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.
npx skillsauth add MichaelVessia/nixos-config gh-commentInstall 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.
Leave comments on a GitHub PR or issue on Michael's behalf. Every comment must be clearly attributed as AI-generated.
The user will provide:
Always start every comment with this line, no exceptions:
> This comment was left by Michael's AI agent on his behalf.
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.
gh api repos/{owner}/{repo}/pulls/{number}/commentsin_reply_to field 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>gh api repos/{owner}/{repo}/issues/{number}/commentsgh 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:
gh pr view first, fall back to gh issue view.You MUST do this in a single message. Do not ask follow-up questions.
development
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.
development
Turn an idea or objective into a goal package for /goal. Interviews the user, builds a reviewed fact sheet via Plannotator, then explores the codebase to produce an execution plan.
development
Open Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on the feedback that comes back.
testing
Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.