skills/git-filtered-merge/SKILL.md
Filtered squash merge: take only matching paths (e.g., doc/) from a source branch and apply them to a target branch via squash merge, PR creation. Use when: (1) User says 'filtered merge', 'sync doc to develop', 'cherry-pick directory', (2) User wants to sync a subset of changes between branches, (3) User needs to apply only specific directory or file changes from one branch to another.
npx skillsauth add takazudo/claude-resources git-filtered-mergeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Squash merge a source branch into a new branch off the target, keep only paths matching a filter, then commit, push, and create a PR.
Collect via AskUserQuestion (single prompt with all questions):
develop)base/fanbassador-post)doc/)sync-doc-to-develop)If the skill was invoked with an argument, use it as the branch name and skip asking for it.
1. git fetch origin
2. Show filtered diff: git diff origin/<base>...<source> -- <filter-paths> --stat
- If no changes, abort with message
- Show to user for confirmation before proceeding
3. git checkout -b <branch-name> origin/<base>
4. git merge --squash <source>
5. git reset HEAD
6. git add <filter-paths>
7. git checkout -- . && git clean -fd
8. git diff --cached --stat (verify only filtered changes staged)
9. Commit with message: "docs: <source> ブランチの変更を <base> に同期"
- Adjust prefix (docs/feat/fix) based on content
10. git push -u origin <branch-name>
11. gh pr create --base <base> with project CLAUDE.md conventions
12. Return PR URL
development
Link Claude Code skill names mentioned in a CodeGrid article (data/{series}/{n}.md) to the author's public claude-resources repo, pinned to the latest commit hash so links don't rot. Use when: (1) user says 'linkify cc resources', 'link the skills', 'link skill names', or invokes /dev-linkify-cc-resources; (2) editing a CodeGrid article that mentions `/commits`, `/pr-complete`, `/skill-creator` or other Claude Code skills and they should point to claude-resources. Only links skills that actually exist in the public repo; skips hypothetical examples and code blocks.
development
Second opinion from Claude Opus on a plan or approach. Use when: (1) Planning phase of /big-plan needs a higher-quality review than /codex-2nd / /gco-2nd / /gcoc-2nd, (2) User says 'opus 2nd' or 'opus opinion', (3) Wanting Anthropic's larger model to critique a plan. Spawns a general-purpose Agent with model: opus that reads the plan file and returns structured feedback. Anthropic quota — not free.
tools
AI-based testing via subagent + a per-task test-flow skill. Use when the user wants to verify something that mechanical assertions can't fully capture — image recognition, visual size/position comparison, animation smoothness, multi-step manual flows that need AI judgment. Triggers: 'AI-based test', 'AI test', 'visual verify', 'image recognition test', 'manual operation test', 'human-eye check', 'verify visually', 'compare screenshots', 'looks the same', 'looks correct'. The skill's job is to (1) author a focused test-flow skill that captures the exact procedure + verdict criteria, then (2) dispatch a verification subagent via the Agent tool that loads BOTH the test-flow skill AND a browser-driving skill (/verify-ui primary, /headless-browser fallback) so the subagent has clear context and consistent verdicts. NEVER uses `claude -p` — subagent dispatch goes through the Agent tool exclusively.
development
End-of-workflow audit of touched GitHub issues, PRs, and branches via a Sonnet subagent. Use when: (1) /big-plan, /x-as-pr, or /x-wt-teams finishes its main work and needs to verify every touched resource is in the right state (closed when done, kept when ongoing, deleted when dead), (2) User says 'cleanup resources', 'audit cleanup', or 'check what should be closed', (3) A long workflow ends and the manager wants a structured paper trail of what it closed/kept/deleted. Auto-execute by default — the Sonnet agent proposes, the manager (you) executes safe actions and prints a final report.