Spec for openclaw
Skill LeoYeAI/openclaw-coding-skills/skills/spec-for-openclaw
Production-grade coding workflow, execution scaffolding, and tuning skills for OpenClaw agents, part of the MyClaw.ai ecosystem.
npx -y skills add LeoYeAI/openclaw-coding-skills --skill spec-for-openclawAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Define implementation scope before coding inside an OpenClaw workspace. Use when the request sounds like "write a spec", "define this feature first", "clarify scope", "turn this idea into something buildable", or any task where outcome, constraints, interfaces, or acceptance criteria are still fuzzy.
SKILL.md
1.3 KB, as published. Nobody here has run it
Spec For OpenClaw
Write the implementation target down before code starts.
Process
- State the problem in concrete terms.
- Define the desired outcome from the user's perspective.
- List constraints from the workspace, runtime, tools, and deployment surface.
- Identify affected files, systems, and interfaces.
- Write acceptance criteria that can later be verified.
- Call out unknowns that must be resolved before broad implementation.
Output Standard
A useful spec is short, testable, and specific enough that planning becomes straightforward.
Include:
- objective
- scope
- non-goals
- affected surfaces
- acceptance criteria
- verification idea
Anti-Rationalization
| Rationalization | Response |
|---|---|
| "The task is obvious." | If it is obvious, it should be easy to state clearly. |
| "I can spec while coding." | That usually hides scope drift. Define the target first. |
| "This is just a bug fix." | Bugs still need expected behavior and proof. |