Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Converts an approved design into a structured implementation plan with discrete 2-5 minute tasks. Each task specifies exact file paths, a code snippet, and a verification command. Plans are saved as markdown files under docs/plans/.
Forcing a verification command per task catches gaps in thinking before code is written, unlike freeform task lists.
When to use it
- Breaking a new feature into reviewable sub-tasks before coding
- Handing off an implementation plan to another developer
- Estimating work by counting discrete tasks
- Catching vague or untestable tasks before writing any code
- Creating a checklist to track progress during a coding session
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: create an implementation plan for adding in-memory API response caching
- 1Identifies discrete goals from the design: create cache module, integrate into API layer
- 2Writes Task 1 with file path src/cache.js, a Map-based implementation snippet, and a node -e verification command
- 3Writes Task 2 with file path src/api.js, showing where to insert cache.get/set calls, and an npm test verification command
- 4Checks each task against the quality checklist: exact paths, verification steps, under 5 minutes, ordered by dependency
- 5Saves the plan to docs/plans/2026-03-16-api-caching.md
A markdown plan file with two concrete tasks, each containing goal, files, code snippet, verification command, and time estimate