pi-feature-dev 1.6.0 → 1.7.0

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/README.md CHANGED
@@ -73,6 +73,7 @@ versions came from:
73
73
  - [anthropics/claude-code feature-dev plugin](https://github.com/anthropics/claude-code/tree/main/plugins/feature-dev)
74
74
  - [mattpocock/skills batch-grill-me and domain-modeling skills](https://github.com/mattpocock/skills)
75
75
  - [danyuchn/asd-ste100-skill](https://github.com/danyuchn/asd-ste100-skill)
76
+ - [AminBlg/SimpleEnglish](https://github.com/AminBlg/SimpleEnglish/tree/main/skills/simple-english)
76
77
 
77
78
  ## Usage
78
79
 
@@ -139,8 +140,9 @@ The `ste` skill selects one of two modes:
139
140
  - **STE clarity** transfers the same clarity discipline to other technical
140
141
  text without claiming formal ASD-STE100 compliance.
141
142
 
142
- The skill loads its detailed writing rules and before/after examples only when
143
- they are relevant to the request. Standard provenance and source links stay in
143
+ The skill loads its detailed writing rules, review checklist, text-type
144
+ patterns, and before/after examples only when they are relevant to the request.
145
+ Standard provenance, design references, and source links stay in
144
146
  `skills/ste/README.md`, outside the agent's writing context.
145
147
 
146
148
  ## Package contents
@@ -172,6 +174,8 @@ pi-feature-dev/
172
174
  ├── agents/openai.yaml
173
175
  ├── references/
174
176
  │ ├── before-after.md
177
+ │ ├── checklist.md
178
+ │ ├── use-cases.md
175
179
  │ └── writing-rules.md
176
180
  ├── README.md
177
181
  └── SKILL.md
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "pi-feature-dev",
3
- "version": "1.6.0",
3
+ "version": "1.7.0",
4
4
  "description": "Portable coding-agent workflows packaged as skills.",
5
5
  "license": "MIT",
6
6
  "type": "module",
@@ -9,6 +9,9 @@ This project skill applies ASD-STE100 Simplified Technical English principles to
9
9
 
10
10
  The skill is Markdown-only and has no runtime or tool dependency.
11
11
 
12
+ Its agent-facing instructions stay compact. Detailed writing rules, review checklists, text-type
13
+ patterns, and examples are separate references that the agent loads only when a task needs them.
14
+
12
15
  ## Standard Baseline
13
16
 
14
17
  The skill uses ASD-STE100 Simplified Technical English, Issue 9, dated 2025-01-15.
@@ -32,3 +35,13 @@ not as a compliant or certified document.
32
35
 
33
36
  ASD owns the copyright and trademarks for ASD-STE100. Do not copy the official dictionary or
34
37
  extended passages without permission.
38
+
39
+ ## Design References
40
+
41
+ The skill design also incorporates ideas from these open-source implementations:
42
+
43
+ - [danyuchn/asd-ste100-skill](https://github.com/danyuchn/asd-ste100-skill)
44
+ - [AminBlg/SimpleEnglish](https://github.com/AminBlg/SimpleEnglish/tree/main/skills/simple-english)
45
+
46
+ This project keeps its own conservative verification boundary. External checklists and examples
47
+ do not establish formal STE compliance.
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: ste
3
- description: Draft, rewrite, and review clear, unambiguous English with ASD-STE100 Simplified Technical English Issue 9 principles. Use for technical procedures, safety instructions, descriptions, prompts, agent-to-agent instructions, tool descriptions, error messages, status reports, translation-ready text, controlled English, terminology normalization, and STE compliance reviews. Support strict STE verification when the official dictionary and project glossary are available; otherwise produce an STE-aligned or STE-style result without claiming compliance.
3
+ description: Draft, rewrite, and review clear, unambiguous English with ASD-STE100 Simplified Technical English Issue 9 principles. Use for READMEs, runbooks, procedures, safety instructions, API and tool documentation, prompts, agent instructions, UI and error messages, status and incident reports, release notes, support text, translation-ready content, terminology normalization, controlled English, and STE compliance reviews. Also use when asked to simplify or de-slop English, help non-native readers, or prepare text for translation. Support strict verification only with the official dictionary and project glossary; otherwise report an STE-aligned or STE-style result.
4
4
  ---
5
5
 
6
6
  # STE
@@ -29,6 +29,10 @@ status reports, translation-ready text, and other technical or operational Engli
29
29
 
30
30
  - Read [references/writing-rules.md](references/writing-rules.md) for strict STE work, compliance
31
31
  reviews, safety text, word-count decisions, or rule details.
32
+ - Read [references/checklist.md](references/checklist.md) for strict reviews, audits, high-risk
33
+ text, or long documents. Use its quick check or full check as the task requires.
34
+ - Read [references/use-cases.md](references/use-cases.md) when the text type needs a clear
35
+ information order or a reusable structure.
32
36
  - Read [references/before-after.md](references/before-after.md) when rewriting dense text,
33
37
  explaining changes, or producing a comparison.
34
38
  - Read all user-supplied glossaries, safety policies, style guides, and regulatory directives that
@@ -51,6 +55,18 @@ Do not invent missing facts. Do not remove precision only to meet a length targe
51
55
  Keep a qualitative modifier such as `carefully` when it affects task intent. Flag it when the
52
56
  project requires a measurable criterion, but do not invent that criterion.
53
57
 
58
+ ## Protect Untouchable Text
59
+
60
+ Unless the user explicitly asks to edit the exact literal, do not change:
61
+
62
+ - Code blocks, inline code, identifiers, placeholders, and data values.
63
+ - CLI commands, flags, file paths, URLs, and protocol elements.
64
+ - Product, API, configuration, database, and schema names.
65
+ - Quoted UI labels, error strings, log text, and externally defined messages.
66
+
67
+ Rewrite the sentence around an untouchable literal when necessary. Never silently normalize the
68
+ literal itself.
69
+
54
70
  ## Apply the Core Discipline
55
71
 
56
72
  | Area | Apply |
@@ -81,6 +97,18 @@ project requires a measurable criterion, but do not invent that criterion.
81
97
 
82
98
  If the input is already clear and meets the applicable rules, say so. Do not force a rewrite.
83
99
 
100
+ ## Self-check Before Delivery
101
+
102
+ Always confirm that:
103
+
104
+ 1. The revision preserves every fact, condition, limit, unit, exception, sequence, and
105
+ responsibility.
106
+ 2. Untouchable text is unchanged unless the user requested that exact change.
107
+ 3. Each procedural sentence has one independent action unless actions occur at the same time.
108
+ 4. Actors, referents, conditions, results, and terminology are unambiguous and consistent.
109
+ 5. The result uses the correct mode, verification status, and unresolved checks.
110
+ 6. Each cited rule number was verified directly against the authoritative standard.
111
+
84
112
  ## Choose the Output
85
113
 
86
114
  For a direct drafting or rewriting request:
@@ -103,6 +131,10 @@ After the table, give the complete revised text. Group unresolved items as:
103
131
 
104
132
  Use the user's requested format when it conflicts with these defaults.
105
133
 
134
+ Name the applicable rule area in explanations. Cite an Issue 9 rule number only after you verify
135
+ that number in the official standard or an authoritative copy supplied by the user. Do not infer
136
+ rule numbers from memory, summaries, or another skill.
137
+
106
138
  ## State Verification Honestly
107
139
 
108
140
  Use one of these statuses only when a status is useful:
@@ -0,0 +1,95 @@
1
+ # STE Review Checklist
2
+
3
+ Use this checklist as an operational review aid. It is not a replacement for the official
4
+ ASD-STE100 standard or dictionary. A search result identifies text to inspect; it does not prove
5
+ that the text violates a rule.
6
+
7
+ ## Quick Check
8
+
9
+ Use this check for a general clarity rewrite:
10
+
11
+ - Compare the source and revision. Preserve facts, conditions, limits, units, exceptions,
12
+ sequence, and responsibility.
13
+ - Confirm that code, identifiers, commands, paths, labels, quoted messages, and other protected
14
+ literals did not change.
15
+ - Use explicit actors, referents, conditions, actions, and results.
16
+ - Put a prerequisite condition before the action that depends on it.
17
+ - Keep one independent action in each procedural sentence unless actions occur at the same time.
18
+ - Use one term for one concept and one wording for one repeated action.
19
+ - Separate observed facts, possible causes, and recovery actions.
20
+ - Report unresolved technical, lexical, safety, or regulatory questions.
21
+
22
+ ## Full Check
23
+
24
+ Use this check for strict STE work, compliance reviews, safety text, high-risk content, or long
25
+ documents.
26
+
27
+ ### 1. Meaning and Scope
28
+
29
+ - Make an inventory of actions, facts, conditions, negation, quantities, units, limits,
30
+ exceptions, warnings, consequences, and cross-references.
31
+ - Confirm the scope of each modifier and logical connector.
32
+ - Confirm that the revision does not add a cause, risk level, requirement, or technical fact.
33
+
34
+ ### 2. Vocabulary and Terminology
35
+
36
+ - Verify each general word against the official Issue 9 dictionary.
37
+ - Verify its approved meaning, part of speech, form, and use.
38
+ - Verify each technical noun and technical verb against the applicable category and project
39
+ glossary.
40
+ - Record unverified terms instead of assuming that they are approved.
41
+ - Check abbreviations, spelling, and alternate names for the same concept.
42
+
43
+ ### 3. Grammar and Sentences
44
+
45
+ - Check active voice, permitted verb forms, articles, complete constructions, and explicit
46
+ referents.
47
+ - Inspect each `-ing` form, passive construction, modal verb, and multi-word verb in context.
48
+ - Split overloaded sentences and complex alternatives.
49
+ - Confirm that connecting words show the intended logical relation.
50
+
51
+ ### 4. Procedures and Descriptions
52
+
53
+ - Classify each section as a procedure, description, safety instruction, or mixed content.
54
+ - For procedures, use imperative commands and put prerequisite conditions first.
55
+ - For descriptions, present information gradually and keep one topic in each paragraph.
56
+ - Put complex sequences and alternatives in vertical lists.
57
+
58
+ ### 5. Length and Mechanics
59
+
60
+ - Apply the Issue 9 word-count method.
61
+ - Check the 20-word procedure limit and the 25-word description limit.
62
+ - Check the six-sentence description-paragraph limit.
63
+ - Inspect semicolons, parentheses, hyphens, and long multi-word nouns.
64
+
65
+ ### 6. Safety
66
+
67
+ - Preserve the governing safety label and required wording.
68
+ - Start with the required command or condition.
69
+ - State only the known risk or possible result.
70
+ - Confirm that simplification did not weaken the safety intent.
71
+
72
+ ### 7. Delivery
73
+
74
+ - Apply project, regulatory, and customer directives before general STE preferences.
75
+ - Use the correct verification status.
76
+ - List unresolved checks.
77
+ - Cite a rule number only after direct verification in an authoritative copy of Issue 9.
78
+
79
+ ## Search Cues
80
+
81
+ Search for these features during a large review:
82
+
83
+ - Contractions such as `can't`, `don't`, `'re`, and `'ve`.
84
+ - Semicolons.
85
+ - `-ing` forms.
86
+ - Perfect or continuous auxiliary constructions.
87
+ - Forms of `be` followed by a past participle.
88
+ - Modal verbs such as `should`, `would`, `may`, `might`, and `could`.
89
+ - Vague referents such as `it`, `this`, `that`, `they`, and `which`.
90
+ - `and` or `then` between commands.
91
+ - Different nouns or verbs that might name the same concept or action.
92
+ - Sentences and description paragraphs above their applicable limits.
93
+
94
+ Inspect each match in context. Do not treat every `if`, `when`, `-ing` form, passive construction,
95
+ modal verb, or repeated connector as an automatic violation.
@@ -0,0 +1,95 @@
1
+ # Text-Type Patterns
2
+
3
+ Use these patterns when the source does not already have a required structure. They describe
4
+ useful information order, not additional ASD-STE100 rules. Preserve the user's requested format
5
+ and all protected literals.
6
+
7
+ ## Procedure or Runbook
8
+
9
+ Present information in this order:
10
+
11
+ 1. Prerequisite conditions and applicable safety instructions.
12
+ 2. One command for each independent action.
13
+ 3. Expected result, when the reader must verify it.
14
+ 4. Recovery or escalation action, when the source supplies one.
15
+
16
+ Do not move a command into a note. Do not invent missing steps or sequence.
17
+
18
+ ## Error Message
19
+
20
+ Include only the fields that are known:
21
+
22
+ 1. What failed.
23
+ 2. Why it failed.
24
+ 3. What effect the failure has.
25
+ 4. What the user can do next.
26
+ 5. A stable identifier or context value.
27
+
28
+ Separate facts from possible causes. Preserve quoted system messages, codes, paths, and
29
+ identifiers unless the user asks to rewrite those exact values.
30
+
31
+ ## API or Tool Documentation
32
+
33
+ Present:
34
+
35
+ 1. The operation and its purpose.
36
+ 2. Required inputs and prerequisites.
37
+ 3. Constraints and defaults.
38
+ 4. The result.
39
+ 5. Errors and recovery actions.
40
+ 6. A minimal example when it adds necessary clarity.
41
+
42
+ Keep API names, parameter names, commands, flags, code, and protocol terms unchanged.
43
+
44
+ ## Prompt or Agent Instruction
45
+
46
+ State:
47
+
48
+ 1. The objective.
49
+ 2. The scope and supplied inputs.
50
+ 3. Required actions and decision conditions.
51
+ 4. Constraints and protected content.
52
+ 5. The expected output.
53
+ 6. Stop, escalation, or uncertainty behavior when it matters.
54
+
55
+ Make ownership explicit when more than one agent or tool can act.
56
+
57
+ ## Status or Incident Report
58
+
59
+ Separate:
60
+
61
+ 1. Observed facts.
62
+ 2. User or system impact.
63
+ 3. Confirmed cause and unconfirmed hypotheses.
64
+ 4. Completed and current actions.
65
+ 5. Next action, owner, or checkpoint when provided.
66
+
67
+ Use time references that are unambiguous in the target context. Do not present a hypothesis as a
68
+ fact.
69
+
70
+ ## Release Note, Commit, or Pull Request
71
+
72
+ State:
73
+
74
+ 1. What changed.
75
+ 2. Why it changed or what user-visible effect it has.
76
+ 3. What component or audience it affects.
77
+ 4. How the change was verified.
78
+ 5. Known limitations or required user actions.
79
+
80
+ Do not add promotional claims to a technical summary.
81
+
82
+ ## Support or UI Text
83
+
84
+ Name the problem or action directly. Use the same terms that the interface uses. Give the next
85
+ action before secondary explanation when the reader must act.
86
+
87
+ Treat exact UI labels, control names, placeholders, and external error text as protected literals
88
+ unless the task explicitly targets them for revision.
89
+
90
+ ## Translation-ready Text
91
+
92
+ Use self-contained sentences and stable sentence boundaries. Repeat terminology instead of
93
+ rotating synonyms. Make conditions, negation, quantities, units, and references explicit.
94
+
95
+ Preserve placeholders, markup, segmentation controls, and variables exactly.