skills/pr-revise/SKILL.md
Update an existing PR's title and description to reflect the full implementation. Use when: (1) User says 'revise pr', 'update pr description', 'pr revise', (2) Additional work was done after the PR was created and the title/body no longer matches, (3) User wants to sync PR metadata with the branch state.
npx skillsauth add takazudo/claude-resources pr-reviseInstall 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.
Update an existing PR's title and description to accurately reflect the full implementation, not just the original scope.
# Get current branch
BRANCH=$(git branch --show-current)
# Fetch latest
git fetch origin
# Get PR details
gh pr view "$BRANCH" --json number,title,body,baseRefName,headRefName
Record the PR number, current title, current body, and base branch.
Review ALL changes in the PR — not just recent commits:
BASE_BRANCH=<baseRefName from step 1>
# All commits in the PR
git log "origin/$BASE_BRANCH".."$BRANCH" --oneline
# Full diff stat
git diff "origin/$BASE_BRANCH"..."$BRANCH" --stat
# Full diff for understanding
git diff "origin/$BASE_BRANCH"..."$BRANCH"
Read the diff carefully. Understand:
Optional: Copilot-assisted body draft
Before drafting manually, attempt to get a Copilot-drafted body:
BASE_BRANCH=<baseRefName from step 1>
DRAFT=$($HOME/.claude/skills/gco/scripts/gco-pr-body.sh "$BASE_BRANCH" 2>/dev/null || true)
If $DRAFT is non-empty, use it as the starting point for the body. Claude must still review and adjust it — fill any gaps, fix inaccuracies, and ensure tone/completeness. If the script fails or returns empty, draft directly as below.
Based on the full diff analysis:
Title: Write a concise PR title (under 70 chars) that captures the overall scope. If the PR covers multiple concerns, summarize the primary theme.
Description: Write a comprehensive PR body using this format:
## Summary
<2-4 bullet points covering the main changes>
## Changes
<Detailed list of what was done, grouped by category if needed>
## Test Plan
<How to verify the changes work correctly>
If the original body contained issue references (e.g., Closes #123, Fixes #456), preserve them in the new body.
Present the proposed updates clearly:
Current title: <old title>
New title: <new title>
Current body:
<old body>
New body:
<new body>
Ask the user to confirm before applying.
PR_NUMBER=<number from step 1>
# Update title
gh pr edit "$PR_NUMBER" --title "<new title>"
# Update body
gh pr edit "$PR_NUMBER" --body "$(cat <<'EOF'
<new body content>
EOF
)"
Report the updated PR URL when done.
--stat first to get an overview, then read key files selectivelyDisposition of every pr-* skill regarding the Copilot-draft path:
| Skill | Disposition |
|---|---|
| /pr | Adopt (this sub-task) |
| /pr-revise | Adopt (this sub-task) |
| /pr-complete | Skip — merge/completion workflow, not text generation |
| /pr-split | Skip — structural rearrangement, not text generation |
| /pr-recreate | Skip — history cleanup, not text generation |
| /pr-make-suggestion-edit | Skip — applies code suggestions as edits, different domain |
| /pr-make-suggestion-to-pr | Defer — creates new PRs from suggestion edits; future candidate, track in a follow-up issue |
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, (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.