skills/pr/SKILL.md
Create a pull request with intelligent base branch detection. Use when: (1) User says 'create pr', 'make pr', or 'open pr', (2) User wants to create a PR from the current branch, (3) User has finished work on a feature branch and needs a PR. Auto-detects base branch from conversation, git history, or repo default.
npx skillsauth add takazudo/claude-resources prInstall 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.
Create a pull request with automatic base branch detection from conversation history, git log, or repository default.
/pr - Create PR with auto-detected base branch/pr <target-branch> - Create PR targeting the specified branchgit status
git branch --show-current
Ensure you're on a feature branch (not main/master/develop).
Priority order for base branch detection:
<target-branch> is provided, use it directlySearch the current conversation for clues about the base branch:
# Fetch latest remote refs
git fetch origin
# Find merge-base with candidate branches
for branch in main master develop staging; do
git merge-base HEAD origin/$branch 2>/dev/null && echo "Found: $branch"
done
# Check which branch has the closest merge-base
# The branch with most recent common ancestor is likely the parent
# Get the default branch
gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name'
gh pr list --head $(git branch --show-current)
If PR exists, ask user if they want to view or update it.
# Get commits
git log origin/<base-branch>..HEAD --oneline
# Get file changes
git diff origin/<base-branch>..HEAD --stat
Before creating, confirm:
<branch-name><base-branch> (with detection method: "specified", "from conversation", "auto-detected", or "default")Optional: Copilot-assisted body draft
Before drafting the body manually, attempt to get a Copilot-drafted body:
DRAFT=$($HOME/.claude/skills/gco/scripts/gco-pr-body.sh "<base-branch>" 2>/dev/null || true)
If $DRAFT is non-empty, use it as the starting point for the body. Claude must still review and adjust it — fill any gaps, fix inaccuracies, and ensure tone/completeness. If the script fails or returns empty, draft the body directly.
# Push if needed
git push -u origin $(git branch --show-current)
# Create PR
gh pr create \
--base <base-branch> \
--title "<title>" \
--body "$(cat <<'EOF'
## Summary
<description>
## Changes
- <change 1>
- <change 2>
## Test Plan
<testing instructions>
EOF
)"
Copilot output is NEVER applied verbatim — always review and adjust before creating the PR.
Display:
The command uses this logic to find the base branch:
gh repo viewIf detection is ambiguous, ask the user to clarify before creating the PR.
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.