From agentic-doc
Scaffold a compact AGENTS.md file with project-specific content. Use when the user wants to create, set up, add, or generate an AGENTS.md for their project. Also triggers on 'set up agent docs', 'create AGENTS.md', 'add AGENTS.md', 'scaffold AGENTS.md'.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentic-doc:agd-init-agents-mdThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Create a compact, lean AGENTS.md file tailored to the current project. Default to a single file; ask about references folder only if the project is complex.
Create a compact, lean AGENTS.md file tailored to the current project. Default to a single file; ask about references folder only if the project is complex.
Load both skills for comprehensive context:
AGENTS.md format - Load agents-md skill:
Use Skill tool with skill="agd:agents-md"
Provides: sections, structure, best practices
Commit format - Load conventional-commits skill (for PR/Commit Guidelines section):
Use Skill tool with skill="agd:conventional-commits"
Provides: Conventional Commits types, style rules, examples
Analyze the project:
package.json, Cargo.toml, go.mod, pyproject.toml, etc.Detect project type:
ls -la
cat package.json 2>/dev/null | head -50
Gather context:
Generate compact AGENTS.md using the format from the skill:
./docs/agents/testing.md, ../api/AGENTS.md)../shared/utils/)Write the file to the specified path (default: ./AGENTS.md)
Validate the generated file:
Ask about references folder using AskUserQuestion: Ask: "Would you like me to create a references folder for detailed documentation?"
Options:
Only ask if:
Ask about symlinks (from skill best practices):
Call AskUserQuestion:
{
"questions": [{
"question": "Would you like me to create symlinks for other AI agents?",
"header": "Symlinks",
"options": [
{"label": "No symlinks", "description": "Keep AGENTS.md as the only file."},
{"label": "Create CLAUDE.md", "description": "Symlink CLAUDE.md → AGENTS.md for Claude Code compatibility."},
{"label": "Create all symlinks", "description": "Create CLAUDE.md, .cursorrules, and .windsurfrules all pointing to AGENTS.md."}
]
}]
}
ln -sf AGENTS.md CLAUDE.mdln -sf AGENTS.md CLAUDE.md && ln -sf AGENTS.md .cursorrules && ln -sf AGENTS.md .windsurfrules| Config File | Detected Context |
|---|---|
package.json | npm/pnpm/yarn commands, scripts |
Cargo.toml | Rust: cargo build, cargo test |
go.mod | Go: go build, go test ./... |
pyproject.toml | Python: poetry/pip commands |
Makefile | Make targets |
Use this format when asking about references folder:
questions: [
{
"question": "Would you like me to create a references folder for detailed documentation?",
"header": "References",
"options": [
{
"label": "No, single file is enough",
"description": "Keep AGENTS.md as a simple, compact file. Recommended for most projects."
},
{
"label": "Yes, create docs/agents/",
"description": "Create references folder with detailed docs for architecture, patterns, tutorials."
},
{
"label": "Yes, use custom path",
"description": "Specify a custom path for the references folder."
}
]
}
]
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub christophe1997/agent-extentions --plugin agentic-doc