메뉴
Orchestrator skill — sequence atomic review-* skills (scope → language → framework → library → cognitive) and aggregate findings into a unified report.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Store, look up, or delete a personal credential (server SSH password, database password, website login, API key/token, certificate passphrase) in the macOS Keychain using a consistent <project>-<env>-<kind> naming scheme, and optionally record a pointer (never the secret itself) in the current project's Claude Code memory. Always use this skill whenever the user asks to save, store, remember, look up, rotate, or delete a password, API key, token, SSH credential, or database credential on this machine — even if they don't say "Keychain" or "security" explicitly, e.g. "save this database password so I don't lose it", "把这个数据库密码存一下", "记一条密钥", "这台服务器的密码帮我记下来", "what's the postgres password for staging again", "delete the old GitHub token from keychain". Do not use this for team-shared secret vaults, CI/CD secret injection, or anything that needs to sync across machines — those need a real secrets manager, not this skill.
Drain pending NATS messages from a producer contract via NATS MCP tools. Discovers the available NATS tool capabilities, selects exact-subject or wildcard mode from .cortex/nats.yaml, applies Tolerant Reader semantics, executes ack/nak/term decisions, and returns aggregated stats.
Audit and refactor existing SKILLs to meet spec compliance, repository asset boundaries, tool adaptation requirements, and LLM best practices.
From inside a linked worktree, deliver the current feature branch into main — merge with --no-ff, push, and optionally clean up the worktree, all without leaving CWD.
After code changes, auto-detect the project's build system and local deployment method for a given directory, then build the project and restart its locally-deployed environment (Docker Compose / systemd / process manager). Never assumes — asks only when detection is ambiguous. Caches detected commands per project in .cortex/redeploy-local.yaml; re-invocations on the same project skip re-scanning until signal files change, the cache expires (30 days), or the skill version bumps.
From the main repo on the main branch, scan all linked worktrees and local branches, let the user multi-select, then merge --no-ff + push them sequentially and clean up succeeded worktrees together.
| name | orchestrate-code-review |
| description | Orchestrator skill — sequence atomic review-* skills (scope → language → framework → library → cognitive) and aggregate findings into a unified report. |
| description_zh | 编排技能——按 scope → language → framework → library → cognitive 顺序串联原子 review-* 技能，聚合 findings 为统一报告。 |
| tags | ["code-review","orchestration"] |
| license | MIT |
| recommended_scope | project |
| metadata | {"author":"ai-cortex"} |
| triggers | ["review code","code review","pr review","orchestrate code review"] |
| input_schema | {"type":"code-scope","description":"Diff or codebase path(s) to review, plus optional language/framework hint","defaults":{"scope":"diff","untracked":"include"}} |
| output_schema | {"type":"findings-list","description":"Aggregated, deduplicated findings with risk signals from all executed atomic skills"} |
按固定顺序串联原子 review-* 技能并聚合 findings。本技能仅做编排，不执行代码分析。单维度审查请直接调用对应原子技能（如仅查 diff 用 review-diff、仅查安全用 review-security）。
按命名规范，编排技能只做 4 件事：
严禁：在本技能内执行代码分析、内嵌 lint 规则、为单一原子 skill 重复实现其逻辑。
| 步骤 | 类型 | 候选原子技能 | 选择规则 |
|---|---|---|---|
| 1 | scope | review-diff 或 review-codebase | 二选一，按用户意图（diff = 当前变更；codebase = 给定路径） |
| 2 | language | review-typescript / review-python / review-go / review-java / review-php / review-powershell / review-dotnet / review-sql | 0 或 1 个，按范围内主语言推断 |
| 3 | framework | review-react / review-vue | 0 或 1 个，按范围内框架推断 |
| 4 | library | review-orm-usage | 0 或 1 个，按范围内 ORM 使用情况推断 |
| 5 | cognitive | review-security → review-performance → review-architecture → review-testing | 全部按顺序执行 |
无匹配的步骤跳过；最终报告标注哪些步骤跳过及原因。
diff / codebase 间二选一按上表顺序依次调用原子技能，每步收集 findings（标准格式：location / category / severity / title / description / suggestion）。
任一原子技能失败 → 停止后续，输出已收集 findings + 失败说明。
location + title 跨步骤合并，保留最高 severity，在 description 标注其他命中步骤[]单一聚合报告：
risk_signals 列表（每条含 signal_name + 可选 confidence ∈ [0, 1]）orchestrate-repair-loop）编排技能内不做（应由原子子技能或下游技能承接）：
orchestrate-repair-loop 或开发流程review-diff → review-dotnet → review-security → review-performance → review-architecture → review-testingsrc/frontend，项目使用 Vue 3 + ORMreview-codebase → review-typescript → review-vue → review-orm-usage → review-security → review-performance → review-architecture → review-testingreview-codebase → 跳过 language / framework / library → cognitive 全部执行