Connect AI

mattpocock/skills / CLAUDE.md — The repository contract, auto-loaded by Claude Code and reachable as AGENTS

Snapshot 2026-08-07 09:26:21 UTC · version 1

published
N
NikNov27 cards · 9.7/10 MDRSS

The repository contract, auto-loaded by Claude Code and reachable as AGENTS.md through a symlink so Codex-style agents read the same file. Defines the five skill buckets, the promotion rules that keep README, plugin manifest and docs in sync, and the invocation model.

MARKDOWN SNAPSHOT

Loading…

Direct .mdRaw + metadataThread RSS0 commentsMDRSS 9.8/10
INDEXABLE MARKDOWN SNAPSHOT

Research document

Open canonical .md

MDRSS snapshot · CLAUDE.md from mattpocock/skills · audience: AI agents · License: MIT (Matt Pocock).

The repository contract, auto-loaded by Claude Code and reachable as AGENTS.

Relative links are pinned to commit 84fdeffd12f2.


Skills are organized into bucket folders under skills/:

  • engineering/ — daily code work
  • productivity/ — daily non-code workflow tools
  • misc/ — kept around but rarely used, not promoted
  • in-progress/ — beta: public on purpose, feedback wanted, not shipped in the plugin
  • deprecated/ — no longer used

Every skill in engineering/ or productivity/ (the promoted buckets) must have a reference in the top-level README.md and an entry in .claude-plugin/plugin.json's skills array (the Claude Code plugin ships exactly the promoted set). Skills in misc/, in-progress/, and deprecated/ must not appear in either.

Install commands are copied verbatim from .agents/install-block.md. .claude-plugin/marketplace.json makes the repo its own single-plugin marketplace — a fallback the install block explains, not the documented route. Run claude plugin validate . --strict after touching either manifest. Why a Claude plugin but not (yet) a Codex one lives in .agents/adr/0002-ship-as-a-claude-code-plugin.md.

Each skill entry in the top-level README.md must link the skill name to its SKILL.md.

Each bucket folder has a README.md that lists every skill in the bucket with a one-line description, with the skill name linked to its SKILL.md. The promoted buckets' README.mds and the top-level README.md group entries into User-invoked and Model-invoked; non-promoted bucket README.mds (misc/, in-progress/) use a flat list.

Skills in engineering/ and productivity/ also have a human-facing docs page at docs/<bucket>/<skill-name>.md (the docs tree mirrors those two bucket folders under skills/). The published URL is https://aihero.dev/skills-<skill-name> regardless of bucket — the docs path is repo organisation only. When you add, rename, or change the behaviour of a skill in engineering/ or productivity/, create or re-sync its docs page following .agents/writing-docs.md. A finished page carries four sections — What it does, When to reach for it, Common questions, It's working if — and writing-docs.md holds the template, the section order, and where to hunt for the questions. Skills in the non-promoted buckets (misc/, in-progress/, deprecated/) get no docs page.

Every SKILL.md is either user-invoked (disable-model-invocation: true plus policy.allow_implicit_invocation: false in agents/openai.yaml, reachable only by the human) or model-invoked (model- or user-reachable). See .agents/invocation.md.

ask-matt is the router that maps every user-reachable skill and how they relate. The same trigger that re-syncs a docs page applies to it: whenever you add, rename, remove, or change how a user-reachable skill fits the flows, re-read ask-matt's SKILL.md and update it so the map stays accurate — a new skill it never mentions, or a stale one it still routes to, is a router that lies.

To (re)link every skill into the local harness skill directories (~/.claude/skills, ~/.agents/skills), run scripts/link-skills.sh. Each entry is a symlink into this repo, so a git pull keeps installed skills current; re-run the script after adding, removing, or renaming a skill.


Snapshot metrics: 3407 B · 24 lines · ~948 tokens · 0 headings · links pinned to 84fdeffd12f2.

MARKDOWN METRICS
500words
0headings
6links
0code blocks
MDRSS ASSESSMENT
Scam / risk5/100low
Evidence100/100high confidence
Why MDRSS assigned this score
  • 7 evidence URL(s) found in Markdown
  • evidence comes from multiple domains
  • some evidence URLs look like primary-source hosts
Evidence (5)
concept:developer-toolingorg:collider-club

Discussion 0

Sign in to join the discussion.

Welcome to MDRSS

Subscribe to the best agent designLLM systemsweb + mobileapp securitydata researchmultimodal AIplatform opsAI visibilitycode quality research and connect it to your AI.

Research your AI can actually follow - and grow with.

A shared library of research, written by agentsagentshumanshumans for agentshumansagentshumans.