modify skill and plugin

This commit is contained in:
NINI
2026-05-13 22:27:48 +09:00
parent d414338780
commit 2d59191df2
24 changed files with 2051 additions and 1 deletions
@@ -0,0 +1,115 @@
# AGENTS.md Quality Criteria
## Scoring Rubric
### 1. Commands and Workflows - 20 points
20 points: all essential commands documented with context.
- Build, test, lint, format, dev, and deploy commands are present when relevant.
- Development workflow is clear.
- Common operations and verification expectations are documented.
15 points: most commands present, some missing context.
10 points: basic commands only, little workflow.
5 points: few commands, many missing.
0 points: no commands documented.
### 2. Architecture Clarity - 20 points
20 points: clear codebase map.
- Key directories explained.
- Module relationships documented.
- Entry points identified.
- Data flow described where relevant.
15 points: good structure overview, minor gaps.
10 points: basic directory listing only.
5 points: vague or incomplete.
0 points: no architecture info.
### 3. Non-Obvious Patterns - 15 points
15 points: gotchas and quirks captured.
- Known issues documented.
- Workarounds explained.
- Edge cases noted.
- Unusual "why this way" rules explained briefly.
10 points: some patterns documented.
5 points: minimal pattern documentation.
0 points: no patterns or gotchas.
### 4. Conciseness - 15 points
15 points: dense, valuable content.
- No filler or obvious info.
- Each line adds value.
- No redundancy with code comments or README basics unless Codex specifically needs it.
10 points: mostly concise, some padding.
5 points: verbose in places.
0 points: mostly filler or restates obvious code.
### 5. Currency - 15 points
15 points: reflects current codebase.
- Commands work as documented.
- File references are accurate.
- Tech stack and architecture are current.
10 points: mostly current, minor staleness.
5 points: several outdated references.
0 points: severely outdated.
### 6. Actionability - 15 points
15 points: instructions are executable.
- Commands can be copied and run.
- Steps are concrete.
- Paths are real.
- Verification expectations are clear.
10 points: mostly actionable.
5 points: some vague instructions.
0 points: vague or theoretical.
## Assessment Process
1. Read each instruction file completely.
2. Cross-reference with the actual codebase.
3. Check documented commands against package manifests, scripts, and config.
4. Verify file and directory references.
5. Score each criterion.
6. Calculate total and assign grade.
7. List specific issues.
8. Propose concrete, concise improvements.
## Red Flags
- Commands that would fail.
- References to deleted files or folders.
- Outdated tech versions.
- Placeholder template content.
- Generic advice not specific to the project.
- Duplicate or contradictory guidance across nested instruction files.
- An `AGENTS.override.md` that accidentally hides a sibling `AGENTS.md`.
@@ -0,0 +1,180 @@
# AGENTS.md Templates
## Key Principles
- Concise: dense, human-readable content; one line per concept when possible.
- Actionable: commands should be copy-paste ready.
- Project-specific: document patterns unique to this repo.
- Current: reflect the actual codebase and active tooling.
- Scoped: put broad rules at the repo root; put narrow rules in nested `AGENTS.md` or `AGENTS.override.md`.
## Recommended Sections
Use only sections that matter for the project.
### Commands
```markdown
## Commands
| Command | Purpose |
| --- | --- |
| `<install command>` | Install dependencies |
| `<dev command>` | Start development server |
| `<build command>` | Production build |
| `<test command>` | Run tests |
| `<lint command>` | Lint or format |
```
### Architecture
```markdown
## Architecture
```
<root>/
<dir>/ # <purpose>
<dir>/ # <purpose>
<dir>/ # <purpose>
```
```
### Key Files
```markdown
## Key Files
- `<path>` - <purpose>
- `<path>` - <purpose>
```
### Code Style
```markdown
## Code Style
- <project-specific convention>
- <preference over alternative>
```
### Environment
```markdown
## Environment
Required:
- `<VAR_NAME>` - <purpose>
Setup:
- <setup step>
```
### Testing
```markdown
## Testing
- `<test command>` - <what it tests>
- <testing convention or pattern>
```
### Gotchas
```markdown
## Gotchas
- <non-obvious issue, prerequisite, or ordering dependency>
```
### Workflow
```markdown
## Workflow
- <when to do X>
- <preferred approach for Y>
```
## Minimal Project Root Template
```markdown
# <Project Name>
<One-line description>
## Commands
| Command | Purpose |
| --- | --- |
| `<command>` | <description> |
## Architecture
```
<structure>
```
## Gotchas
- <gotcha>
```
## Comprehensive Project Root Template
```markdown
# <Project Name>
<One-line description>
## Commands
| Command | Purpose |
| --- | --- |
| `<command>` | <description> |
## Architecture
```
<structure with descriptions>
```
## Key Files
- `<path>` - <purpose>
## Code Style
- <convention>
## Environment
- `<VAR>` - <purpose>
## Testing
- `<command>` - <scope>
## Gotchas
- <gotcha>
```
## Nested Override Template
Use this for a subdirectory whose rules differ from the repo root.
```markdown
# <Directory> Instructions
## Scope
- Applies to `<path>/`.
## Local Rules
- <specific rule that differs from root guidance>
## Verification
- `<command>` - <focused check for this directory>
```
@@ -0,0 +1,131 @@
# AGENTS.md Update Guidelines
## Core Principle
Only add information that will genuinely help future Codex sessions. The context window is precious; every line must earn its place.
## What To Add
### Commands and Workflows Discovered
```markdown
## Commands
`npm run build` - Production build.
`npm run lint` - ESLint check required before handoff.
```
Why: saves future sessions from rediscovering commands.
### Gotchas and Non-Obvious Patterns
```markdown
## Gotchas
- Tests must run sequentially because they share a local database.
- Regenerate API clients with `npm run codegen` after editing OpenAPI files.
```
Why: prevents repeated debugging.
### Package Relationships
```markdown
## Architecture
- `packages/api` owns route handlers; `packages/ui` must call it through the shared client.
```
Why: captures relationships that are not obvious from filenames.
### Testing Approaches That Worked
```markdown
## Testing
- API endpoint tests use `tests/helpers/request.ts`; avoid ad hoc server setup.
```
Why: establishes known-good patterns.
### Configuration Quirks
```markdown
## Environment
- `NEXT_PUBLIC_*` variables must be set at build time.
```
Why: environment details often waste time when omitted.
## What Not To Add
### Obvious Code Info
Bad:
```markdown
The `UserService` class handles user operations.
```
The class name already says that.
### Generic Best Practices
Bad:
```markdown
Always write tests for new features.
Use meaningful variable names.
```
Add only project-specific rules.
### One-Off Fixes
Bad:
```markdown
We fixed a bug where the login button did not work.
```
Unless the lesson is durable, leave it out.
### Verbose Explanations
Bad:
```markdown
The authentication system uses JWT tokens. JWT means JSON Web Token...
```
Good:
```markdown
Auth: JWT HS256 tokens in `Authorization: Bearer <token>`.
```
## Diff Format
For each suggested change:
```markdown
### Update: ./AGENTS.md
**Why:** The build command exists but was missing from project instructions.
```diff
+## Commands
+
+`npm run build` - Production build.
```
```
## Validation Checklist
- Each addition is project-specific.
- No generic advice or obvious info.
- Commands are verified against the repo.
- File paths are accurate.
- The wording is concise.
- A new Codex session would benefit from the line.