Loading...
Loading...
Found 48 Skills
Execute and implement approved specification proposals in sequence using a test-and-validation-first approach. It is used for implementing changes, applying proposals, executing specification tasks, or building according to approved plans. Trigger words include "speckit-implement", "speckit-develop", "develop", "implement", "realize proposal", "apply change", "execute specification", "complete tasks in order", "build feature", "start implementation".
Documentation-driven project development workflow. Intelligently determines task types, executes existing plans or generates new plans using feature-dev. **Use Cases:** - Complete project documentation exists, need to execute development tasks - User specifies to execute a certain plan (e.g., "Execute plan 001") - User requests to develop new features (automatically uses feature-dev to generate plans) **Prerequisites:** - The project should already have a docs/ documentation structure (PRD, SAD, etc.) - For new projects, it is recommended to first use the project-docs-setup skill to create complete documentation - If plan formulation is needed, it is recommended to use the project-planning skill **Relationship with Other Skills:** - project-docs-setup: Creates project documentation structure - project-planning: Formulates development plans (requirement clarification + design discussion + plan writing) - project-workflow: Executes development plans + updates documentation - Recommended workflow: project-docs-setup → project-planning → project-workflow **Trigger Methods:** - "Execute plan 001" / "Continue 001-user-authentication" - "Start development" / "Execute plan" / "Continue last task"
Automate Postgrid Verify tasks via Rube MCP (Composio). Always search tools first for current schemas.
Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans in current session, when tasks need fresh subagent context to avoid pollution, when formal review cycles (spec compliance then code quality) are required between tasks, or when you need diff-based validation of each task before proceeding.
在當前會話中執行具有獨立任務的實施計劃時使用
Use at the start of any conversation - Determine how to find and use skills, requiring the skill tool to be invoked before any response (including clarification questions)
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.
Meta-skill enforcing skill discovery and invocation discipline through mandatory workflows. Use when starting any conversation to check for relevant skills before any response, ensuring skill-first workflow before proceeding.
PRD construction for work planning. Compulsory in PLAN phase. Builds .prd file as frozen dependency graph of every possible work item before execution begins. Triggers on any new task, multi-step work, or when gm enters PLAN state.
Decomposes a spec or architecture into buildable tasks with acceptance criteria, dependencies, and implementation order for AI agents or engineers. Produces `.agents/tasks.md`. Not for clarifying unclear requirements (use discover) or designing architecture (use system-architecture). For code quality checks after building, see review-chain. For packaging and PRs, see ship.
Used when executing implementation plans with independent tasks in the current session
Use this when you have a written implementation plan to execute in a separate session with review checkpoints.