TheCardGoat/.agents/skills/review-pr-comments
.agents/skills/review-pr-comments/SKILL.md
--- name: review-pr-comments description: Systematically process GitHub pull request review feedback end-to-end: pick a target PR, identify unanswered or unresolved comments, handle each thread sequentially, implement required code updates, run repository verification checks, and post clear responses. Use when asked to review PR comments, resolve review threads, or address reviewer suggestions/questions. --- # Review PR Comments Process pull request feedback one thread at a time and finish wit
$ install --global
skillsauthnpx skillsauth add TheCardGoat/lorcana-engine .agents/skills/review-pr-commentsInstall 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: Apr 17, 2026, 2:10 AM5.6s1 file scanned
SKILL.md
- name:
- review-pr-comments
- description:
- Systematically process GitHub pull request review feedback end-to-end: pick a target PR, identify unanswered or unresolved comments, handle each thread sequentially, implement required code updates, run repository verification checks, and post clear responses. Use when asked to review PR comments, resolve review threads, or address reviewer suggestions/questions.
Review PR Comments
Process pull request feedback one thread at a time and finish with verified code plus a clear summary.
Operating Rules
- Process review comments sequentially, never in parallel.
- Read full file context before changing code.
- Ask the user before making product or architecture decisions.
- Do not commit automatically; ask the user after all work is complete.
- Follow repository standards from
AGENTS.mdandCLAUDE.md. - Use Bun-based validation commands from repo root.
Workflow
1. Select a PR
- List open PRs.
- If multiple PRs are open and no PR number is specified, ask the user which PR to process.
- Confirm the selected PR number, title, and author before continuing.
2. Gather Full Review Context
Collect:
- PR metadata (title, description, author, changed files)
- Review state (approvals, change requests, unresolved threads)
- All review comments and existing thread replies
Use GitHub MCP tools when available. If unavailable, use gh equivalents.
3. Build the Unanswered Queue
Create a numbered list of comments that still need action:
- No author reply yet
- Thread unresolved
- Pending change request
- Contains a concrete code suggestion
Exclude already handled threads.
4. Process Each Comment (Strictly One by One)
For each queued comment:
- Present context:
- Reviewer, file path, line number, thread text, and relevant code snippet
- Classify the comment:
- question, bug, improvement suggestion, style concern, or discussion
- Decide and execute:
- question: draft and post clear answer
- valid code suggestion: implement minimal fix, run targeted checks, post confirmation
- discussion: explain trade-offs, ask user when judgment is needed, then reply
- no code change needed: post respectful technical rationale
- Mark thread/comment as processed in your working checklist.
Use this confirmation style after implemented changes:
Implemented. <brief description of what changed>
5. Verify After Processing
Run repository checks in this order:
bun test
bun run check-types
bun run lint
Fix any introduced issues before final reporting.
6. Deliver Final Summary
Report:
- PR number and title
- Total comments processed
- Counts by type (questions answered, code changes made, discussions resolved)
- Files changed with one-line rationale per file
- Validation results for tests, type-check, and lint
- Remaining follow-ups, if any
Use this template:
PR Review Comments Summary
==========================
PR: #<number> - <title>
Comments Processed: <count>
- Questions answered: <count>
- Code changes implemented: <count>
- Discussions responded to: <count>
Changes Made:
- <file>: <description>
All Tests: <PASSED|FAILED>
Type Check: <PASSED|FAILED>
Lint: <PASSED|FAILED>
Next Steps:
- <remaining action or "None">
Related Skills
TheCardGoat/teach-impeccable
documentation
VerifiedTrustedCommunity
One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
12SKILL.mdUpdated Apr 17, 2026
TheCardGoat/skill-creator
tools
VerifiedTrustedCommunity
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
12SKILL.mdUpdated Apr 17, 2026
TheCardGoat/quieter
testing
VerifiedTrustedCommunity
Tone down overly bold or visually aggressive designs. Reduces intensity while maintaining design quality and impact.
12SKILL.mdUpdated Apr 17, 2026
TheCardGoat/polish
development
VerifiedTrustedCommunity
Final quality pass before shipping. Fixes alignment, spacing, consistency, and detail issues that separate good from great.
12SKILL.mdUpdated Apr 17, 2026