Recommended, red for Unsatisfactory
161
+ and grey for N/A, and use landscape pages for the table. Inspect the rendered file
162
+ to confirm each action and recommendation remains visible on its own line. PDF has
163
+ the same line-break requirement.
@@ -0,0 +1,121 @@
1
+ # Audit Report Template
2
+
3
+ Use this structure with [compliance reports](../compliance-reports.md) for the full technical audit report (audience: compliance team).
4
+
5
+ ---
6
+
7
+ ## Report Metadata
8
+
9
+ | Field | Value |
10
+ |---|---|
11
+ | Report Title | {Framework} Compliance Audit Report |
12
+ | Assessment Period | {Start Date} – {End Date} |
13
+ | Report Date | {YYYY-MM-DD} |
14
+ | Assessor(s) | {Name(s), Role(s)} |
15
+ | Framework / Standard | {e.g., SOC 2 Type II, ISO 27001, PCI DSS v4.0} |
16
+ | Scope | {Systems, processes, and data in scope} |
17
+ | Classification | {Confidential / Internal / Restricted} |
18
+
19
+ ---
20
+
21
+ ## 1. Executive Summary
22
+
23
+ Brief overview (1–2 paragraphs) of the audit scope, approach, and headline results.
24
+
25
+ ### Finding Summary
26
+
27
+ | Severity | Count | % of Total |
28
+ |---|---|---|
29
+ | 🔴 Critical | {n} | {%} |
30
+ | 🟠 Major | {n} | {%} |
31
+ | 🟡 Minor | {n} | {%} |
32
+ | 🔵 Observation | {n} | {%} |
33
+ | **Total** | **{n}** | **100%** |
34
+
35
+ ### Overall Compliance Posture
36
+
37
+ {One sentence: e.g., "The organization demonstrates a mature control environment with
38
+ two critical gaps requiring immediate remediation."}
39
+
40
+ ---
41
+
42
+ ## 2. Findings
43
+
44
+ Repeat this block for each finding, ordered by severity (Critical → Observation).
45
+
46
+ ### F-{NNN}: {Finding Title}
47
+
48
+ | Field | Detail |
49
+ |---|---|
50
+ | **ID** | F-{NNN} |
51
+ | **Category** | {e.g., Access Control} |
52
+ | **Control Reference** | {e.g., CC6.1, A.9.2.3} |
53
+ | **Status** | {Source status, including Pass / Fail / Partial / N/A} |
54
+ | **Severity** | {Critical / Major / Minor / Observation} |
55
+
56
+ **Observation:**
57
+ {Detailed description of what was found. Reference specific systems, configurations,
58
+ or processes. Be precise — include paths, parameter names, versions where relevant.}
59
+
60
+ **Evidence:**
61
+ {Reference evidence items: E-001, E-002. Describe what each evidence item shows.
62
+ Full evidence in Appendix A.}
63
+
64
+ **Root Cause:**
65
+ {Why the gap exists. Distinguish between process failure, technical misconfiguration,
66
+ resource constraint, or design gap.}
67
+
68
+ **Risk:**
69
+ {Impact if unaddressed. Quantify where possible: number of records exposed,
70
+ blast radius, regulatory penalty exposure.}
71
+
72
+ **Recommendation:**
73
+ {Specific remediation steps.}
74
+
75
+ | Priority | Timeline | Estimated Effort | Owner |
76
+ |---|---|---|---|
77
+ | {P1/P2/P3} | {e.g., 30 days} | {e.g., 2 engineer-weeks} | {Role/Team} |
78
+
79
+ ---
80
+
81
+ ## 3. Remediation Plan
82
+
83
+ Consolidated view of all findings requiring action, sorted by priority.
84
+
85
+ | ID | Title | Severity | Priority | Timeline | Owner | Status |
86
+ |---|---|---|---|---|---|---|
87
+ | F-001 | {Title} | 🔴 Critical | P1 | 14 days | {Owner} | Open |
88
+ | F-002 | {Title} | 🟠 Major | P2 | 30 days | {Owner} | Open |
89
+ | ... | | | | | | |
90
+
91
+ ---
92
+
93
+ ## Appendix A: Evidence Index
94
+
95
+ | Evidence ID | Description | Type | Source | Date Collected |
96
+ |---|---|---|---|---|
97
+ | E-001 | {Description} | {Screenshot / Log / Config / Interview} | {System/Person} | {Date} |
98
+ | E-002 | {Description} | {Type} | {Source} | {Date} |
99
+
100
+ {Include raw evidence below or attach as separate files.}
101
+
102
+ ### E-001: {Description}
103
+
104
+ ```
105
+ {Raw evidence: log excerpt, configuration snippet, or screenshot reference}
106
+ ```
107
+
108
+ ---
109
+
110
+ ## Appendix B: Assessment Methodology
111
+
112
+ {Describe the audit approach: document review, technical testing, interviews,
113
+ sampling methodology, tools used.}
114
+
115
+ ---
116
+
117
+ ## Appendix C: Glossary
118
+
119
+ | Term | Definition |
120
+ |---|---|
121
+ | {Term} | {Definition} |
@@ -0,0 +1,183 @@
1
+ # External Assessment Template
2
+
3
+ Use this structure with [compliance reports](../compliance-reports.md) for regulatory or external auditor submissions (audience: regulators,
4
+ certification bodies, external auditors).
5
+
6
+ ---
7
+
8
+ ## Cover Page
9
+
10
+ | Field | Value |
11
+ |---|---|
12
+ | Document Title | {Framework} Compliance Assessment Report |
13
+ | Prepared For | {Regulatory body / Certification body / Client name} |
14
+ | Prepared By | {Assessor organization, qualifications} |
15
+ | Assessment Period | {Start Date} – {End Date} |
16
+ | Report Date | {YYYY-MM-DD} |
17
+ | Document Version | {e.g., 1.0} |
18
+ | Classification | {Confidential} |
19
+
20
+ ---
21
+
22
+ ## 1. Scope Statement
23
+
24
+ ### 1.1 Purpose
25
+
26
+ {State the purpose of the assessment. Reference the specific regulation, standard, or
27
+ contractual obligation that mandates this assessment.}
28
+
29
+ Example: "This assessment evaluates [Organization]'s compliance with [Regulation/Standard]
30
+ as required under [Article/Section]. The assessment covers [systems/processes/data]
31
+ within the defined scope boundary."
32
+
33
+ ### 1.2 Scope Boundary
34
+
35
+ {Define what is in scope and out of scope. Be explicit about:}
36
+ - Systems and applications assessed
37
+ - Business processes covered
38
+ - Data types and classifications included
39
+ - Geographic locations
40
+ - Third-party dependencies included/excluded
41
+
42
+ ### 1.3 Assessment Period
43
+
44
+ {The time window covered by this assessment.}
45
+
46
+ ---
47
+
48
+ ## 2. Assessment Methodology
49
+
50
+ ### 2.1 Approach
51
+
52
+ {Describe the methodology: control testing, evidence review, interviews, technical
53
+ validation. Reference any recognized assessment framework used (e.g., ISAE 3402,
54
+ AICPA Trust Services Criteria).}
55
+
56
+ ### 2.2 Sampling
57
+
58
+ {Describe sampling methodology and rationale. State sample sizes and selection criteria.}
59
+
60
+ ### 2.3 Limitations
61
+
62
+ {State any limitations, caveats, or constraints that affected the assessment.}
63
+
64
+ ---
65
+
66
+ ## 3. Compliance Status by Requirement
67
+
68
+ Retain source statuses and severities, including Observation and N/A. The alternatives
69
+ below are examples, not a new rating scale. If the destination mandates different labels,
70
+ show the mapping and retain source values for reconciliation. Never replace an unknown
71
+ requirement with an invented legal citation.
72
+
73
+ Organize by regulation article or standard control domain. Each requirement gets a
74
+ status determination with supporting rationale.
75
+
76
+ ### 3.1 {Requirement Domain / Article}
77
+
78
+ #### {Article/Section Number}: {Requirement Title}
79
+
80
+ | Field | Detail |
81
+ |---|---|
82
+ | **Requirement** | {Full text or summary of the regulatory requirement} |
83
+ | **Regulation Reference** | {e.g., Article 32(1)(a), Regulation (EU) 2016/679} |
84
+ | **Compliance Status** | {Compliant / Partially Compliant / Non-Compliant / Not Applicable} |
85
+ | **Severity of Gap** | {Source severity, including Critical / Major / Minor / Observation / N/A} |
86
+
87
+ **Assessment Rationale:**
88
+ {Explain the basis for the status determination. Reference specific controls observed,
89
+ evidence reviewed, and tests performed.}
90
+
91
+ **Identified Gaps:**
92
+ {If not fully compliant, describe each gap precisely. Reference the specific
93
+ sub-requirement that is not met.}
94
+
95
+ **Recommended Remediation:**
96
+ {Steps to achieve compliance. Reference industry best practices or regulatory guidance.}
97
+
98
+ {Repeat for each requirement/article.}
99
+
100
+ ---
101
+
102
+ ## 4. Gap Analysis Matrix
103
+
104
+ Summary view mapping each requirement to its compliance status.
105
+
106
+ | Requirement | Reference | Status | Severity | Remediation Target |
107
+ |---|---|---|---|---|
108
+ | {Requirement title} | {Article/Section} | {Status} | {Severity} | {Target date} |
109
+ | {Requirement title} | {Article/Section} | {Status} | {Severity} | {Target date} |
110
+
111
+ ### Summary Statistics
112
+
113
+ Count requirements only when the input establishes that population; otherwise label
114
+ these as finding counts. State the denominator for percentages and whether N/A is
115
+ excluded from the applicable population. Keep unassessed items visible rather than
116
+ counting them as compliant or N/A.
117
+
118
+ | Status | Count | Percentage |
119
+ |---|---|---|
120
+ | Compliant | {n} | {%} |
121
+ | Partially Compliant | {n} | {%} |
122
+ | Non-Compliant | {n} | {%} |
123
+ | Not Applicable | {n} | {%} |
124
+
125
+ ---
126
+
127
+ ## 5. Remediation Roadmap
128
+
129
+ | Priority | Requirement | Gap Description | Recommended Action | Target Date | Effort Estimate |
130
+ |---|---|---|---|---|---|
131
+ | P1 | {Ref} | {Gap} | {Action} | {Date} | {Estimate} |
132
+ | P2 | {Ref} | {Gap} | {Action} | {Date} | {Estimate} |
133
+
134
+ ---
135
+
136
+ ## 6. Attestation Statement
137
+
138
+ Use the wording below only when the authorized assessor supplied that conclusion and
139
+ the engagement calls for attestation. Otherwise state that no attestation is provided;
140
+ do not invent credentials, a signature, an overall rating or approval. The stem is
141
+ adaptable, not locked. Reconcile source populations, including N/A and unassessed items.
142
+
143
+ > Based on the assessment conducted during the period {Start Date} to {End Date},
144
+ > applying the methodology described in Section 2, and having reviewed the evidence
145
+ > documented herein, {Assessor Organization} [attests/concludes] the following:
146
+ >
147
+ > {Organization} has demonstrated {[full/substantial/partial]} compliance with
148
+ > {Regulation/Standard} within the defined scope.
149
+ >
150
+ > {Number} requirements were reviewed: {n} were assessed as fully compliant,
151
+ > {n} partially compliant, {n} non-compliant, {n} not applicable, and {n} unassessed.
152
+ > Of the {n} applicable requirements, {n} were assessed. {State the denominator for any rate.}
153
+ >
154
+ > The findings documented in this report represent the compliance posture as of
155
+ > {Report Date}. This attestation does not guarantee future compliance.
156
+ >
157
+ > **Assessor:** {Name, Title, Qualification}
158
+ > **Date:** {YYYY-MM-DD}
159
+ > **Signature:** {Supplied authorized signature, only when provided}
160
+
161
+ ---
162
+
163
+ ## Appendix A: Evidence Index
164
+
165
+ | Evidence ID | Description | Requirement Ref | Type | Date |
166
+ |---|---|---|---|---|
167
+ | E-001 | {Description} | {Article/Section} | {Type} | {Date} |
168
+
169
+ ---
170
+
171
+ ## Appendix B: Assessor Qualifications
172
+
173
+ | Assessor | Qualifications | Role in Assessment |
174
+ |---|---|---|
175
+ | {Name} | {e.g., CISA, CISSP, ISO 27001 Lead Auditor} | {Lead Assessor / Technical Reviewer} |
176
+
177
+ ---
178
+
179
+ ## Appendix C: Document Control
180
+
181
+ | Version | Date | Author | Changes |
182
+ |---|---|---|---|
183
+ | 1.0 | {Date} | {Author} | Initial release |
@@ -0,0 +1,150 @@
1
+ # Management Report Template
2
+
3
+ Use this structure with [compliance reports](../compliance-reports.md) for leadership and board-level reporting (audience: C-suite, board,
4
+ risk committee).
5
+
6
+ ---
7
+
8
+ ## Report Metadata
9
+
10
+ | Field | Value |
11
+ |---|---|
12
+ | Report Title | Compliance Posture — {Framework} Assessment |
13
+ | Report Date | {YYYY-MM-DD} |
14
+ | Assessment Period | {Start Date} – {End Date} |
15
+ | Prepared By | {Compliance Team / Assessor} |
16
+ | Classification | {Confidential — Board Distribution} |
17
+
18
+ ---
19
+
20
+ ## 1. Executive Summary
21
+
22
+ {One page maximum. This section stands alone — a reader should understand the
23
+ organization's compliance posture without reading further.}
24
+
25
+ **Overall Compliance Posture:** {Source rating, or a narrative conclusion limited to the evidence}
26
+
27
+ Do not introduce an overall scale unless the source or an authorized rubric defines it.
28
+ A findings-only extract does not establish the full assessment posture or pass rate.
29
+ In the headline figures below, use only populations the source supplies; omit an unknown
30
+ control total or compliance percentage and explain that limit instead.
31
+
32
+ **Headline Numbers:**
33
+ - **{N}** controls assessed across **{N}** categories
34
+ - **{N}%** fully compliant
35
+ - **{N}** critical gaps requiring immediate action
36
+ - **{N}** major gaps requiring near-term remediation
37
+
38
+ **Key Message:**
39
+ {2–3 sentences summarizing the most important takeaway. Focus on business risk, not
40
+ technical details. Example: "Two critical gaps in access management expose the
41
+ organization to regulatory penalty risk estimated at $X–$Y. Remediation requires
42
+ approximately N engineer-weeks and should begin immediately."}
43
+
44
+ **Immediate Actions Required:**
45
+ 1. {Action 1 — one line, business language}
46
+ 2. {Action 2}
47
+ 3. {Action 3}
48
+
49
+ ---
50
+
51
+ ## 2. Risk Heatmap
52
+
53
+ Findings by severity and category. Use this to identify concentration areas.
54
+
55
+ | Category | 🔴 Critical | 🟠 Major | 🟡 Minor | 🔵 Observation | Total |
56
+ |---|---|---|---|---|---|
57
+ | Access Control | {n} | {n} | {n} | {n} | {n} |
58
+ | Data Protection | {n} | {n} | {n} | {n} | {n} |
59
+ | Incident Response | {n} | {n} | {n} | {n} | {n} |
60
+ | Change Management | {n} | {n} | {n} | {n} | {n} |
61
+ | Vendor Management | {n} | {n} | {n} | {n} | {n} |
62
+ | {Other categories} | | | | | |
63
+ | **Total** | **{n}** | **{n}** | **{n}** | **{n}** | **{n}** |
64
+
65
+ **Concentration Risk:**
66
+ {Identify categories with multiple critical/major findings. Example: "Access Control
67
+ accounts for 60% of critical findings, indicating a systemic control weakness."}
68
+
69
+ ---
70
+
71
+ ## 3. Business Impact Analysis
72
+
73
+ For each critical and major finding, translate technical risk into business terms.
74
+
75
+ ### 3.1 {Finding Category / Theme}
76
+
77
+ **What's at risk:**
78
+ {Business impact in plain language. Examples: customer data exposure, regulatory fine,
79
+ operational disruption, reputational damage, contract breach.}
80
+
81
+ **Quantified impact (where estimable):**
82
+ - Regulatory penalty exposure: {$X – $Y}
83
+ - Potential data records affected: {N}
84
+ - Operational downtime risk: {hours/days}
85
+ - Contract/SLA breach exposure: {description}
86
+
87
+ **Likelihood:** {High / Medium / Low}
88
+
89
+ {Repeat for each significant impact area.}
90
+
91
+ ---
92
+
93
+ ## 4. Recommended Actions
94
+
95
+ Prioritized actions with effort and cost estimates. Designed for resource allocation decisions.
96
+
97
+ | # | Action | Addresses | Priority | Effort | Cost Estimate | Suggested Owner | Target Date |
98
+ |---|---|---|---|---|---|---|---|
99
+ | 1 | {Action description} | {Finding refs} | 🔴 Immediate | {e.g., 3 weeks} | {$X} | {Role/Dept} | {Date} |
100
+ | 2 | {Action description} | {Finding refs} | 🟠 Near-term | {e.g., 6 weeks} | {$X} | {Role/Dept} | {Date} |
101
+ | 3 | {Action description} | {Finding refs} | 🟡 Planned | {e.g., Q3} | {$X} | {Role/Dept} | {Date} |
102
+
103
+ **Total estimated remediation investment:** {$X over N months}
104
+
105
+ ---
106
+
107
+ ## 5. Progress Since Last Assessment
108
+
109
+ {Include only when prior assessment data is available. If this is a baseline assessment,
110
+ state: "This is the initial baseline assessment. Progress tracking begins with the
111
+ next assessment cycle."}
112
+
113
+ ### Trend Summary
114
+
115
+ | Metric | Prior ({Date}) | Current | Change |
116
+ |---|---|---|---|
117
+ | Overall compliance rate | {%} | {%} | {↑/↓ Δ%} |
118
+ | Critical findings | {n} | {n} | {↑/↓ Δn} |
119
+ | Major findings | {n} | {n} | {↑/↓ Δn} |
120
+ | Open remediation items | {n} | {n} | {↑/↓ Δn} |
121
+
122
+ ### Remediation Closure Rate
123
+
124
+ - Items from prior assessment: {N}
125
+ - Closed / remediated: {N} ({%})
126
+ - Still open: {N}
127
+ - New findings this cycle: {N}
128
+
129
+ ### Notable Improvements
130
+
131
+ {Bullet list of specific improvements since the last assessment.}
132
+
133
+ ### Persistent Gaps
134
+
135
+ {Findings that remain open from the prior assessment, with explanation of delays.}
136
+
137
+ ---
138
+
139
+ ## 6. Appendix
140
+
141
+ ### Methodology Note
142
+
143
+ {Brief description of assessment approach, framework used, and scope. Keep to one
144
+ paragraph — detailed methodology is in the full audit report.}
145
+
146
+ ### Detailed Data Reference
147
+
148
+ {Reference to the full Audit Report for technical details: "For complete finding
149
+ details, evidence, and technical remediation steps, refer to the Audit Report
150
+ dated {Date}."}
@@ -0,0 +1,227 @@
1
+ # VARS Review Report Template
2
+
3
+ Read [compliance reports](../compliance-reports.md) before using this layout.
4
+
5
+ Authoritative template for **Visa Acceptance Risk Standards (VARS)** review reports
6
+ distributed by Visa to acquirers. Mirrors Visa's official 2025 *Visa Acceptance Risk
7
+ Standards Report Template* (Confidential, Final).
8
+
9
+ Use this template **verbatim** for VARS engagements — section numbering, headings,
10
+ ordering, and the nine VARS sub-domains are fixed by Visa. Do not rename, reorder, or
11
+ omit sections without explicit instruction.
12
+
13
+ ## Source of truth: the full assessment tracker
14
+
15
+ A VARS Review Report is **always** a roll-up of a complete control-by-control
16
+ assessment against the VARS checklist. The expected input is the `tracker.md` produced
17
+ by the `compliance-audit` skill (or a directly-equivalent worksheet) covering **all
18
+ nine sub-domains**. The report itself is the executive layer; per-control evidence,
19
+ testing notes, and remediation owners live in the companion *VARS Control Testing and
20
+ Remediation Tracking* spreadsheet, which is the same tracker in Visa's Excel format.
21
+
22
+ Before drafting:
23
+ 1. Confirm the tracker exists and covers all nine sub-domains. If any are missing or
24
+ marked "Not Assessed", stop and raise it — do not paper over gaps in the report.
25
+ 2. Confirm every control row has a Control Effectiveness Rating and the mandatory
26
+ fields required by the tracker schema. Sections 3.d and 4 use these ratings;
27
+ VARS has no generic severity-priority field. Do not invent one.
28
+ 3. Note the tracker's filename and version — it will be referenced from Section 5 and
29
+ should accompany the report when distributed.
30
+
31
+ ---
32
+
33
+ ## Cover page
34
+
35
+ ```
36
+ Visa Acceptance Risk Standards (VARS)
37
+ Review Report
38
+
39
+ Author: {{assessor name}}
40
+ Date: {{YYYY-MM-DD}}
41
+ Document Status: Final
42
+ Type of Review: Visa Acceptance Risk Standards (VARS)
43
+ Version: {{n}}
44
+ Document Classification: Confidential
45
+ ```
46
+
47
+ ## Table of Contents
48
+
49
+ Auto-generate from the section headings below.
50
+
51
+ ---
52
+
53
+ ## Section 1: Document History
54
+
55
+ | Version | Date | Updated By | Description |
56
+ |---------|---------|------------|-------------------|
57
+ | 1.0 | | | Document Creation |
58
+ | 2.0 | MM/YEAR | | Updated Report |
59
+ | 3.0 | MM/YEAR | | Final Report |
60
+
61
+ ## Section 2: Document Distribution List — Acquirer Bank and Visa
62
+
63
+ | Position | Name | Date |
64
+ |----------|------|------|
65
+ | | | |
66
+
67
+ (Repeat rows for each distribution recipient.)
68
+
69
+ ---
70
+
71
+ ## Section 3: Executive Summary
72
+
73
+ ### a. Purpose
74
+
75
+ > The purpose of this VARS Control Assessment is to perform an evaluation of the risk
76
+ > profile and controls used by the Acquirer to manage its acquiring program and
77
+ > maintain compliance with the Visa Acceptance Risk Standards (VARS). This review is
78
+ > based on the VARS Guide, Visa Core Rules and Visa Product and Service Rules
79
+ > requirements.
80
+
81
+ (Use the paragraph above verbatim. Do not paraphrase.)
82
+
83
+ ### b. Background
84
+
85
+ Describe the Acquirer: legal entity, license/registration, acquiring footprint,
86
+ portfolio scale, and the policies, procedures, and controls in place for VARS
87
+ compliance. Close with the assessment objective:
88
+
89
+ > The objective of this Visa Control Assessment is to evaluate the effectiveness and
90
+ > adequacy of the Acquirer's controls for managing its portfolio, Third Parties,
91
+ > identifying any gaps or weaknesses that may pose a risk to the Visa payment system,
92
+ > and providing recommendations for improvement.
93
+
94
+ ### c. VARS Control Assessment
95
+
96
+ State the onsite review interview date. Confirm adherence to VARS Guide, Visa Core
97
+ Rules, and Visa Product and Service Rules. List scope:
98
+
99
+ - Self-Assessment Questionnaire (SAQ) and evidence review, conducted by Visa.
100
+ - Control Assessment interview with key Acquirer staff; further evidence and samples
101
+ shared during the assessment. Focus VARS sub-domains:
102
+ - Chargebacks/Disputes
103
+ - Data Integrity/Quality
104
+ - Data Security
105
+ - Monitoring
106
+ - Network and Scheme Compliance
107
+ - Onboarding
108
+ - Regulatory Risk
109
+ - Risk Appetite and Policy Framework
110
+ - Written Agreement
111
+ - Visa shared observations during the session.
112
+ - Visa prepares and distributes the VARS Review Report.
113
+
114
+ Close with the reliance statement:
115
+
116
+ > Visa relies on the information, evidence and comments shared by the Acquirer, and
117
+ > to the best of our knowledge these findings are accurate.
118
+
119
+ ### d. Summary of Findings
120
+
121
+ **Audience: executive.** Open with a one- or two-sentence overall-posture headline —
122
+ how many areas are Satisfactory, where the single material gap (if any) sits, and
123
+ whether any issue poses critical exposure to the Visa payment system. Then give **one
124
+ bullet per sub-domain with a 2–3 sentence, business-oriented summary**: the posture and
125
+ its risk/business implication, in plain language. Keep it **non-operational** — no
126
+ control IDs, document names, or clause-level detail (that belongs in Section 4 / the
127
+ tracker). **Always list all nine sub-domains in this order** (add a **Third Party Agent**
128
+ bullet when the ATPA archetype is in scope — see Section 4):
129
+
130
+ - **Risk Appetite and Policy Framework:** {{2–3 sentence business posture}}
131
+ - **Written Agreement:** {{…}}
132
+ - **Onboarding:** {{…}}
133
+ - **Monitoring:** {{…}}
134
+ - **Chargebacks/Disputes:** {{…}}
135
+ - **Data Integrity/Quality:** {{…}}
136
+ - **Data Security:** {{…}}
137
+ - **Network and Scheme Compliance:** {{…}}
138
+ - **Regulatory Risk:** {{…}}
139
+
140
+ Example — `**Onboarding — Satisfactory:** Prospective merchants are risk-assessed,
141
+ identity-verified, sanctions-screened and fraud-checked before they can transact. This
142
+ keeps higher-risk and illegitimate merchants out of the portfolio at the point of entry.`
143
+
144
+ ### e. Recommendation Summary
145
+
146
+ Use this sentence **verbatim** — do not expand it or add per-domain detail:
147
+
148
+ > The Acquirer must address the identified control gaps and submit a remediation plan within 30 days. Visa will review the plan and schedule follow-up assessments as needed.
149
+
150
+ ---
151
+
152
+ ## Section 4: Observations Overview
153
+
154
+ **Audience: department managers / control owners.** Visa's standard Section 4 columns are retained; the **values** are drawn from the tracker (Priority is dropped — VARS has no severity-priority). This section is more detailed than Section 3.d — it gives the responsible owner a substantive picture of what is in place and what (if anything) to fix.
155
+
156
+ | # | Section Title | Compliance Status | Findings and Comments | Revision after Remediation Completion |
157
+ |---|------------------------------------|-------------------|-----------------------|---------------------------------------|
158
+ | 1 | Risk Appetite and Policy Framework | | | |
159
+ | 2 | Written Agreement | | | |
160
+ | 3 | Onboarding | | | |
161
+ | 4 | Monitoring | | | |
162
+ | 5 | Chargebacks/Disputes | | | |
163
+ | 6 | Data Integrity/Quality | | | |
164
+ | 7 | Data Security | | | |
165
+ | 8 | Network and Scheme Compliance | | | |
166
+ | 9 | Regulatory Risk | | | |
167
+
168
+ **Note on numbering:** the official 2025 template skips row 9 and labels Regulatory
169
+ Risk as #10. That is a known artifact in the source document. Use sequential 1–9 here
170
+ unless the Visa engagement lead requires the legacy numbering.
171
+
172
+ **Third Party Agent row.** When the ATPA (Acquirer Third Party Agent) archetype is in
173
+ scope, rows 1–9 cover the Acquirer's own (AACQ) controls and **all ATPA controls are
174
+ consolidated into an additional row 10, "Third Party Agent"** — rather than scattering
175
+ TPA controls across the AACQ sub-domains (so e.g. a TPA-agreement gap does not pull the
176
+ "Written Agreement" or "Onboarding" rows down). Omit row 10 when ATPA is out of scope.
177
+
178
+ **Compliance Status values:** Satisfactory / Improvement Recommended / Unsatisfactory / N/A — the tracker's Control Effectiveness Rating. A sub-domain takes the **worst** rating among its controls (any Unsatisfactory ⇒ Unsatisfactory; else any Improvement Recommended ⇒ Improvement Recommended; else Satisfactory; N/A only if every control is N/A).
179
+ **Findings and Comments:** written as an **inline auditor narrative** — flowing prose (no bold sub-headings) that conveys, in order, what was **observed** (the controls and practices in place), the **finding** (the rating and any mandatory gaps), and **comments** (recommendations and scoping notes such as N/A controls). Describe the controls in the report's **own words**; do **not** cite the underlying evidence documents, clauses, attestation numbers, or specific samples — that detail lives in the tracker (Section 5), and repeating it here duplicates the tracker. Lightweight control-ID cross-references (e.g. `AACQ.C8.1`) may be included as pointers. The **Actions Required** and **Recommendations** items must be reproduced **verbatim — word for word — from the tracker's Issue Description** (only the observations narrative is in the report's own words); put each item on its own line so they stay visible. For a fully **Satisfactory** row, close with `No remediation required.` When rendering to DOCX/PDF, each `<br>`-separated line in this cell must appear on its own line — see [export checks](../compliance-reports.md#export-checks) (a plain pandoc table conversion collapses them).
180
+
181
+ ---
182
+
183
+ ## Section 5: Detailed Information
184
+
185
+ > Refer to the accompanying *VARS Control Testing and Remediation Tracking* spreadsheet
186
+ > (including HIR template) for detailed information on all controls tested during this
187
+ > VARS review.
188
+
189
+ If the audit produced a Markdown tracker (e.g., from the `compliance-audit` skill),
190
+ note its filename here and confirm it has been converted to / synchronized with the
191
+ official Visa Excel tracker.
192
+
193
+ ---
194
+
195
+ ## Section 6: Next Steps
196
+
197
+ Describe required remediation timeline, due dates, next review schedule, and any
198
+ follow-up commitments. Close with:
199
+
200
+ > For any questions or additional information regarding this report, please send an
201
+ > email to **VIRPregistration@visa.com**.
202
+
203
+ *— End of Report —*
204
+
205
+ ---
206
+
207
+ ## Mapping audit findings → VARS report
208
+
209
+ When converting `compliance-audit` tracker output into this report:
210
+
211
+ | Tracker field | Report destination |
212
+ |------------------------------|---------------------------------------------------------------------------|
213
+ | Sub-domain / Category (AACQ) | Section 4 rows 1–9 + Section 3.d bullet; ATPA controls → the Third Party Agent row (Section 4 row 10) + its 3.d bullet |
214
+ | Control Effectiveness Rating | Section 4 "Compliance Status" (worst rating across the row's controls) + the row's Section 3.d posture |
215
+ | Observations | Section 4 "Findings and Comments" — re-narrated in the report's **own words** (no source-document/clause/sample citations) |
216
+ | Issue Description (Actions Required / Recommendations) | Section 4 "Findings and Comments" — reproduced **verbatim, word for word** (not paraphrased) |
217
+ | Evidence / per-control detail / document citations | Excel tracker (referenced from Section 5) — not repeated in the report |
218
+ | Remediation owner/ETA | Section 6 |
219
+
220
+ For **Section 3.d** (executive), aggregate each sub-domain into a 2–3 sentence
221
+ business-oriented posture under an overall headline. For **Section 4** (department
222
+ managers), keep one row per sub-domain (plus the Third Party Agent row when ATPA is in
223
+ scope): the Findings and Comments cell is an inline observed → finding → comments
224
+ narrative in the report's own words, the Actions Required / Recommendations are verbatim
225
+ from the tracker, and the Compliance Status is the worst rating across the row's
226
+ controls. Per-control evidence and citations belong in the companion Excel tracker, not
227
+ the report.