Best use case
mention-conventions is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
It is a strong fit for teams already working in Codex.
Display @-mention naming conventions and placement rules
Teams using mention-conventions should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/mention-conventions/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How mention-conventions Compares
| Feature / Agent | mention-conventions | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Display @-mention naming conventions and placement rules
Which AI agents support this skill?
This skill is designed for Codex.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# @-Mention Conventions
Display AIWG @-mention naming conventions and placement rules.
## Usage
```bash
/mention-conventions # Show all conventions
/mention-conventions --section naming # Show naming patterns only
/mention-conventions --section placement # Show placement rules only
```
## Naming Patterns
### Requirements
```
@.aiwg/requirements/UC-{NNN}-{slug}.md # Use cases (UC-001-user-auth.md)
@.aiwg/requirements/NFR-{CAT}-{NNN}.md # Non-functional (NFR-SEC-001.md)
@.aiwg/requirements/user-stories.md # User story collection
```
Categories for NFRs:
- `SEC` - Security
- `PERF` - Performance
- `SCAL` - Scalability
- `AVAIL` - Availability
- `MAINT` - Maintainability
- `USAB` - Usability
### Architecture
```
@.aiwg/architecture/adrs/ADR-{NNN}-{slug}.md # Decision records (ADR-005-jwt-strategy.md)
@.aiwg/architecture/components/{name}.md # Component specs
@.aiwg/architecture/software-architecture-doc.md # Main SAD
@.aiwg/architecture/api-contract.md # API specifications
```
### Security
```
@.aiwg/security/threat-model.md # Main threat model
@.aiwg/security/TM-{NNN}.md # Individual threats (TM-001.md)
@.aiwg/security/controls/{control-id}.md # Security controls (authn-001.md)
```
### Testing
```
@.aiwg/testing/test-plan.md # Master test plan
@.aiwg/testing/test-cases/TC-{NNN}.md # Individual test cases
@.aiwg/testing/test-results/{run-id}.md # Test run results
```
### Code References
```
@$AIWG_ROOT/src/{path/to/file} # Source files
@test/{path/to/file} # Test files
@lib/{path/to/file} # Library files
@$AIWG_ROOT/docs/{path/to/file} # Documentation
```
## Placement Rules
### In Code Files
Place @-mentions in file header docblock:
```typescript
/**
* @file Authentication Service
* @implements @.aiwg/requirements/UC-003-user-auth.md
* @architecture @.aiwg/architecture/adrs/ADR-005-jwt-strategy.md
* @security @.aiwg/security/controls/authn-001.md
* @tests @test/integration/auth.test.ts
*/
export class AuthService {
// Implementation
}
```
### In Python Files
```python
"""
Authentication Service
@implements: @.aiwg/requirements/UC-003-user-auth.md
@architecture: @.aiwg/architecture/adrs/ADR-005-jwt-strategy.md
@security: @.aiwg/security/controls/authn-001.md
@tests: @test/integration/test_auth.py
"""
```
### In Markdown Documents
Add a References section:
```markdown
## References
- @.aiwg/requirements/user-stories.md - Functional requirements basis
- @.aiwg/architecture/software-architecture-doc.md - Architecture context
- @.aiwg/security/threat-model.md - Security considerations
```
### In Inline Comments
For specific code sections:
```typescript
// Per @.aiwg/security/controls/authn-001.md - validate token expiry
if (token.exp < Date.now()) {
throw new AuthError('Token expired');
}
```
## ID Format Rules
| Type | Format | Example |
|------|--------|---------|
| Use Case | UC-NNN | UC-001, UC-042 |
| NFR | NFR-CAT-NNN | NFR-SEC-001, NFR-PERF-002 |
| ADR | ADR-NNN | ADR-001, ADR-015 |
| Threat | TM-NNN | TM-001, TM-023 |
| Test Case | TC-NNN | TC-001, TC-150 |
**Rules**:
- Always use 3-digit zero-padded numbers
- Use lowercase for paths
- Use hyphens for slugs (not underscores)
## Best Practices
1. **Be Specific**: Reference exact documents, not directories
2. **Keep Current**: Update @-mentions when files move
3. **Validate Often**: Run `/mention-validate` before commits
4. **Lint Style**: Run `/mention-lint --fix` to normalize
5. **Generate Reports**: Use `/mention-report` for traceability audits
## CLI Equivalent
```bash
aiwg mention-conventions
```
## Related Commands
- `/mention-wire` - Add @-mentions automatically
- `/mention-lint` - Validate style conventions
- `/mention-validate` - Check all @-mentions resolve
Display conventions: $ARGUMENTSRelated Skills
mention-wire
Analyze codebase and inject @-mentions for traceability
mention-validate
Validate all @-mentions resolve to existing files
mention-report
Generate traceability report from @-mentions
mention-lint
Lint @-mentions for style consistency and correctness
aiwg-orchestrate
Route structured artifact work to AIWG workflows via MCP with zero parent context cost
venv-manager
Create, manage, and validate Python virtual environments. Use for project isolation and dependency management.
pytest-runner
Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.
vitest-runner
Execute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.
eslint-checker
Run ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.
repo-analyzer
Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.
pr-reviewer
Review GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.
YouTube Acquisition
yt-dlp patterns for acquiring content from YouTube and video platforms