agentsclimarketplace

Scaffold agent docs

Skill Mergemat/agent-readiness-skills/skills/scaffold-agent-docs

Harness-agnostic skills for agent-readable repos and task prep

Install
npx -y skills add Mergemat/agent-readiness-skills --skill scaffold-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

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 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.

What its author says it does

Copied from the file, not written here

Creates minimal agent-readable project docs without importing a large readiness framework. Use when user wants to set up AGENTS.md, CONTEXT.md, docs/agents, build/test/owner/tool-policy docs, or prepare a repo for coding agents.

SKILL.md

1.6 KB, 319 tokens by cl100k_base, as published. Nobody here has run it

Scaffold Agent Docs

Create the smallest useful set of project-owned facts for agents.

Do not create placeholder documents just to match a standard. Prefer one accurate paragraph over a full empty template.

Process

  1. Inspect existing agent instructions, domain docs, ADRs, package scripts, CI, and test config.
  2. Reuse existing files when they already serve the purpose.
  3. Propose the exact files to create or update.
  4. Write only facts discovered from the repo or confirmed by the user.
  5. Mark unknown but required facts as TBD with owner or follow-up, not invented values.

Default Layout

Use this layout unless the project already has a clearer one:

AGENTS.md
CONTEXT.md
docs/agents/build.md
docs/agents/testing.md
docs/agents/owners.md
docs/agents/tool-policy.md
docs/adr/

Use templates.md only when drafting files.

Boundaries

  • AGENTS.md: routing instructions and stop conditions.
  • CONTEXT.md: domain vocabulary only.
  • docs/agents/build.md: install, build, run, env facts.
  • docs/agents/testing.md: checks and known failures.
  • docs/agents/owners.md: decision owners and escalation.
  • docs/agents/tool-policy.md: allowed tools, connectors, skills, hooks, approvals.
  • docs/adr/: durable decisions only.

If a procedure appears in these docs, move it to a skill or reference an existing skill.

What ships with it: 1 file

1.3 KB alongside SKILL.md

references/

Keep looking

Skills are one crate of 326,984. 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.