admin/airi
1
0
Fork 0
mirror of https://github.com/moeru-ai/airi.git synced 2026-08-14 00:48:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore(AGENTS.md): enfore simple-english

Browse Source
This commit is contained in:
Neko Ayaka
2026-08-05 20:45:44 +08:00
parent 774b2daf03
commit f7604edce8
5 changed files with 449 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.agents/skills/simple-english/SKILL.md
+326
View File
@@ -0,0 +1,326 @@
---
name: simple-english
version: 1.0.0
description: |
Write or rewrite technical text with the rules of ASD-STE100 Simplified
Technical English so it is clear, unambiguous, and free of AI slop. Use for
documentation, READMEs, runbooks, procedures, error messages, release notes,
incident reports, and API guides. Also use when the user says "STE",
"Simplified Technical English", "ASD-STE100", "de-slop", "make this
readable", "write for non-native readers", or asks for docs that translate
well. Enforces the standard's 53 rules: 20/25-word sentence limits, one word
one meaning, simple tenses, active voice, condition before command.
license: MIT
compatibility: claude-code cursor codex gemini-cli opencode
metadata:
standard: ASD-STE100 Issue 9 (2025-01-15)
---
# Simple English: Write Like an Aerospace Manual
Write technical text with the rules of ASD-STE100 Simplified Technical English. STE is the controlled language that aerospace and defense manufacturers use for maintenance documentation. The rules exist so that a tired reader who is not a native English speaker cannot misread an instruction. They remove the usual signs of AI-generated text as a side effect: long sentences, synonym rotation, hedges, filler, and decorative clauses.
Write for that tired reader. Each sentence must survive one read.
## Your Task
When asked to write or rewrite technical text:
1. **Select the mode** (pragmatic or strict, below).
2. **Classify each passage** as procedural or descriptive. Every other rule depends on this.
3. **Fix your vocabulary before drafting.** Pick ONE verb for the check/verify/confirm/validate concept and ONE noun for config/settings. Use no other word for these concepts in the whole document.
4. **Apply the rules** from the catalog below.
5. **Run the self-check** before you deliver. This step is not optional.
6. **Never touch code**, identifiers, commands, or quoted errors (see Untouchables).
When asked to CHECK text instead of writing it, report each violation as: rule number, the offending text, a compliant rewrite. Cite only rule numbers that exist in this file. Do not cite rule numbers from memory: the numbering is unintuitive and models invent it (tested — an agent without this file cited "Rule 3.1: short sentences"; the real Rule 3.1 is about verb forms).
## Two Modes
| Mode | When | What you apply |
|---|---|---|
| **Pragmatic** (default) | Docs, READMEs, error messages — the user wants clear text | All structural rules. Domain words stay ("idempotent", "webhook"). |
| **Strict** | The user names STE, ASD-STE100, or compliance | Structural rules + full vocabulary discipline, and tell the user that full compliance needs the official dictionary (free at asd-ste100.org). |
## Step 1: Classify the Text
| | Procedural (instructions) | Descriptive (explanations) |
|---|---|---|
| Purpose | Tell the reader what to do | Explain what a thing is or does |
| Verb form | Imperative: "Install the pump." | Simple present/past/future |
| Sentence limit | **20 words** (Rule 5.1) | **25 words** (Rule 6.3) |
| Unit rule | One instruction per sentence (5.2) | One topic per paragraph (6.5), max six sentences per paragraph (6.6) |
Do not mix the two in one passage. A "Getting started" section is procedural. An "Architecture" section is descriptive. A note inside a procedure is descriptive (25-word limit, no imperative).
## THE RULE CATALOG
53 rules in 9 sections, paraphrased from ASD-STE100 Issue 9 with software examples. The official wording is in the free standard at asd-ste100.org.
### Section 1 — Words (Rules 1.1-1.14)
| Rule | Instruction |
|---|---|
| 1.1 | Use only approved words, technical nouns, or technical verbs. |
| 1.2 | Use an approved word only as its listed part of speech. |
| 1.3 | Use an approved word only with its approved meaning. |
| 1.4 | Use only the approved forms of verbs and adjectives. |
| 1.5 | You can use domain words as technical nouns ("webhook", "commit", "endpoint"). |
| 1.6 | Use an unapproved word only when it is a technical noun or part of one. |
| 1.7 | Do not use technical nouns as verbs. |
| 1.8 | Use the technical nouns of your project or industry. |
| 1.9 | When you pick a technical noun, pick a short and clear one. |
| 1.10 | No regional, slang, or jargon words as technical nouns. |
| 1.11 | One item, one name. Do not call it "config" here and "settings" there. |
| 1.12 | You can use domain verbs as technical verbs ("deploy", "compile", "merge"). |
| 1.13 | Do not use technical verbs as nouns. |
| 1.14 | Use American English spelling. |
In pragmatic mode, rules 1.5, 1.8, and 1.12 do the heavy lifting: your domain vocabulary is legal. The ones agents break are 1.7, 1.11, and 1.13.
**Before:** You can webhook the event, then do a deploy.
**After:** Send the event to the webhook. Then deploy the service.
### Section 2 — Multi-word nouns (Rules 2.1-2.2)
| Rule | Instruction |
|---|---|
| 2.1 | Write multi-word nouns of three words or fewer. |
| 2.2 | When a technical noun needs more than three words, write it in full once, then give a short form or hyphenate the units. |
Break long noun chains with prepositions (of, on, in, for):
**Before:** the connection pool timeout configuration value
**After:** the timeout value for the connection pool
### Section 3 — Verbs (Rules 3.1-3.7)
| Rule | Instruction |
|---|---|
| 3.1 | Use only the verb forms that the dictionary gives. |
| 3.2 | Use only: infinitive, imperative, simple present, simple past, simple future, past participle as adjective. |
| 3.3 | Use the past participle only as an adjective ("the cached response"). |
| 3.4 | No auxiliary verbs for complex constructions. No present perfect, no "is to be installed". |
| 3.5 | Use an "-ing" form only as a technical noun or inside one ("logging", "the mounting bracket") — never as a verb. |
| 3.6 | Active voice. In descriptive text, passive is legal only when the agent is unknown. |
| 3.7 | Describe an action with a verb, not a noun ("compress the file", not "perform compression of the file"). |
**Approved modals: can, will, must. Banned: should, would, may, might, could.**
The standard rejects "could" even for possibility: write "an explosion can occur", never "could occur". For "should": a requirement becomes "must"; a suggestion is stated as fact or deleted. This matters double for agent instructions — models read "should" as optional.
**Before:** The migration has completed and the table is being rebuilt.
**After:** The migration is complete. The database rebuilds the table.
**Before:** The flag can be set in the config file, making restarts unnecessary.
**After:** You can set the flag in the config file. Then a restart is not necessary.
**Before:** The temperature must be adjusted.
**After:** Adjust the temperature.
### Section 4 — Sentences (Rules 4.1-4.5)
| Rule | Instruction |
|---|---|
| 4.1 | Write short and clear sentences. |
| 4.2 | Do not omit words or use contractions to shorten sentences. Keep articles, keep "that". |
| 4.3 | Use a vertical list for complex text. |
| 4.4 | Use connecting words between sentences on related topics ("Then", "As a result"). |
| 4.5 | Put an article (the, a, an) or a demonstrative adjective (this, these) before nouns where applicable. |
Rule 4.2 is the anti-terseness rule. STE is short sentences with complete grammar, not telegraph style:
**Wrong shortening:** Ensure file exists before running.
**STE:** Make sure that the file exists before you run the command.
### Section 5 — Procedural writing (Rules 5.1-5.5)
| Rule | Instruction |
|---|---|
| 5.1 | Maximum 20 words per sentence. Warnings and cautions included. |
| 5.2 | One instruction per sentence, unless two actions happen at the same time. |
| 5.3 | Write instructions in the imperative: "Run the migration." |
| 5.4 | Put a required condition before the command, divided by a comma: "If the build fails, read the log." |
| 5.5 | Notes give information, never instructions. Notes get the 25-word limit. |
**Before:** You'll want to grab the API key from the dashboard before configuring the client, which you can do under Settings.
**After:** Get the API key from the dashboard, under Settings. Then configure the client with this key.
### Section 6 — Descriptive writing (Rules 6.1-6.6)
| Rule | Instruction |
|---|---|
| 6.1 | Give information gradually: one new fact per sentence. |
| 6.2 | Use key words and phrases to give the text a logical structure. |
| 6.3 | Maximum 25 words per sentence. |
| 6.4 | Group related information in paragraphs. |
| 6.5 | One topic per paragraph. |
| 6.6 | Maximum six sentences per paragraph. |
No imperative in descriptive text. Descriptions explain; procedures instruct.
### Section 7 — Safety instructions (Rules 7.1-7.3)
| Rule | Instruction |
|---|---|
| 7.1 | Use a word that shows the risk level ("WARNING" = injury, "CAUTION" = damage). |
| 7.2 | Start with a clear command or condition. |
| 7.3 | Then give the risk or the possible result. |
Never bury the instruction after the explanation. The pattern transfers directly to destructive CLI flags, irreversible migrations, and dangerous API options.
**Before:** Note that data loss may occur in some circumstances if the destructive flag happens to be enabled when running against production.
**After:** CAUTION: Do not use the `--force` flag against production. The flag deletes rows that do not match the source.
### Section 8 — Punctuation and word count (Rules 8.1-8.7)
| Rule | Instruction |
|---|---|
| 8.1 | All standard punctuation is legal except the semicolon. Write two sentences instead. |
| 8.2 | Use hyphens to connect words that act as one unit. |
| 8.3 | Parentheses are legal for references, item numbers, abbreviations, plural forms, explanations, alternatives. |
| 8.4 | In a vertical list, the lead-in colon ends a sentence for word count. |
| 8.5 | Text inside parentheses counts as one word. |
| 8.6 | Count as one word each: numbers, numbers with units, abbreviations, alphanumeric identifiers, quoted text, titles, labels, proper nouns. |
| 8.7 | A hyphenated word counts as one word. |
Rule 8.6 matters for software text: `sqlpipe run --config sqlpipe.yaml` in backticks is quoted text and counts as one word. Long identifiers do not blow your sentence budget.
### Section 9 — Writing practices (Rules 9.1-9.4, GR-1 to GR-8)
| Rule | Instruction |
|---|---|
| 9.1 | When a word-for-word replacement does not work, restructure the sentence. |
| 9.2 | Use each approved word correctly: approved meaning, approved part of speech. |
| 9.3 | Do not build phrasal verbs ("go down" → "decrease", "set up" → "install" or "configure"). |
| 9.4 | Keep one consistent style and terminology through the whole document. |
General recommendations GR-1 to GR-8: keep the conjunction "that", be careful with "with", give pronouns clear referents, prefer "this + noun" over bare "this", avoid false friends, avoid Latin abbreviations, use inclusive language, and use the possessive apostrophe form only when you are sure it is correct (GR-8: if unsure, do not use it — non-native readers find it hard).
GR-6 for software docs: "e.g." → "for example", "i.e." → "that is", and delete "etc." — name the items or write "and more".
## VOCABULARY DISCIPLINE
The official dictionary (~900 approved words, ~1,200 banned words with alternatives) is copyrighted by ASD and is not reproduced here. Its mechanics apply without it: **one word, one meaning, one part of speech.**
Known part-of-speech rulings, useful as patterns:
| Word | Ruling |
|---|---|
| test, check, work | Noun only. "Do a test", not "test the pump". "Check that X" becomes "make sure that X". |
| oil | Noun only as used in STE examples. For the verb, the dictionary gives "lubricate". |
| help | Verb only. For the noun, the dictionary gives "aid": "with the aid of". |
| fall | "To move down by gravity" only, never "decrease". |
| follow | "To come after" only, never "obey". Write "obey the instructions". |
| above, below | Physical positions only. For limits write "more than", "less than". |
### The modal ladder
| You wrote | STE writes |
|---|---|
| should (requirement) | must |
| should (recommendation) | Delete it, or state it as fact: "X is better because Y." |
| may / might / could (possibility) | can |
| may (permission) | can |
| would (hypothetical) | Restructure: "If X occurs, Y occurs." |
### Slop-to-simple substitutions
This table is ours, not the ASD dictionary. It maps the words AI-generated docs overuse to plain replacements. If the word carries no fact, delete it instead of replacing it.
| Slop | Write instead |
|---|---|
| leverage, utilize | use |
| in order to | to |
| prior to | before |
| ensure | make sure that |
| it is worth noting that | (delete) |
| it's important to, crucially | (delete — state the fact) |
| simply, just, easily, seamlessly, effortlessly | (delete) |
| robust, powerful, comprehensive, performant | (delete, or give the measurable property) |
| functionality | function, feature |
| enables you to, allows you to | you can |
| is designed to, aims to | (delete — say what it does) |
| facilitate | help, make possible |
| dive into, delve into | read, examine |
| when it comes to | for |
| in the event that | if |
| due to the fact that | because |
| as needed, as necessary | (state the condition) |
| and/or | Pick one, or write "X, or Y, or both" |
| e.g. / i.e. / etc. | for example / that is / (name the items) |
| gracefully handles | (say what it does: "retries three times, then stops") |
| out of the box | by default |
| under the hood | internally |
| blazingly fast, state-of-the-art | fast (give the number) / (delete) |
| streamline | make simpler, make faster |
| plethora, myriad | many |
| addresses the issue, tackles | corrects the fault, removes the error |
### Consistency pass
Collapse these common rotations to one term each (Rules 1.11, 9.4):
- check / verify / confirm / validate / ensure → pick one
- config / configuration / settings / options → pick one
- delete / remove / drop / destroy → one per meaning, kept consistent
- error / issue / problem / failure → "error" for errors, "failure" for failed operations
- run / execute / invoke / launch → pick one
- show / display / render / present → pick one
## Untouchables
These are technical names (Rules 1.5, 8.6). Leave them exact, even when they break vocabulary rules:
- Code blocks, inline code, identifiers, CLI commands, flags, file paths
- Quoted error messages and log lines
- Product names, API endpoint names, config keys
- Numbers with units — each counts as one word in the sentence limit
## Beyond Documentation
Same rules, different targets. Full adaptations in `references/use-cases.md`:
- **Error messages**: state what happened (simple past), the cause if known, then the fix as an imperative. No "Oops", no "Please ensure", no apology filler.
- **Runbooks**: STE's home turf. Imperative steps, conditions first, warnings before the step.
- **Incident reports**: simple past only. "We have identified an issue that may have impacted" becomes "Between 14:02 and 14:31 UTC, 12% of requests failed."
- **Release notes**: breaking changes follow the warning pattern — command first, risk second.
- **Agent instructions (prompts, AGENTS.md)**: a system prompt is a procedure for a reader that cannot ask questions. One instruction per sentence, no "should", condition first.
- **Translation prep**: STE's original job. One meaning per word plus complete grammar removes most translation ambiguity.
## Self-Check Before You Deliver
This step is not optional. Run these four checks on your draft:
1. Count words in your three longest sentences. Over the 20/25 limit → split them.
2. Search your draft for: `'ll`, `'re`, `'s` (contraction), `has been`, `have been`, `should`, `-ing` verbs after a comma, semicolons.
3. Search for every `if` and `when`. Each one stands at the START of its sentence, before the command. "Increase the timeout if the network is slow" → "If the network is slow, increase the timeout."
4. Search for the verbs you did NOT pick in Your Task step 3 (the check/verify/confirm set). Replace every hit with your chosen verb.
Fix what you find, then deliver. For a full audit, run `references/checklist.md`.
## Full Example
**Before (real unedited AI output):**
> **Connection timeouts.** If sqlpipe hangs or fails with `dial tcp: i/o timeout`, check that the host running sqlpipe can reach the Postgres port (usually 5432) — this is often a security group or firewall rule blocking the connection. If you're connecting to a managed database (RDS, Cloud SQL, etc.), confirm the instance allows connections from sqlpipe's IP. You can also try increasing `source.connect_timeout_seconds` in your config, since a slow network path can trip the default timeout even when the connection eventually succeeds.
**After (classified procedural, verb = "make sure", conditions first, one instruction per sentence):**
> **Connection timeouts.** sqlpipe stops with `dial tcp: i/o timeout` when it cannot reach the Postgres port (5432 by default).
>
> 1. Make sure that the host that runs sqlpipe can reach the Postgres port. A firewall or security group usually blocks it.
> 2. If the database is managed (RDS, Cloud SQL), make sure that the instance accepts connections from the IP of sqlpipe.
> 3. If the network is slow, increase `source.connect_timeout_seconds` in the configuration.
What changed: 40-word sentences split under 20; "you're" expanded; "check/confirm" collapsed to "make sure that"; every condition moved before its command; "etc." removed; code and error strings untouched.
## Limits
STE is for technical facts and instructions. Do not apply it to marketing copy, blog voice, or brand writing — it deletes persuasion by design. When a user asks for STE on marketing text, say so and offer it for the docs instead.
This skill is an unofficial aid. It is not affiliated with or endorsed by ASD or STEMG, and no tool can guarantee STE compliance. ASD-STE100 is a registered trademark of ASD. The official standard is a free download at asd-ste100.org.
## References
- `references/checklist.md` — full verification pass with searchable patterns, for check mode and final audits
- `references/use-cases.md` — long-form adaptations: error messages, runbooks, incident reports, commits, UI copy, i18n
.agents/skills/simple-english/references/checklist.md
+43
View File
@@ -0,0 +1,43 @@
# Verification checklist
Run this pass on every draft before you deliver it. The checks are ordered from mechanical to judgment.
## Mechanical checks (searchable)
Search the draft for each pattern. Every hit outside code blocks and quoted text is a violation.
| Search for | Violation | Fix |
|---|---|---|
| `'ll`, `'re`, `'ve`, `n't`, `it's` | Contraction (Rule 4.2) | Expand it. |
| `has been`, `have been`, `had been` | Present/past perfect (Rule 3.4) | Simple past or simple present. |
| `has` / `have` + past participle | Present perfect (Rule 3.4) | Simple past. |
| `should`, `would`, `may`, `might`, `could` | Unapproved modal (Rule 3.2) | See the modal ladder in SKILL.md. |
| `is being`, `are being`, `was being` | Progressive passive (Rules 3.4, 3.5) | Active, simple tense. |
| `, making`, `, allowing`, `, enabling`, `, ensuring` | "-ing" clause as verb (Rule 3.5) | New sentence with a real subject. |
| `;` | Semicolon (Rule 8.1) | Two sentences. |
| `e.g.`, `i.e.`, `etc.` | Latin abbreviation (GR-6) | "for example", "that is", name the items. |
| `simply`, `easily`, `seamlessly`, `robust` | Filler (no fact) | Delete. |
| ` if `, ` when ` (mid-sentence) | Trailing condition (Rule 5.4) | Move the condition to the start of the sentence, add a comma. |
## Countable checks
1. **Sentence length.** Count words in each sentence. Procedural limit: 20. Descriptive limit: 25. Notes: 25.
Backticked commands, numbers with units, and identifiers count as one word each (Rule 8.6).
2. **Paragraph size.** Maximum six sentences per paragraph (Rule 6.6).
3. **Multi-word nouns.** Any noun chain over three words → break it with prepositions (Rule 2.1).
4. **Instructions per sentence.** One, unless the actions are simultaneous (Rule 5.2).
## Judgment checks
5. **Classification.** Is each passage cleanly procedural or descriptive? Procedures in imperative, descriptions never in imperative.
6. **Voice.** Any passive sentence: is the agent truly unknown, and is the passage descriptive? Otherwise make it active (Rule 3.6).
7. **Condition placement.** Every "if/when" stands before its command, with a comma (Rule 5.4).
8. **Synonym rotation.** One term per concept across the whole document (Rules 1.11, 9.4). Scan for check/verify/confirm, config/settings, run/execute.
9. **Warnings.** Command or condition first, risk second (Rules 7.2, 7.3).
10. **Completeness.** Articles present, "that" present after "make sure", no telegraph style (Rule 4.2).
11. **Untouchables intact.** Code, identifiers, quoted errors, and proper nouns are unchanged.
## When reporting violations (check mode)
For each violation give: the rule number, the offending text, and a compliant rewrite. Cite only rule numbers that appear in rules.md.
End the report with this statement when the user asked for STE compliance: "No tool can guarantee ASD-STE100 compliance. Final approval rests with the writer. The official standard is a free download at asd-ste100.org."
.agents/skills/simple-english/references/use-cases.md
+64
View File
@@ -0,0 +1,64 @@
# Use cases beyond documentation
STE was built for aircraft maintenance manuals. The same properties — one meaning per word, short sentences, condition-first commands — transfer to any text where misreading has a cost. By the end of Issue 8, 64% of registered STE users were outside aerospace and defense.
Each case below names the mode and the adaptations.
## Error messages and CLI output
Mode: procedural. This is the highest-value target: an error message is a 2 a.m. instruction to a stressed reader.
Pattern: state what happened (past simple), state the cause if known, give the command or condition to fix it.
> **Before:** Oops! Something went wrong while attempting to establish a connection. Please ensure your credentials are properly configured and try again.
> **After:** Connection to the database failed. The password for user `app` was not correct. Set `DB_PASSWORD` and connect again.
## Runbooks and standard operating procedures
Mode: strict-leaning procedural. This is STE's home turf — an on-call runbook is a maintenance manual.
- Every step imperative, one instruction per step, conditions first.
- Warnings before the step, command first, risk second.
- 20-word limit enforced hard: an operator under pager stress reads each sentence once.
## Incident reports and postmortems
Mode: descriptive. Simple past only — a timeline in present perfect ("we have identified...") hides when things happened.
> **Before:** We have identified an issue that may have impacted some users' ability to access the service.
> **After:** Between 14:02 and 14:31 UTC, 12% of requests failed. A deploy at 14:00 removed the cache warmup step.
STE bans hedges ("may have impacted") — the report states what is known and says "unknown" for the rest. This reads more honest because it is.
## Commit messages and PR descriptions
Mode: descriptive body, imperative subject. Convention already matches STE: imperative subject line, plain past facts in the body. Apply the substitution table and the 25-word limit to the body. Delete "this PR aims to".
## API changelogs and release notes
Mode: descriptive. One entry, one change, one sentence where possible. "Breaking:" entries follow the warning pattern — command first: "Update your calls to `v2/users`. The `name` field split into `first_name` and `last_name`."
## Instructions for AI agents (prompts, AGENTS.md, skills)
Mode: procedural. A system prompt is a procedure executed by a reader with no ability to ask questions — the exact reader STE was designed for.
- One instruction per sentence keeps rules independently quotable and hard to half-follow.
- One word, one meaning prevents the model from treating "check", "verify", and "validate" as three different operations.
- Condition-first ("If the build fails, stop") beats trailing conditions, which models drop.
- No "should" — a model reads "should" as optional. Write "must" or delete the rule.
## Support macros and status-page updates
Mode: descriptive, 25-word limit. Non-native readers are the majority of many user bases. No "we sincerely apologize for any inconvenience this may have caused" — "The API was down for 18 minutes. Uploads made during this time were saved and will process today."
## Translation and localization prep
Mode: strict. STE's original purpose was making English readable for non-native maintenance crews, and it doubles as pre-editing for machine translation. One meaning per word plus complete grammar (articles, "that") removes most translation ambiguity. If your docs get localized, STE cuts the error rate and the cost.
## UI copy and empty states
Mode: procedural, hard length limits. Buttons and labels are technical names (exempt). Body copy follows the rules: "No projects yet. Create a project to start." Nothing else survives at this length anyway.
## Where STE does not fit
Marketing pages, launch posts, blog voice, brand writing. STE deletes persuasion on purpose. Write those in your own voice — then use STE for the docs the landing page links to.
AGENTS.md
+10 -7
View File
@@ -82,6 +82,16 @@ Concise but detailed reference for contributors working across the `moeru-ai/air
- `pnpm -F <package.json name> build`
- Example: `pnpm -F @proj-airi/stage-tamagotchi build` (typecheck + electron-vite build).
## Before You Start
## Enforced Repository Skills
- For testing, Vitest, regression reproduction, mocks, or test import-boundary work, always use [`enforce-rules-for-vitest` skill](.agents/skills/enforce-rules-for-vitest/SKILL.md).
- For UnoCSS, Vue styling, UI components, animations, icons, or color-mode work, always use [`enforce-rules-for-unocss` skill](.agents/skills/enforce-rules-for-unocss/SKILL.md).
- For web or Electron workflows that upload a local file through an HTML input, a dynamically created input, or a file chooser, invoke [`$use-agent-browser-with-input-file`](.agents/skills/use-agent-browser-with-input-file/SKILL.md). Also invoke `$agent-browser`, and invoke `$agent-browser-electron` when the target is Electron.
- For AIRI Live2D, VRM, or MMD import and rendering tests across stage-web, stage-tamagotchi, or stage-pocket, invoke [`$use-agent-browser-for-airi`](.agents/skills/use-agent-browser-for-airi/SKILL.md). It invokes `$use-agent-browser-with-input-file` for the upload mechanism and adds AIRI-specific routes, state preparation, format behavior, and renderer verification.
- For editing, writing, refactoring, re-writing code, submitting issues, Pull Requests, and docs, comments, invoke [`$simple-english`](./agents/skills/simple-english/SKILL.md).
## Development Practices
- Favor clear module boundaries; shared logic goes in `packages/`.
@@ -93,13 +103,6 @@ Concise but detailed reference for contributors working across the `moeru-ai/air
- If the refactor scope is small, do a progressive refactor step by step.
- For new feature requirements or requirement-related tasks involving `node:*` built-in modules, DOM operations, Vue composables, React hooks, Vite plugins, or GitHub Actions workflows, always do deep research for suitable existing libraries or open source modules first. Before choosing any library, always ask the user to choose and help judge which option is right. Never choose generalized utility libraries on your own (for example, `es-toolkit`, utilities from `github.com/unjs`, or tiny tools from `github.com/tinylib`) without explicit user confirmation. If the user is working spec-driven, list candidate choices in a clear and concise Markdown comparison table.
## Enforced Repository Skills
- For testing, Vitest, regression reproduction, mocks, or test import-boundary work, always use [`enforce-rules-for-vitest` skill](.agents/skills/enforce-rules-for-vitest/SKILL.md).
- For UnoCSS, Vue styling, UI components, animations, icons, or color-mode work, always use [`enforce-rules-for-unocss` skill](.agents/skills/enforce-rules-for-unocss/SKILL.md).
- For web or Electron workflows that upload a local file through an HTML input, a dynamically created input, or a file chooser, invoke [`$use-agent-browser-with-input-file`](.agents/skills/use-agent-browser-with-input-file/SKILL.md). Also invoke `$agent-browser`, and invoke `$agent-browser-electron` when the target is Electron.
- For AIRI Live2D, VRM, or MMD import and rendering tests across stage-web, stage-tamagotchi, or stage-pocket, invoke [`$use-agent-browser-for-airi`](.agents/skills/use-agent-browser-for-airi/SKILL.md). It invokes `$use-agent-browser-with-input-file` for the upload mechanism and adds AIRI-specific routes, state preparation, format behavior, and renderer verification.
## TypeScript / IPC / Tools
- Keep JSON Schemas provider-compliant (explicit `type: object`, required fields; avoid unbounded records).
skills-lock.json
+6
View File
@@ -22,6 +22,12 @@
"sourceType": "github",
"computedHash": "318f9fca2441a3e06fedc336e195dd18be5dbe901064e4fa71b76b40b096ab3a"
},
"simple-english": {
"source": "AminBlg/SimpleEnglish",
"sourceType": "github",
"skillPath": "skills/simple-english/SKILL.md",
"computedHash": "8e1b7d3d2c20a34318c2971256f74fc6480bc317f07168d51ffad6b21469ec49"
},
"tsdown": {
"source": "antfu/skills",
"sourceType": "github",