Skip to content

Tohuhono/Oberon / .agents/skills/setup-matt-pocock-skills

setup-matt-pocock-skills

Verified

Configures repository references for engineering skills without duplicating existing guidance. Use when setting up issue workflows, triage labels, or domain documentation for Matt Pocock's skills, or when those skills lack repository context.

Setup Matt Pocock's skills

Keep product behavior in public documentation. Record tracker configuration in .agents/ISSUES.md and domain paths in the root ## Agent skills section.

1. Inspect

Read the root AGENTS.md and any CLAUDE.md before changing either. Inspect existing guidance rather than assuming an upstream layout:

  • .agents/ISSUES.md and .agents/METADATA.md
  • .agents/CONTEXT.md, .agents/ARCHITECTURE.md, and any .agents/CONTEXT-MAP.md
  • .agents/CODESTYLE.md, .agents/TESTING.md, and relevant .agents/adr/ decisions
  • The public documentation linked from those files
  • git remote -v to identify the tracker
  • gh label list --limit 100 --json name,description for GitHub labels
  • Whether the triage skill is installed. Skip label setup if it is not.

2. Confirm decisions

Explain and ask about one decision at a time. Preserve approved settings on reruns unless the user requests a change.

  1. Tracker: GitHub (gh), GitLab (glab), local markdown, or a described external workflow. For local markdown, confirm a durable location rather than using .tmp/.
  2. Labels: Map category roles bug and enhancement, and state roles needs-triage, needs-info, ready-for-agent, ready-for-human, and wontfix. Each triaged issue needs one category and one state. Identify missing tracker labels.
  3. Domain docs: Confirm the existing glossary, architecture references, and ADR paths. This repo uses .agents/CONTEXT.md and optional .agents/adr/, not parallel root or docs/ files.

Upstream skills call the glossary GLOSSARY.md; use the existing .agents/CONTEXT.md instead. Keep PR discovery out of issue triage unless .agents/ISSUES.md enables it. Do not prompt to enable it during setup.

3. Show the draft

Present the root section and .agents/ISSUES.md changes before writing. Keep existing policy and product explanations in their current documents. Use these templates only where the selected tracker needs them:

4. Write

Update the existing root instruction file: CLAUDE.md if present, otherwise AGENTS.md. If neither exists, ask which one to create. Do not create a second instruction file. Update ## Agent skills in place without overwriting surrounding guidance.

Combine tracker operations and labels in .agents/ISSUES.md. Record domain paths and ADR rules in the root section. Link to public documentation for product behavior. Do not create separate tracker, label, or domain guides.

For GitHub, create missing approved labels:

gh label create "<label>" --description "<meaning>" --color "<six-digit hex>"

Preserve existing labels and their metadata. Do not use --force.

5. Verify

Confirm that the mapped labels exist in the tracker. Run pnpm format and pnpm validate from the root. Report the changed references and verification results.

rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall