Loading...
Loading...
Found 72 Skills
Explore-first wave pipeline. Decomposes requirement into exploration angles, runs wave exploration via spawn_agents_on_csv, synthesizes findings into execution tasks with cross-phase context linking (E*→T*), then wave-executes via spawn_agents_on_csv.
Requirement planning to wave-based CSV execution pipeline. Decomposes requirement into dependency-sorted CSV tasks, computes execution waves, runs wave-by-wave via spawn_agents_on_csv with cross-wave context propagation.
Orchestrate teams of parallel Claude Code sessions working on the same codebase. Handles task decomposition, agent coordination, context isolation, and merge strategies. Builds on worktree-manager for infrastructure.
Requirement-level progressive roadmap planning with issue creation. Decomposes requirements into convergent layers or task sequences, creates issues via ccw issue create, and generates roadmap.md for human review. Issues stored in .workflow/issues/issues.jsonl (single source of truth).
Use after exploring completes or whenever a feature already has locked requirements and now needs research, synthesis, phase definition, story mapping, and executable task beads. Use for prompts like "plan this", "break this into tasks", "decompose this work", "map the stories", "research and plan", or "turn this into beads" before implementation begins.
Spawn specialized sub-agents with context handoff for complex multi-phase tasks. Enables expertise delegation within a session with automatic context merging and depth limiting to prevent infinite loops.
Decompose requirements into structured task lists and build a task management system for long-running Agents (based on the Anthropic Effective harnesses methodology). Automatically trigger when users need to manage multi-session development tasks, track feature completion progress, or request "task decomposition", "task management", or "project planning".
Create implementation task plans in `_/local-plans/<plan-name>.md`. First investigate the codebase using the Explore Agent, then document it in verifiable granularity and parallel-executable units, following the standard format (Background & Purpose, Current Status, Design, File Structure Tree, Implementation Steps, Verification Methods) that can be validated by the plan-verifier Agent. Used for requests like "Make a plan", "Design", "Task decomposition", "Think about implementation approach". plan, planning, design, implementation plan, task decomposition, create-plan
Break down large, complex, or ambiguous tasks into independent subtasks with dependency maps, execution order, and success criteria. Plan first, then execute step by step. Triggers on "how should I do this", "where do I start", "plan the project", "break it down", "implement" or whenever a task involves multiple phases.
Create a safe implementation plan as both markdown and JSON DAG artifacts. Challenge scope with the user first, explore real code before decomposing, then emit atomic TASK-NNN entries with explicit dependencies, write scope, validation, and assigned agents. Use when the user asks to plan, decompose, or break work into execution-ready tasks.
Owner-scoped task decomposition with gates, rollback, verification commands, and smoke tests.
Plan large pieces of work that can't fit into a single agent session into a shared map of investigation issues on an issue tracker, and resolve one issue at a time until the path to the goal is clear.