tumftumf/skills/AGENTS.md

skills

AGENTS.md4 starsChanged 7 months agoMITView on GitHub

This is a collection of skills for AI coding agents following the Agent Skills format. For specific development guidelines, see: - Python Style Guide - Script structure, formatting, error handling - Documentation Standards - SKILL.md and README.md formats - Development Workflow - Creating skills, Git workflow - Project Standards - JSON output, environment variables, licensing

Create a free account to mount

Files

AGENTS.md

Agent Development Guidelines

This is a collection of skills for AI coding agents following the Agent Skills format.

Repository Structure

skills/
├── README.md              # Main documentation
├── LICENSE                # MIT License
├── .gitignore            # Git ignore rules
└── {skill-name}/         # Individual skill directories
    ├── SKILL.md          # Agent instructions (YAML frontmatter + docs)
    ├── README.md         # Full documentation for users
    └── scripts/          # Executable Python scripts

Quick Commands

# Make scripts executable
chmod +x {skill}/scripts/*.py

# Run a script
./{skill}/scripts/{script-name}.py [arguments]

# Example
./firecrawl/scripts/scrape.py "https://example.com"

# Validate repository metadata
python3 scripts/validate_skills.py

# Regenerate the top-level README skill index, then re-check
python3 scripts/validate_skills.py --write
python3 scripts/validate_skills.py

Detailed Guidelines

For specific development guidelines, see:

Python Style Guide - Script structure, formatting, error handling
Documentation Standards - SKILL.md and README.md formats
Development Workflow - Creating skills, Git workflow
Project Standards - JSON output, environment variables, licensing

Download now (ZIP)

In this repository25 other files it gives its agents.
- greats-soul-archive-contributor/AGENTS.mdAGENTS.md
- agentic-cli-designSkill
- ai-chat-frontendSkill
- autoresearch-agentSkill
- brainstorm-frameworksSkill
- business-planningSkill
- clawdbot-configSkill
- dashboard-design-guidebookSkill
- fermi-estimationSkill
- firecrawlSkill
- gogcliSkill
- greats-soul-archive-contributorSkill
- jp-grantsSkill
- openclaw-agent-creatorSkill
- opencode-agent-creatorSkill
- opencode-command-creatorSkill
- openspec-brownfield-baselineSkill
- oss-publishSkill
- product-improvement-proposalSkill
- python-uv-projectSkill
- rust-cliSkill
- slack-rsSkill
- unit-test-hygieneSkill
- wt-setupSkill
- youtube-summarizerSkill

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free