agentsclimarketplace
Sign in

Setup agent docs

Skill martonpaulo/skills/setup-agent-docs

Configure lightweight per-repository conventions for optional domain glossaries, ADRs, research notes, handoffs, and disposable prototypes. Use when the user directly requests these artifact paths or when setup-project delegates this step after establishing root guidance. Do not use for complete project setup, ordinary documentation edits, personal-skill configuration, trackers, tickets, labels, or backlog workflows.From its SKILL.md

Install
npx -y skills add martonpaulo/skills --skill setup-agent-docs

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 17 days oldThe repository was created 17 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.8 KB, 514 tokens by cl100k_base, as published. Nobody here has run it

Setup Agent Docs

Run this setup once per repository when the user wants explicit paths for artifacts written by the project skills in this collection. It may be invoked directly or as the delegated final documentation step of setup-project, and it must remain safe to run again.

Keep this skill model-invocable because setup-project calls it through the agent's skill tool. The already explicit parent setup request authorizes this narrow documentation step; it does not authorize any broader project mutation.

Scope: only project skills produce repository artifacts. Personal-use skills such as disk-cleaner and grey-market operate on the user's machine, not on a repository, never configure paths, conventions, or guidance for them.

Workflow

  1. Inspect existing guidance and conventions before proposing anything:
    • AGENTS.md
    • CLAUDE.md
    • CONTRIBUTING.md
    • existing architecture and documentation directories
    • existing glossary, ADR, research, handoff, and prototype paths
  2. Reuse established paths where they are clear. Ask only which still-unconfigured artifact types the user actually wants.
  3. Suggested defaults when no convention exists:
    • domain glossary: CONTEXT.md
    • ADRs: docs/adr/
    • research: docs/research/
    • handoffs: .scratch/handoffs/
    • prototypes: .scratch/prototypes/
  4. Show the short configuration block before writing it.
  5. Record only selected conventions in existing repository guidance. Prefer AGENTS.md; use CLAUDE.md when it is the repository's active agent guidance. If neither exists, create AGENTS.md only with the user's selected conventions.
  6. If a ## Agent skill paths section already exists, update it in place. Preserve surrounding content and remove entries the user no longer wants.

Example block:

## Agent skill paths

- Domain glossary: `CONTEXT.md` (optional; create only when useful)
- Research notes: `docs/research/` (create only when persisting research)
- Handoffs: `.scratch/handoffs/`
- Prototypes: `.scratch/prototypes/`

Safety and completion

Do not create empty files or directories. Do not introduce process configuration unrelated to these optional artifact paths. Setup is complete when the selected paths appear once in the active guidance file and a second run would update rather than duplicate the block.

What ships with it: 2 files

2.9 KB alongside SKILL.md

agents/

Keep looking

Skills are one crate of 326,852. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.