claude-orchestrator-server

General-purpose code review standard: test real logic, fail loud on configuration errors, no meaningless fallbacks, structural decomposition for testability. Use when reviewing any code change.

TDD: enforce RED-GREEN-REFACTOR, tests before code, traceable trust, and test-suite hygiene.

General-purpose code review standard: test real logic, fail loud on configuration errors, no meaningless fallbacks, structural decomposition for testability. Use when reviewing any code change.

Guided task execution for the Executor role. Use when the Executor claims a task from the orchestrator queue and needs to execute it — reading the blueprint, making code changes, running verification, and reporting results with full traceability from every code change back to the Plan. Triggers on keywords like "执行任务", "开始构建", "claim task", "execute", "implement", "开发", "写代码", or when an Executor has claimed a task and is ready to work. Complements task-traceability as the foundational traceability layer.

Magic-loop terminator. Use when a chain reaches the explore link (only present under `--magic`) and the Explorer must decide between `spawn_chain` (open a follow-up chain with a concrete `next_requirement`) and `close_chain` (terminate the autonomous loop). Triggers on keywords like "explore link", "spawn_chain", "magic loop", "next iteration", "autonomous follow-up". The skill enforces evidence-traced reasoning over speculation and respects the `--magic-max-chains` depth cap.

TDD: enforce RED-GREEN-REFACTOR, tests before code.

Multi-agent orchestration system reference for Workers. Covers the v0.4 unified run command, worktree isolation, directory memory (CLAUDE.md), responsibility chain (Plan→Build→Verify→Review→Accept), output standards, and common pitfalls. Use this skill whenever a Worker executes any link in the responsibility chain — read it at session start and whenever you are unsure about process, output paths, or role boundaries.

PM task-level acceptance verification with full traceability. Use when the PM needs to verify completed work from team members, run acceptance on daily work assignments, or confirm deliverables before signing off — every acceptance decision must be traceable to specific criteria and verified deliverables. Triggers on keywords like "确认并验收", "验收一下", "verify and accept", "检查完成情况", "task acceptance", "任务验收". Covers per-task-assignment verification workflow with cross-worktree git checks, commit signature validation, and report data cross-validation.

Requirement analysis and task breakdown for the Planner role. Use when the Planner needs to analyze requirements, define task blueprints, break down work into executable tasks with acceptance criteria, establish responsibility chain ordering, and push tasks to the orchestrator queue — all with full traceability from requirements to tasks. Triggers on keywords like "分析需求", "拆解任务", "制定计划", "task planning", "blueprint", "break down", "define tasks", "规划", or when starting a new work cycle that needs tasks created.

Quality review of the full Plan→Build→Verify chain for the Reviewer role. Use when the Reviewer needs to assess whether the implementation matches the Planner's design intent — checking code quality, architecture compliance, verification completeness, and producing a review report with a pass/revise decision, with full traceability from every judgment back through the chain. Triggers on keywords like "审查", "review", "code review", "检查代码", "审批", "复核", or when verification is complete and the task enters the Review stage of the responsibility chain.

Foundational traceability layer for the entire Plan→Build→Verify→Review→Accept responsibility chain. Every role must leave a traceable record: upstream requirements → execution → output mapping → evidence → persisted record. Without traceability at every link, the chain cannot be audited, handoffs break, and sign-off is unreliable. Use this skill whenever any team member executes work in any link of the responsibility chain — planning, building, verifying, reviewing, or accepting. Triggers on any task execution context: task assignment, work plans, code changes, verification, review, or acceptance.

Independent verification of Builder output for the Verifier role. Use when the Verifier needs to verify that a Builder's output matches the Planner's blueprint — running tests, checking deliverables, identifying deviations, and producing a verification report with full traceability from every finding back to acceptance criteria. Triggers on keywords like "验证任务", "verify", "check", "测试验证", "排查问题", "验证产出", or when a Builder reports completion and the task enters the Verify stage of the responsibility chain.

Reference for developing Claude Code extensions — hooks, settings, MCP, CLI, and skills. Use when building tools on Claude Code, configuring automation, debugging hooks, or understanding extension points.