ds-jury — Claude Code skill: review changes and install
The ds-jury Claude Code skill gathers independent reviews of a code change from several models. The agent works through accepted findings and runs another review round until the reviewers agree.
MIT 539 installs ★ 320 updated 2026-10-28
npx skills add aicodeking/deepseek-stack --skill ds-jury -a claude-codeWhat ds-jury does
ds-jury asks two or three independent reviewers to assess the same change. Before the review, the agent handles open PR comments, fixes known issues, and runs relevant checks. Reviewers share one brief and cannot edit the code.
The agent checks each finding against the code, applies accepted fixes, and reruns the checks. A new round uses the updated diff and the same brief. Review ends when every reviewer approves with no open serious findings, when three rounds are complete, or when only minor findings remain. Disagreements after three rounds go to the user.
What it helps with
- collect independent model reviews of a diff
- catch code issues before merging a change
- check whether reviewers accept the fixes
- separate verified findings from rejected ones
Example prompts for the agent
- Ask several models to review this change independently and work through their findings.
- Run
/ds-juryon the current diff. - Get other models to review this PR, then repeat the fixes until they agree.
How to install ds-jury
1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-jury -a claude-code2Manually: put the files in place
~/.claude/skills/ds-jury/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ds-jury/
1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-jury -a codex2Manually: put the files in place
.agents/skills/ds-jury/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-jury -a cursor2Manually: put the files in place
.cursor/skills/ds-jury/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install aicodeking/deepseek-stack skills/ds-jury2Manually: put the files in place
.github/skills/ds-jury/SKILL.md1Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-jury -a gemini-cli2Platform CLI
gemini skills install https://github.com/aicodeking/deepseek-stack --path skills/ds-juryManually: put the files in place
.devin/skills/ds-jury/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add aicodeking/deepseek-stack --skill ds-jury -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-jury
How do I install ds-jury in Claude Code?
Run npx skills add aicodeking/deepseek-stack --skill ds-jury -a claude-code. The skill is available at ~/.claude/skills/ds-jury/SKILL.md.
What does ds-jury do?
It coordinates independent reviews of a change by two or three reviewers, helps assess their findings, and starts another round after fixes.
When does ds-jury stop reviewing?
It stops when all reviewers approve with no open serious findings, after three rounds, or when only minor findings remain. Disagreements after three rounds are passed to the user.
Source text
SKILL.md · MIT
--- name: ds-jury description: "Gets independent reviews of a change from two or three different models or providers and loops on fixes until they agree. Use when the user says jury, panel review, second opinions, ask other models, or /ds-jury." --- Get two or three independent reviewers to judge the same change, then fix until they agree. ## Steps 1. Get the work ready first. Answer open PR comments, fix known issues and run the relevant checks. Skip this only if the user wants to throw the code away. 2. Pick the jurors. Use models the user named. Otherwise pick the strongest available model from two or three different providers, at high reasoning effort. 3. Find a way to reach them in this harness: team workers or subagents with a model setting, a second agent CLI in the terminal (for example a Codex or Claude CLI), or an API call. If only one model is available, start two or three fresh-context subagents of that model, each with a different persona: correctness, security and edge cases, simplicity and scope. 4. Write one brief for all jurors: repo path, base SHA, diff command, goal in one sentence, out-of-scope items and check results. Tell them to review only and change nothing. 5. Ask each juror for: a verdict (APPROVE or CHANGES), a score out of 10 and findings as `id severity file:line claim fix`. Severity is blocker, should or nit. 6. Run the jurors in parallel. Wait for all of them. A timeout or error is not approval. 7. Check each finding against the code yourself. Fix the ones you agree with, with the smallest change. Write a one-line reason for each one you reject. 8. Re-run checks. Start a new round with the same brief, your answers and the new diff. 9. Report the result. If there is a PR, edit its description and add a table: juror, model, score per round. Write `no score` when a juror gave none. If there is no PR, put the table in your final reply. ## Stop when - Every juror returns APPROVE with no open blocker or should finding. - Three rounds are done. Report the open disagreements, with both sides in two lines each. The user decides. - A round returns only nits. Stop without another round. ## Rules - Jurors are read-only. They do not edit, push, comment or start their own subagents. - Say which jurors are the same model as each other. Do not claim a provider you did not reach. - Never invent a score or verdict. - Guard the scope. Decline new features and list them as follow-ups.
© aicodeking · MIT · aicodeking/deepseek-stack