メニュー
Check for and apply updates to locally installed skills from the kimgoetzke/coding-agent-configs GitHub repo. Use when user asks to update skills, sync skills, check for skill updates, or mentions updating their skills.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Review a GitHub pull request for correctness, security, observability, test coverage, and conventions. Identify applicable skills, verify and triage sub-agent findings to cut noise, score each review dimension purple-red-amber-green, and produce a structured review saved to disk and presented to the user. Use when user asks to review a PR, check a pull request, or give feedback on changes in a PR.
Walk a user through a GitHub pull request to help them understand what it does, using markdown visualisations and a guided diff-by-diff tour. Use when the user wants to understand, explore, learn from, or be walked through a PR (not when they want a formal review).
Capture aha-moments as durable insight notes under `.ai/insight/`, or quiz the user on past insights to reinforce recall. Use when the user has just learnt something non-obvious (a fix they didn't know, an explanation that clicked, a gotcha discovered) and wants to record it, or when the user invokes `/aha quiz` to be tested on stored insights.
Toggle persistent planning mode on/off. When on, hook support can remind the agent to keep planning documents updated throughout the conversation, with manual fallback if unavailable. Combines the full planning workflow with persistent mode for long-running planning and implementation sessions. Use with a topic to start, with "continue" to resume an existing plan, or with "off" to stop.
Planning a change to any codebase. Use when user asks you to plan something instead of taking immediate action.
Toggle persistent research mode on/off. When on, hook support can remind the agent to keep the research document updated throughout the conversation, with manual fallback if unavailable. Use with a research topic to start, with "continue" to resume an existing research doc, or with "off" to stop.
| name | update-skills |
| description | Check for and apply updates to locally installed skills from the kimgoetzke/coding-agent-configs GitHub repo. Use when user asks to update skills, sync skills, check for skill updates, or mentions updating their skills. |
| disable-model-invocation | true |
Check for updates to locally installed skills by fetching the latest from kimgoetzke/coding-agent-configs on GitHub and comparing against the local skills directory.
https://github.com/kimgoetzke/coding-agent-configs.gitscripts/ directory| Tool | Default target directory |
|---|---|
| Claude Code | ~/.claude/skills |
| Copilot | ~/.copilot/skills |
| Pi | ~/.pi/agent/skills |
If you cannot determine which tool you are, ask the user.
Set the target directory based on the table above. Use the variable TARGET_DIR in subsequent steps.
Also resolve SKILL_DIR to the absolute path of this locally installed skill directory. Typical values:
~/.claude/skills/update-skills~/.copilot/skills/update-skills~/.pi/agent/skills/update-skillsRun the check script:
bash "$SKILL_DIR/scripts/check-updates.sh" "$TARGET_DIR"
The script outputs one line per skill with a status prefix:
| Prefix | Meaning |
|---|---|
UP_TO_DATE:<name> | No changes |
CHANGED:<name> | Files differ — diff follows until END_DIFF line |
MISSING_LOCALLY:<name> | Exists in repo but missing locally |
ALL_UP_TO_DATE | No updates available at all |
Skills that exist locally but not in the remote repo are ignored.
ALL_UP_TO_DATE: tell the user all skills are up to date and stopCHANGED or MISSING_LOCALLY skill:
For each skill the user approves, run:
bash "$SKILL_DIR/scripts/apply-update.sh" "$TARGET_DIR" <skill-name>
Report success or failure for each.
After processing all skills, print a summary:
Finally, ask the user if they wish to use the /update-agents skill to sync any agents from the remote repo.