Writing plans
Skill kimtth/agent-skill-100-lines-or-less/skills/writing-plans
Use when: write a structured implementation plan before starting a complex or multi-step task.From its SKILL.md
npx -y skills add kimtth/agent-skill-100-lines-or-less --skill writing-plansAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 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.
SKILL.md
1.1 KB, 205 tokens by cl100k_base, as published. Nobody here has run it
Goal: produce a plan an agent can execute step by step with verification.
Use for:
- multi-file changes, migrations, or features with ordering risk
- work that will be handed to another session or subagent
- tasks where mistakes are expensive to unwind
Workflow:
- State the outcome and how success is verified.
- Map current state: files, interfaces, and constraints involved.
- Break work into ordered tasks with explicit dependencies.
- For each task define the change and its verification step.
- Mark checkpoints where progress is committed.
- List risks, blockers, and what to do when verification fails.
Plan shape:
- goal and acceptance criteria
- ordered tasks with per-task verification
- checkpoints and rollback points
- risks and open questions
Rules:
- every task must be independently verifiable
- prefer small reversible steps over large rewrites
- do not bury assumptions inside steps; list them up front
- keep the plan in the repo so execution can reference it
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.