agent-skill-observatory-conventions
Development conventions and patterns for agent-skill-observatory. Python project with conventional commits.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-11
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- agent-skill-observatory-conventions
- description
- Development conventions and patterns for agent-skill-observatory. Python project with conventional commits.
03 SKILL.md 正文
Agent Skill Observatory Conventions
Generated from imMamdouhaboammar/agent-skill-observatory on 2026-09-09
Overview
This skill teaches Claude the development patterns and conventions used in agent-skill-observatory.
Tech Stack
- Primary Language: Python
- Architecture: hybrid module organization
- Test Location: separate
When to Use This Skill
Activate this skill when:
- Making changes to this repository
- Adding new features following established patterns
- Writing tests that match project conventions
- Creating commits with proper message format
Commit Conventions
Follow these commit message conventions based on 16 analyzed commits.
Commit Style: Conventional Commits
Prefixes Used
feattestcidocsdatabuild
Message Guidelines
- Average message length: ~38 characters
- Keep first line concise and descriptive
- Use imperative mood ("Add feature" not "Added feature")
Commit message example
feat: add GitHub-native catalog publisher
Commit message example
ci: refresh and publish catalog every 15 minutes
Commit message example
docs: expose GitHub-native Awesome directory
Commit message example
data: seed repository rollups
Commit message example
test: cover Markdown catalog publishing
Commit message example
feat: add repository catalog rollups
Commit message example
feat: add catalog publish command
Commit message example
feat: add generated Awesome catalog surface
Architecture
Project Structure: Single Package
This project uses hybrid module organization.
Source Layout
src/
├── skill_observatory/
Configuration Files
.github/workflows/pages.yml.github/workflows/refresh.yml
Guidelines
- This project uses a hybrid organization
- Follow existing patterns when adding new code
Code Style
Language: Python
Naming Conventions
| Element | Convention |
|---|---|
| Files | camelCase |
| Functions | camelCase |
| Classes | PascalCase |
| Constants | SCREAMING_SNAKE_CASE |
Import Style: Relative Imports
Export Style: Named Exports
Preferred import style
// Use relative imports
import { Button } from '../components/Button'
import { useAuth } from './hooks/useAuth'
Preferred export style
// Use named exports
export function calculateTotal() { ... }
export const TAX_RATE = 0.1
export interface Order { ... }
Testing
Test Framework
No specific test framework detected — use the repository's existing test patterns.
File Pattern: *.test.ts
Test Types
- Unit tests: Test individual functions and components in isolation
Common Workflows
These workflows were detected from analyzing commit patterns.
Feature Development
Standard feature implementation workflow
Frequency: ~11 times per month
Steps:
- Add feature implementation
- Add tests for feature
- Update documentation
Example commit sequence:
feat: add GitHub-native catalog publisher
feat: add repository catalog rollups
feat: add catalog publish command
Best Practices
Based on analysis of the codebase, follow these practices:
Do
- Use conventional commit format (feat:, fix:, etc.)
- Follow *.test.ts naming pattern
- Use camelCase for file names
- Prefer named exports
Don't
- Don't write vague commit messages
- Don't skip tests for new features
- Don't deviate from established patterns without discussion
This skill was auto-generated by ECC Tools. Review and customize as needed for your team.
04 同仓库更多 Skills
sample-skill
Analyze repositories and produce evidence-based engineering findings. Use when reviewing unfamiliar codebases.
risky-skill
Performs maintenance tasks. Use when maintaining a project.
agent-skill-observatory
Evidence-based discovery, specification validation, static security analysis, and multi-dimensional scoring for open Agent Skills across GitHub and local workspaces. Use when an agent needs to evaluate a skill before installation, scan a local skill directory for malicious or risky instructions, audit specification compliance, or inspect catalog evidence across Claude Code, Codex, Antigravity, Cursor, OpenCode, and Skills.sh. DO NOT USE for executing unvetted third-party skill code or general non-skill tasks.
agent-skill-observatory
Evidence-based discovery, specification validation, static security analysis, and multi-dimensional scoring for open Agent Skills across GitHub and local workspaces. Use when an agent needs to evaluate a skill before installation, scan a local skill directory for malicious or risky instructions, audit specification compliance, or inspect catalog evidence across Claude Code, Codex, Antigravity, and Cursor. DO NOT USE for executing unvetted third-party skill code or general non-skill tasks.