understand-scrap-issues — Claude Code skill: setup and usage
Fetches up to three recent open GitHub issues labeled maintainer-scrap and extracts their context, background, and next steps before you start coding.
npx skills add dyoshikawa/rulesync --skill understand-scrap-issues -a claude-codeWhat understand-scrap-issues does
The skill queries GitHub via gh issue list --label maintainer-scrap --state open --limit 3 --json number,title,url,createdAt. If no matching issues are returned, the process stops immediately and informs you.
For each returned note, the agent executes gh issue view <issue_number> and gh issue view <issue_number> --comments to read the issue body and ongoing discussions. When relevant pull requests or commits are referenced, it inspects those as well. The resulting summary breaks each issue into topic, background motivation, findings, and proposed next steps.
Without an authenticated gh CLI installed in your terminal, the skill cannot fetch issues and will fail.
What it helps with
- summarize recent raw maintainer notes stored in GitHub issues
- extract action items and background context from issue comments
- review open
maintainer-scraptasks without switching to the browser
Example prompts for the agent
- Check the latest maintainer-scrap issues and explain what needs to be done.
- Fetch open scrap notes from GitHub and list their proposed solutions.
How to install understand-scrap-issues
1Skills CLI (Vercel)
npx skills add dyoshikawa/rulesync --skill understand-scrap-issues -a claude-code2Manually: put the files in place
~/.claude/skills/understand-scrap-issues/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/understand-scrap-issues/
1Skills CLI (Vercel)
npx skills add dyoshikawa/rulesync --skill understand-scrap-issues -a codex2Manually: put the files in place
.agents/skills/understand-scrap-issues/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add dyoshikawa/rulesync --skill understand-scrap-issues -a cursor2Manually: put the files in place
.cursor/skills/understand-scrap-issues/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install dyoshikawa/rulesync understand-scrap-issues2Manually: put the files in place
.github/skills/understand-scrap-issues/SKILL.md1Skills CLI (Vercel)
npx skills add dyoshikawa/rulesync --skill understand-scrap-issues -a gemini-cli2Platform CLI
gemini skills install https://github.com/dyoshikawa/rulesync --path .rulesync/skills/understand-scrap-issuesManually: put the files in place
.devin/skills/understand-scrap-issues/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add dyoshikawa/rulesync --skill understand-scrap-issues -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about understand-scrap-issues
How to install understand-scrap-issues in Claude Code?
Run npx skills add dyoshikawa/rulesync --skill understand-scrap-issues -a claude-code or place the definition file at ~/.claude/skills/understand-scrap-issues/SKILL.md.
What does understand-scrap-issues do?
It lists up to three newest open issues labeled maintainer-scrap, gathers their discussion threads, and provides an overview with topic, context, and next steps.
What prerequisites are required?
You need the gh command-line tool installed and logged in, because the skill uses gh issue list and gh issue view to retrieve data.
Source text
SKILL.md · MIT
--- name: understand-scrap-issues description: >- Fetch the most recent maintainer-scrap issues (up to 3) and understand their content targets: - "*" --- Fetch the newest scrap issues (GitHub issues labeled `maintainer-scrap`) and understand what each one is about, so you can catch up on recently jotted-down notes before acting on them. ## Step 1: Fetch the Latest Scrap Issues List the most recent open issues that carry the `maintainer-scrap` label. `gh issue list` returns issues in creation order (newest first), so limiting to 3 yields the 3 newest: ```bash gh issue list --label maintainer-scrap --state open --limit 3 --json number,title,url,createdAt ``` If the result is empty, report that there are no open scrap issues and stop. ## Step 2: Gather Each Issue's Content For each scrap issue returned, read both the body and the discussion. Run these in parallel across the issues where practical: ```bash gh issue view <issue_number> gh issue view <issue_number> --comments ``` If an issue references related pull requests, commits, or files that are needed to understand it, gather that context as well. ## Step 3: Understand and Summarize For each scrap issue, explain the following based on its content: 1. **Topic:** A one-line summary of what the scrap note is about. 2. **Background:** The context, motivation, or problem the note captures and why it matters. 3. **Details / Findings:** The specific observations, problems, or content recorded in the note. 4. **Proposed Solution / Next Steps:** Any solution or actionable next step mentioned. If none is recorded, state explicitly that it is still undecided. Keep each summary concise and focused. Present the issues in the order returned (newest first), with the issue number, title, and URL as a heading for each. Use the language of the current conversation (follow the user's language).
© dyoshikawa · MIT · dyoshikawa/rulesync