Resolve Pr CommentsSAFE
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
Overview
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
ae618ef5da66OBSERVED · 2026-10-12What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: resolve-pr-comments
description: This skill should be used when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR issues", "respond to PR review", or explicitly invokes "resolve-pr-comments".
---
# Resolve PR Comments
Analyze unresolved PR review comments, fix valid concerns, and draft responses for comments
that do not require code changes.
When explicitly invoked with extra text, treat that text as the PR number or URL. If no PR
reference is provided, infer it from the current branch.
## Process
1. **Preferred execution**
- If subagents are available, use `github-dev:pr-comment-resolver` and pass the PR reference.
- Otherwise follow the manual steps below.
2. **Fetch unresolved comments**
- If a PR number or URL is provided, use it directly.
- Otherwise auto-detect the PR from the current branch with `gh pr view --json number,headRefName`.
- Fetch inline comments with `gh api repos/{owner}/{repo}/pulls/{number}/comments`.
- Fetch review-level comments with `gh pr view <number> --json reviews,comments`.
- Filter to unresolved or pending threads.
3. **Resolve each comment**
- If the comment is valid, fix the code and search the codebase for the same problem in other locations.
- Fix all matching occurrences, not just the location mentioned in the comment.
- If the comment does not require a code change, draft a concise reply.
- If the comment is from a bot, reply with a direct factual sentence and no pleasantries.
4. **Reply style**
- Start in lowercase.
- Use simple language and short sentences.
- Avoid end punctuation when possible.
- Be concise and polite when replying to real people.
5. **Never auto-submit**
- Present all draft responses before posting them.
- Reply comments are posted directly with `gh api repos/{owner}/{repo}/pulls/{number}/comments/{comment_id}/replies -f body="..."` (the `{number}` PR number is required, the endpoint 404s without it).
- Add a random 3-5 second delay between posted replies with `sleep $((RANDOM % 3 + 3))`.Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
.claude/output-styles/adhd-explanatory.md
AGENTS.md
GEMINI.md
Gates applied: no_behavioural_pass.
ae618ef5da66full audit observations/trust-audit/skill/fcakyon__resolve-pr-comments.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | ae618ef5da66 | SAFE | B | 89 | first audit |
Questions
What does the Resolve Pr Comments skill do?
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
Is Resolve Pr Comments safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Resolve Pr Comments access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (ae618ef5da66), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.