takazudo/pr-recreate
skills/pr-recreate/SKILL.md
Recreate a PR with clean commit history when it has too many messy commits. Use when: (1) User says 'recreate pr' or 'clean up pr history', (2) A PR has accumulated try-and-error commits and needs a fresh start, (3) User wants to squash messy history into clean logical commits.
$ install --global
skillsauthnpx skillsauth add takazudo/claude-resources pr-recreateInstall 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, 4:31 AM142.2s1 file scanned
SKILL.md
- name:
- pr-recreate
- description:
- Recreate a PR with clean commit history when it has too many messy commits. Use when: (1) User says 'recreate pr' or 'clean up pr history', (2) A PR has accumulated try-and-error commits and needs a fresh start, (3) User wants to squash messy history into clean logical commits.
- argument-hint:
- [PR_URL]
PR Recreate Command
Recreate a PR with a clean history when it has too many try-and-error commits or review comments.
IMPORTANT: This command ALWAYS uses squash merge to discard try-and-error history and create clean, meaningful commits. Never use cherry-pick.
Usage
/pr-recreate- Recreate PR for current branch/pr-recreate <PR_URL>- Recreate PR from specified URL
Steps
1. Identify Target PR
- If PR URL provided: Extract PR information using
gh pr view <URL> - If no URL: Get current branch and find PR using
gh pr list --head <current-branch>
2. Analyze PR Information
Extract:
- Old branch name
- Base branch (CRITICAL: Extract from
gh pr view --json baseRefName) - PR title
- PR number
- Original issue reference
CRITICAL: ALWAYS use the exact base branch from the original PR - NEVER default to main or develop
3. Determine New Branch Name
Check for existing versioned branches and generate next available version:
implement-foo-bar->implement-foo-bar-v2(or-v3if-v2exists)
4. Create New Branch
git fetch origin
git checkout -b <new-branch> origin/<base-branch>
5. Squash Merge Old Branch
git merge --squash origin/<old-branch>
6. Create Meaningful Commits
CRITICAL: ALWAYS create MULTIPLE meaningful commits - NEVER just one commit
- Review staged changes with
git diff --cached - Break down into logical units (feature, tests, docs, refactoring)
- Create separate commits for each unit
- Aim for 2-5 commits minimum
CRITICAL - NO COMMIT ALTERATION:
- NEVER use
git commit --amend - NEVER use
git rebase - Each commit must be created fresh
7. Push New Branch
git push -u origin <new-branch>
8. Create New PR
Use the EXACT base branch from step 2. Include:
- Original issue reference FIRST
- PR description
- Old PR reference LAST
9. Update Old PR
- Add
[outdated]prefix to title - Add comment referencing new PR
- Close old PR
10. Report Summary
- Old PR: #<number> (closed)
- New PR: #<number> (created)
- Branch:
<old-branch>-><new-branch> - Commits created
- Base branch
Important Notes
- CRITICAL: ALWAYS use squash merge to discard try-and-error history
- CRITICAL: ALWAYS use the original PR's base branch
- CRITICAL: Never alter commits (no amend, no rebase, no force push)
- CRITICAL: Create MULTIPLE meaningful commits (2-5 minimum)
- All PR titles must be in Japanese (project requirement)
- Always include the AI header in PR body and comments
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, (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