ds-pr-comments — Claude Code skill for GitHub PR comments
The ds-pr-comments Claude Code skill formats and posts agent-written GitHub PR comments. It runs for PR comments, review replies, and dismissal reasons.
MIT 531 installs ★ 320 updated 2026-10-28
npx skills add aicodeking/deepseek-stack --skill ds-pr-comments -a claude-codeWhat ds-pr-comments does
The skill prepares a PR comment with clear agent attribution, checks it, then posts it to GitHub. It starts with the conclusion and cites supporting code, a check, a test, or a reproduction, while separating verified details from opinion.
Before posting, it scans the full comment for secrets, tokens, personal data, and private paths. It also previews the Markdown to ensure the attribution and reply render as separate blocks. After posting, it prints the GitHub URL and resolves a review thread only once the reply is live. If posting fails twice, it reports the error and leaves the thread unresolved.
What it helps with
- format an agent's reply to a PR comment
- attribute an agent-written GitHub comment
- remove secrets and personal data before posting
- check Markdown rendering before publishing
- resolve a review thread after its reply is posted
Example prompts for the agent
- Format and post a reply to this PR comment.
- Reply to the review feedback, then resolve the thread after posting.
- Use
/ds-pr-commentsto prepare a review dismissal reason.
How to install ds-pr-comments
1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-pr-comments -a claude-code2Manually: put the files in place
~/.claude/skills/ds-pr-comments/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ds-pr-comments/
1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-pr-comments -a codex2Manually: put the files in place
.agents/skills/ds-pr-comments/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-pr-comments -a cursor2Manually: put the files in place
.cursor/skills/ds-pr-comments/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install aicodeking/deepseek-stack skills/ds-pr-comments2Manually: put the files in place
.github/skills/ds-pr-comments/SKILL.md1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-pr-comments -a gemini-cli2Platform CLI
gemini skills install https://github.com/aicodeking/deepseek-stack --path skills/ds-pr-commentsManually: put the files in place
.devin/skills/ds-pr-comments/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-pr-comments -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about ds-pr-comments
How do I install ds-pr-comments in Claude Code?
Run npx skills add aicodeking/deepseek-stack --skill ds-pr-comments -a claude-code. The skill file is at ~/.claude/skills/ds-pr-comments/SKILL.md.
What does ds-pr-comments do?
It formats and posts PR comments, review replies, and dismissal reasons with agent attribution. Before sending, it scans the text for secrets and personal data.
What happens if GitHub rejects a comment?
After two failed posting attempts, the skill reports the error and does not resolve the review thread.
Source text
SKILL.md · MIT
--- name: ds-pr-comments description: "Formats and posts GitHub comments written by an agent on the user's behalf, with clear attribution and no leaked secrets. Use whenever you post a PR comment, review reply or dismissal reason, or on /ds-pr-comments." --- Make every agent-written comment easy to spot, short and safe to publish. ## Steps 1. Write the reply. Lead with the conclusion. Cite the code line, check, test or reproduction that supports it. Mark what you verified and what is your opinion. 2. Put this note at the top, with the reply below it: ```md > [!NOTE] > **<model> responding on behalf of <user>** Reply text starts here. ``` Use the model name the harness reports. If it reports none, use the harness name. Use the user's name or GitHub login. 3. Scan the full comment, including quotes and attachments, for secrets, tokens, private paths and personal data. Remove them. 4. Preview the final Markdown. Confirm the note and the reply render as two separate blocks. 5. Post the comment. 6. Confirm GitHub returned the comment or review URL. Print it. 7. Resolve a review thread only after its reply posted. ## Stop when - GitHub returned a URL for each comment you meant to post. - A post fails twice. Report the error and do not resolve the thread. ## Rules - Use the note on top-level comments, inline review comments, replies to bots and people, and dismissal reasons. - Do not use it in PR descriptions, commit messages or text the user asked to post word for word. - One attribution only. No signature, footer, heading or horizontal rule. - No thanks, filler or status updates such as "still working on it". - Never guess the model name.
© aicodeking · MIT · aicodeking/deepseek-stack