MichaelVessia/gh-comment
modules/programs/agents/shared/skills/gh-comment/SKILL.md
Comment on a GitHub PR or issue on Michael's behalf, clearly attributed as AI-generated. Use when asked to leave a comment, reply, or respond on GitHub.
$ install --global
skillsauthnpx skillsauth add MichaelVessia/nixos-config gh-commentInstall 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 4, 2026, 6:55 AM249.3s1 file scanned
SKILL.md
- name:
- gh-comment
- description:
- Comment on a GitHub PR or issue on Michael's behalf, clearly attributed as AI-generated. Use when asked to leave a comment, reply, or respond on GitHub.
- allowed-tools:
- Bash(gh pr comment:*), Bash(gh issue comment:*), Bash(gh pr view:*), Bash(gh issue view:*), Bash(gh api:*)
Your task
Leave comments on a GitHub PR or issue on Michael's behalf. Every comment must be clearly attributed as AI-generated.
Arguments
The user will provide:
- A PR/issue number or URL
- What they want the comment(s) to say
AI disclaimer
Always start every comment with this line, no exceptions:
> This comment was left by Michael's AI agent on his behalf.
Inline comments preferred
When commenting on a PR, always prefer inline reply comments over a single top-level comment. If the user's feedback addresses multiple files, lines, or existing review threads, post a separate inline reply to each relevant thread or location instead of lumping everything into one big comment.
- To list existing review comments on a PR:
gh api repos/{owner}/{repo}/pulls/{number}/comments - To reply to an existing review thread (use the
in_reply_tofield with the top-level review comment ID of that thread):gh api repos/{owner}/{repo}/pulls/{number}/comments -f body="..." -F in_reply_to=<comment_id> - To list top-level issue-style comments:
gh api repos/{owner}/{repo}/issues/{number}/comments - To reply to a top-level comment thread:
gh api repos/{owner}/{repo}/issues/{number}/comments -f body="..."
Fall back to a single top-level comment (gh pr comment / gh issue comment)
only when:
- The target is an issue (not a PR).
- There are no existing review threads to reply to.
- The user's message is a single general remark not tied to specific code.
Steps
- Determine whether the target is a PR or issue. If a number is given without
context, check
gh pr viewfirst, fall back togh issue view. - For PRs, fetch existing review comments to find threads to reply to.
- Match the user's feedback to the appropriate threads or locations.
- Post inline replies (each prefixed with the AI disclaimer) for each piece of feedback. Use a top-level comment only as a last resort.
- Output the URL(s) of the posted comment(s) or confirm they were posted.
You MUST do this in a single message. Do not ask follow-up questions.
Related Skills
MichaelVessia/bro
development
VerifiedTrustedCommunity
Restate the last message in plain human language, with no jargon.
2SKILL.mdUpdated Jul 23, 2026
MichaelVessia/fanout-prs
testing
VerifiedTrustedCommunity
Fan out a batch of work items into one PR each via isolated worktree agents, review every PR before it opens, then babysit all PRs through green CI and review feedback. Use when the user wants to fan out PRs, dispatch parallel PR agents over a list of items, or run a batch of independent changes as separate PRs.
2SKILL.mdUpdated Jul 10, 2026
MichaelVessia/herdr-dispatch
development
VerifiedTrustedCommunity
Dispatch user-visible coding or research agents through Herdr with Codex-Desktop-like thread ergonomics. Use when the user asks to use Herdr to spawn, dispatch, fan out, inspect, follow up with, or monitor agent workspaces/threads.
2SKILL.mdUpdated Jun 30, 2026
MichaelVessia/plannotator-visual-explainer
development
VerifiedTrustedCommunity
Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Plans and PR explainers follow Plannotator's prescriptive approach; all other visual content delegates to nicobailon/visual-explainer.
2SKILL.mdUpdated Jun 12, 2026