takazudo/pr-split
skills/pr-split/SKILL.md
Split a multi-feature pull request into smaller, focused PRs. Use when: (1) User says 'split pr' or 'break up pr', (2) A PR contains multiple independent features that should be reviewed separately, (3) User wants to decompose a large PR.
$ install --global
skillsauthnpx skillsauth add takazudo/claude-resources pr-splitInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 8, 2026, 4:32 AM153.1s1 file scanned
SKILL.md
- name:
- pr-split
- description:
- Split a multi-feature pull request into smaller, focused PRs. Use when: (1) User says 'split pr' or 'break up pr', (2) A PR contains multiple independent features that should be reviewed separately, (3) User wants to decompose a large PR.
PR Split Command
Split a multi-feature pull request into smaller, focused PRs.
IMPORTANT: This command ALWAYS uses squash merge to discard try-and-error history and create clean, meaningful commits. Never use cherry-pick.
Process
1. Analyze Current PR
- Check current branch and commits
- Use
gh pr viewfor PR details - CRITICAL: Extract EXACT base branch using
gh pr view --json baseRefName - Extract original issue reference
- Run
git log origin/<BASE>..HEAD(not main!) - Identify distinct features/fixes
2. Determine if Split is Needed
- Check if PR contains multiple independent features
- If single feature, inform user split not needed
- If beneficial, explain what will be split
3. Plan the Split
- Use the EXACT base branch from step 1
- List distinct features/fixes to split
- Present plan for user approval
4. Execute Split
For each split feature:
a. Create new branch from base
git fetch origin
git checkout -b feature/split-name origin/<base-branch>
b. Apply changes using squash merge
git merge --squash original-branch
-
Review staged changes
-
Unstage files not related to this feature
-
Create clean, logical commits
CRITICAL - NO COMMIT ALTERATION:
-
NEVER use
git commit --amend -
NEVER use
git rebase
c. Push and create PR
- Use
gh pr create --base <base-branch> - Include original issue reference FIRST
- Include old PR reference LAST
5. Handle Original PR
- Add
[outdated]prefix to title - Update description with references to new PRs
- Close with comment listing new PRs
Important Notes
- CRITICAL: ALWAYS use the original PR's base branch for ALL new PRs
- CRITICAL: Compare against the correct BASE branch
- CRITICAL: Never alter commits (no amend, no rebase, no force push)
- CRITICAL: Mark original PR as outdated
- All PR titles must be in Japanese (project requirement)
- Always use squash merge to create clean commits
- Ask for confirmation before executing
Related Skills
takazudo/dev-linkify-cc-resources
development
VerifiedTrustedCommunity
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.
10SKILL.mdUpdated Jun 2, 2026
takazudo/opus-2nd
development
VerifiedTrustedCommunity
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.
10SKILL.mdUpdated May 29, 2026
takazudo/dev-ai-based-test
tools
VerifiedTrustedCommunity
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.
10SKILL.mdUpdated May 29, 2026
takazudo/cleanup-resources
development
VerifiedTrustedCommunity
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.
10SKILL.mdUpdated May 29, 2026