菜单
Research a topic using multiple sources and conduct multi-agent voting. Use when making architectural decisions, choosing dependencies, or designing APIs. Triggers on "research", "decide", "vote on", "consensus".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Operating manual for documentation work in nexus-agents. Use when updating docs, adding new docs, changing doc pipeline, or troubleshooting doc issues. Triggers on "update docs", "add documentation", "doc pipeline".
Periodically exercise ALL nexus-agents feature families end-to-end against a real task — research → synthesize → vote → plan → dev-pipeline → graph workflow → memory → audit — capturing ACTUAL outputs to validate that fixes, docs, and claims hold in real usage (the things unit tests miss: live voter panels, adapter routing, pipeline stage wiring, audit chains). Use after a release, weekly, when several fixes have landed since the last run, or on demand. Triggers on "e2e validation", "end-to-end validation", "dogfood the loops", "validate end to end", "real usage test", "periodic validation run", "full-loop validation".
Run the CI gates locally before pushing, so failures surface in seconds instead of one CI cycle at a time. Enumerates the checks in .github/workflows/, runs the locally-runnable subset in CI's order, and pins the local-vs-CI delta as a memory the first time you work in a repo. Use before `git push` / opening a PR, or when CI just failed on something your local gate missed. Triggers on "pre-push", "before push", "ci parity", "will ci pass", "local gate", "prepush", "pre-push check".
Review code changes following project standards and security guidelines. Checks for lint compliance, type safety, test coverage, and security issues. Use when reviewing PRs, auditing code, checking implementation quality, or running a blind pre-merge review pass before merging your own change. Triggers on "review code", "code review", "check this", "audit", "PR review", "pre-merge review", "blind reviewer", "before merge".
Execute a release following project standards. Use when publishing a new version, creating release tags, or deploying. Triggers on "release", "publish", "version bump", "create release".
Improve an existing technical doc in-place via a phased Audit → Research → Rewrite → Validate workflow. Calls docs-review for audit and validate; never re-derives scoring. Applies answer-first H2s, citation capsules, and info-gain markers per .rules/docs-rubric.md. Use when the user says "rewrite docs", "improve this doc", "optimize doc", "docs rewrite".
| name | research-and-vote |
| description | Research a topic using multiple sources and conduct multi-agent voting. Use when making architectural decisions, choosing dependencies, or designing APIs. Triggers on "research", "decide", "vote on", "consensus". |
| allowed-tools | Read, Grep, Glob, WebSearch, WebFetch, Task |
| context | fork |
Full documentation:
grep -ri "keyword" docs/research/Create proposal with:
Voting Agents: Architect, Security, DevEx, AI/ML, PM
Thresholds:
| Decision Type | Threshold |
|---|---|
| Reversible changes | Majority |
| Architecture | Supermajority |
| Security-critical | Unanimous |
See CONSENSUS_PROTOCOLS.md for protocol selection matrix.
Record decision in GitHub issue with voting record.
# Decision Record: [Topic]
## Status: [Approved/Rejected]
## Voting Record
| Agent | Vote | Reasoning |
| ----- | ---- | --------- |
| Excuse | Counter |
|---|---|
| "I already know the answer" | Then write up the alternatives anyway. The vote isn't to discover the answer; it's to surface what you missed. |
| "Skip the research, just vote" | A vote without research surfaces opinion, not informed judgment. Cite primary sources. |
| "Simulated votes are fine for this" | Per CLAUDE.md and memory: simulated votes are random. Never use for real decisions. |
| "Unanimous would be too slow" | Unanimous applies to security-critical and breaking-API. Match the threshold to the reversibility. |
| "We can revisit if it's wrong" | Some decisions are expensive to reverse (data shape, public API, dep choice). Apply higher threshold accordingly. |
simulateVotes: true for anything other than unit testsconsensus_vote ran with real CLIs (simulateVotes: false)