claude-workflow

Identifies independent tasks and spawns parallel agent workers. This skill should be used after cw-plan to execute multiple tasks concurrently.

Persistent agent team dispatcher with lead coordination. This skill should be used after cw-plan to execute tasks via a managed team (requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 and CLAUDE_CODE_TASK_LIST_ID).

Executes a single task from the task board using the 11-step implementation protocol. This skill should be used after cw-plan or cw-dispatch assigns a task, or when manually implementing a specific task by ID.

Transforms a specification into a task graph with dependencies. This skill should be used after cw-spec to break a spec into executable tasks with proper sequencing before dispatching with cw-dispatch.

Reviews implementation code for bugs, security issues, and quality problems. Creates FIX tasks for issues found. This skill should be used after cw-validate to catch issues before merge.

Team-based concern-partitioned code review. Each reviewer sees ALL files through a specialized lens (security, correctness, spec compliance). This skill should be used after cw-validate for thorough cross-file review (requires CLAUDE_CODE_TASK_LIST_ID).

E2E testing with auto-fix. Generates tests from specs, executes in isolated sub-agents, and auto-fixes application bugs. This skill should be used after implementation to verify end-to-end behavior.

Validates implementation against spec using 6 gates and generates a coverage matrix. This skill should be used after implementation is complete to verify coverage, proof artifacts, and credential safety before review.

Manages git worktrees for parallel feature development. This skill should be used when starting multiple features at once, or to list, switch between, and merge existing worktrees.

Generates a structured specification with demoable units, functional requirements, and proof artifact definitions. This skill should be used when starting a new feature to define what will be built before any code is written.

Internal subagent that generates Gherkin BDD scenarios from spec acceptance criteria. Produces one .feature file per demoable unit in the spec directory and optionally creates cw-testing task stubs on the task board. Called automatically by cw-spec.

Performs preliminary codebase fact-finding and produces a structured research report. This skill should be used before cw-spec to understand an unfamiliar or complex codebase and generate enriched context for specification writing.