@1aboveio/core-skills 0.1.14 → 0.1.16
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 +2 -2
- package/skills/distill-writing/SKILL.md +7 -1
- package/skills/doc-to-md/SKILL.md +1 -1
- package/skills/editorial-review/SKILL.md +1 -1
- package/skills/house-style/SKILL.md +1 -1
- package/skills/house-style/references/persistence.md +8 -3
- package/skills/house-style/scripts/init-guidance.mjs +1 -1
- package/skills/plain-language/SKILL.md +1 -1
- package/skills/polish-cn/SKILL.md +1 -1
- package/skills/reg-parser/SKILL.md +1 -1
- package/skills/terminology/SKILL.md +1 -1
- package/skills/terminology/references/init.md +11 -0
- package/skills/write-doc/SKILL.md +1 -1
- package/skills/write-report/SKILL.md +1 -1
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@1aboveio/core-skills",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.16",
|
|
4
4
|
"description": "Shared writing and document foundation: house style, plain-language replies, editorial review, Chinese polish, terminology, write-doc, write-report, 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": "
|
|
30
|
+
"digest": "9ebeb4b0ab9e0e1fd172c49972d829ce629af81178dba361927d8e52c72342c7"
|
|
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, or save an explicitly stated project document preference, into WRITING.md and writing/templates/. Use for sample-based style learning, house-style setup or refresh, and requests such as 'remember this for future PRDs' or 'make this our report default', including handoffs from write-doc, write-report or plain-language. Preserve manual edits and separate document types. NOT for drafting a document (write-doc) or analytical report (write-report) or saving chat-only preferences (plain-language)."
|
|
4
|
-
release-version: 0.
|
|
4
|
+
release-version: 0.48.0
|
|
5
5
|
---
|
|
6
6
|
**Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
|
|
7
7
|
# Distill a writing style
|
|
@@ -81,6 +81,12 @@ and the patterns supported by the approved documents.
|
|
|
81
81
|
guide, and `TERMINOLOGY.md` by the [terminology setup](../terminology/references/init.md). Existing:
|
|
82
82
|
follow [updating](references/updating.md). Keep at most three short annotated excerpts; sanitize
|
|
83
83
|
names and numbers in them.
|
|
84
|
+
After explicit project style setup, make the result discoverable through the scoped agent
|
|
85
|
+
entrypoints using [the document loader](../house-style/references/persistence.md#make-the-saved-policy-discoverable).
|
|
86
|
+
That step installs only the missing loader within its preservation and scope rules; it does
|
|
87
|
+
not save extra preferences or rerun initialization. Future drafting uses `write-doc` and
|
|
88
|
+
analytical reports use `write-report`, not this style-learning workflow. A guide link alone
|
|
89
|
+
is not a skill-routing rule. Report unreachable entrypoints or unavailable writer skills.
|
|
84
90
|
6. **Test transfer.** Pick a topic none of the references cover. Write its first one or two sections
|
|
85
91
|
with `write-doc` (documents) or `write-report` (analytical reports) using the new files. Compare them with the references: voice, terms, structure,
|
|
86
92
|
presentation. Fix each rule that did not carry over or that copied a reference fact. Do not save
|
|
@@ -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.
|
|
4
|
+
release-version: 0.48.0
|
|
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, write-report and domain report skills. NOT for Chinese wording (polish-cn) or code review (better-review)."
|
|
4
|
-
release-version: 0.
|
|
4
|
+
release-version: 0.48.0
|
|
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.
|
|
6
|
+
release-version: 0.48.0
|
|
7
7
|
---
|
|
8
8
|
**Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
|
|
9
9
|
# House style
|
|
@@ -73,11 +73,13 @@ do not save a rule that would weaken them. Explain the conflict instead.
|
|
|
73
73
|
|
|
74
74
|
## Make the saved policy discoverable
|
|
75
75
|
|
|
76
|
-
At the guide's in-scope directory
|
|
77
|
-
|
|
76
|
+
At the guide's in-scope directory (or the glossary's directory for explicit terminology-only
|
|
77
|
+
setup without `WRITING.md`), ensure `AGENTS.md` and every existing `CLAUDE.md` entrypoint
|
|
78
|
+
can reach this instruction, adapted to the correct relative guidance paths:
|
|
78
79
|
|
|
79
80
|
```markdown
|
|
80
|
-
|
|
81
|
+
Before document drafting and editing, read and apply `write-doc`; for analytical reports,
|
|
82
|
+
read and apply `write-report`. After context loss, reload the applicable skill rules.
|
|
81
83
|
Follow their shared nearest-WRITING.md lookup.
|
|
82
84
|
Read the applicable guide and its selected project template before writing. Save a preference
|
|
83
85
|
only when explicitly asked; keep reply preferences separate from document rules.
|
|
@@ -88,6 +90,9 @@ An entrypoint already loading a configured local agent file needs no duplicate i
|
|
|
88
90
|
Preserve other content and valid links, including distinct in-scope symlink targets. Do not
|
|
89
91
|
claim persistence setup is complete while an entrypoint is unresolved. Reply-preference setup
|
|
90
92
|
uses `plain-language`'s own loader instead; mixed saves may need both loaders without duplicates.
|
|
93
|
+
Terminology-only setup requires reading the applicable `TERMINOLOGY.md` but does not create
|
|
94
|
+
a missing writing guide or invoke writer initialization. A pre-existing equivalent writer
|
|
95
|
+
loader stays unchanged; this setup adds missing routing, not a policy refresh.
|
|
91
96
|
|
|
92
97
|
## Report the result
|
|
93
98
|
|
|
@@ -5,7 +5,7 @@ import os from 'node:os';
|
|
|
5
5
|
|
|
6
6
|
const WRITING = '<!-- writing-md: 1 -->\n# Writing guide\n\nProject document preferences are not yet saved; bundled defaults apply.\n\n## Terms\n\nTerms: see [TERMINOLOGY.md](TERMINOLOGY.md).\n';
|
|
7
7
|
const TERMS = '# Terminology\n\n## Terms\n\n| Concept | English | 简体 | 繁體 | Avoid | Meaning | Status | Source |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n';
|
|
8
|
-
const LOADER = '## Document guidance\n\nFor document drafting and editing, use `write-doc`; for analytical reports, use `write-report`. Read the applicable `WRITING.md` and `TERMINOLOGY.md`. Save future preferences only when explicitly requested; automatic skill selection does not initialize guidance.\n';
|
|
8
|
+
const LOADER = '## Document guidance\n\nFor document drafting and editing, use `write-doc`; for analytical reports, use `write-report`. Read the applicable `WRITING.md` and `TERMINOLOGY.md`. Save future preferences only when explicitly requested; automatic skill selection does not initialize guidance.\nAfter context loss, read and apply the applicable writer skill again before continuing.\n';
|
|
9
9
|
const inside = (root, p) => p === root || (!path.relative(root, p).startsWith('..' + path.sep) && path.relative(root, p) !== '..' && !path.isAbsolute(path.relative(root, p)));
|
|
10
10
|
const home = fs.realpathSync(os.homedir());
|
|
11
11
|
const result = { scope: null, start: null, projectBoundary: null, inherited: null, missingInputs: [], files: [], errors: [] };
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: plain-language
|
|
3
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 for /plain-language, 'talk plainly', '说人话', and explicit requests to remember project reply preferences; /plain-language init persists the default and loading instructions. Save reply rules only under Agent replies; route document preferences to distill-writing. Ordinary mode toggles remain session-only. Turn off with '/plain-language off' or 'normal mode'. NOT for writing a document (write-doc) or analytical report (write-report) or reviewing one (editorial-review)."
|
|
4
|
-
release-version: 0.
|
|
4
|
+
release-version: 0.48.0
|
|
5
5
|
---
|
|
6
6
|
**Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
|
|
7
7
|
# Plain language
|
|
@@ -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 or write-report)."
|
|
4
|
-
release-version: 0.
|
|
4
|
+
release-version: 0.48.0
|
|
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), writing a gap-analysis report (write-report), or writing a policy from the checklist (write-doc)."
|
|
5
|
-
release-version: 0.
|
|
5
|
+
release-version: 0.48.0
|
|
6
6
|
---
|
|
7
7
|
**Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
|
|
8
8
|
# reg-parser
|
|
@@ -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 analytical reports (write-report) or the code domain model (domain-modeling)."
|
|
4
|
-
release-version: 0.
|
|
4
|
+
release-version: 0.48.0
|
|
5
5
|
---
|
|
6
6
|
**Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
|
|
7
7
|
# Terminology
|
|
@@ -30,3 +30,14 @@ the house style is set up, or over a file `write-doc` seeded, to widen it to the
|
|
|
30
30
|
`proposed`, and add `WRITING.md` to Source. Replace the table with one line under the heading:
|
|
31
31
|
`Terms: see [TERMINOLOGY.md](TERMINOLOGY.md).` When another skill started this setup, ask before
|
|
32
32
|
editing WRITING.md.
|
|
33
|
+
9. **Make explicit project setup discoverable.** Within the authorized project/client scope,
|
|
34
|
+
ensure local agent entrypoints tell document writers to read the applicable
|
|
35
|
+
`TERMINOLOGY.md` before drafting or editing. Use the
|
|
36
|
+
[document loader](../../house-style/references/persistence.md#make-the-saved-policy-discoverable)
|
|
37
|
+
with its scope, preservation and entrypoint checks: drafting routes to `write-doc`,
|
|
38
|
+
analytical reports to `write-report`, not to a new terminology-extraction run. Reuse an
|
|
39
|
+
equivalent existing loader; a glossary link alone does not establish skill routing.
|
|
40
|
+
Do not create `WRITING.md` or run writer initialization just to add the loader. Report
|
|
41
|
+
missing writer skills or partial entrypoint reachability without installing anything.
|
|
42
|
+
This step belongs to explicit project terminology setup, not an ordinary term correction
|
|
43
|
+
or automatically selected writing task, and does not expand existing write scope.
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: write-doc
|
|
3
3
|
description: "Write or edit documents that define or propose something: BRD, PRD, technical spec, integration guide, proposal, policy or risk procedure; English, Chinese or bilingual. Use automatically for drafting or revising these documents. Markdown by default; export when requested. NOT for analytical reports or writing up findings (write-report), ordinary chat replies (plain-language), learning style or saving preferences alone (distill-writing), performing an audit (compliance-audit), or WeChat articles (wechat-article-writer)."
|
|
4
|
-
release-version: 0.
|
|
4
|
+
release-version: 0.48.0
|
|
5
5
|
---
|
|
6
6
|
**Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
|
|
7
7
|
# Write a document
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: write-report
|
|
3
3
|
description: "Write or edit analytical reports from data, research, analysis or findings: payment, fraud, operational, performance, research, gap-analysis, audit, external assessment, management and Visa VARS reports. Use whenever asked to report results, write up findings, or turn analysis into a report, even without naming this skill. English, Chinese or bilingual; Markdown by default, export when requested. NOT for defining requirements, policies or proposals (write-doc), performing the underlying domain analysis or audit, chat-only answers (plain-language), or learning house style (distill-writing)."
|
|
4
|
-
release-version: 0.
|
|
4
|
+
release-version: 0.48.0
|
|
5
5
|
---
|
|
6
6
|
**Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
|
|
7
7
|
# Write an analytical report
|