agent-skills

58 Claude Code skills and 9 autonomous agents. Polyglot dev, web3, ZK, genomics, UI/UX, systems programming.

How skill loading works

This is probably your first question, so let's get it out of the way.

Skills are lazy. Claude Code reads the short trigger clause from each SKILL.md frontmatter -- the first few lines per skill -- and only pulls in the full skill content when the trigger matches your conversation. The sub-files (examples, checklists, reference tables) stay out of context until they're actually needed.

What's always present: ~2-4 lines of trigger description per skill. What's lazy: everything else. 58 skills at a few lines each is a small fraction of the context window. The heavy content -- sometimes hundreds of lines of domain-specific reference -- only loads when you're actually working in that domain.

So no, installing all 58 won't bloat your sessions. I.E. the noir ZK skill isn't eating tokens while you're reviewing a PR.

Skills

Each skill lives in skills/<name>/ with a SKILL.md entry point.

Domain

Workflow

Infrastructure

Meta

Agents

Nine standalone tools, each with a Typer CLI, pydantic models, and a FastMCP server. They run independently of the skill system -- install them separately, talk to them over MCP.

MCP integration

Each agent doubles as an MCP server. Add to ~/.mcp.json:

{
  "mcpServers": {
    "digest": { "command": "digest", "args": ["serve"] },
    "recall": { "command": "recall", "args": ["serve"] },
    "scribe": { "command": "scribe", "args": ["serve"] },
    "autoresearch": { "command": "autoresearch", "args": ["serve"] },
    "watchdog": { "command": "watchdog", "args": ["serve"] },
    "prepper": { "command": "prepper", "args": ["serve"] },
    "sentinel": { "command": "sentinel", "args": ["serve"] },
    "patchbot": { "command": "patchbot", "args": ["serve"] },
    "regen": { "command": "regen", "args": ["serve"] },
    "coingecko": { "url": "https://mcp.api.coingecko.com/mcp" }
  }
}

See TODO.md for the roadmap.

Install

Claude Code plugin

/plugin install agent-skills@DROOdotFOO/agent-skills

Or add the marketplace first:

/plugin marketplace add DROOdotFOO/agent-skills

npx

Pick individual skills:

npx skills@latest add DROOdotFOO/agent-skills/tdd
npx skills@latest add DROOdotFOO/agent-skills/code-review
npx skills@latest add DROOdotFOO/agent-skills/polymath

Or grab everything:

npx skills@latest add DROOdotFOO/agent-skills

chezmoi

Add to .chezmoiexternal.toml:

[".agents/skills"]
    type = "archive"
    url = "https://github.com/DROOdotFOO/agent-skills/archive/main.tar.gz"
    stripComponents = 2
    include = ["*/skills/**"]
    refreshPeriod = "168h"

Then symlink into Claude Code:

mkdir -p ~/.claude/skills
for d in ~/.agents/skills/*/; do
    ln -sf "../../.agents/skills/$(basename "$d")" ~/.claude/skills/
done

Manual

git clone https://github.com/DROOdotFOO/agent-skills.git ~/.agents/skills-repo
ln -s ~/.agents/skills-repo/skills ~/.agents/skills

Agents

Each agent installs independently:

cd agents/<name> && pip install -e .

Lint

./scripts/skills-lint.sh

Checks frontmatter, trigger clauses, file references, and cross-skill links.

License

MIT