boilerplan
Skill4 starsChanged 25 days agoMITView on GitHub
Prepare an implementation plan for a task the user describes, including docs and comment updates, clarifying questions as needed, a self-review of the plan, and a final step to commit the implemented changes. Use only when the user explicitly invokes boilerplan or asks to "boilerplan" a task.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Keep docs and code comments up to date: Treat the documentation and comment updates the change requires as explicit steps in the plan, not …
- Distinctive: line 22
Present the plan when ready: Do not start implementing until the user has seen and accepted it.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prepare an implementation plan for the task the user has described. The task may appear before or after this invocation in their message, so read the whole message to find it. If no task is discernible, ask what to plan before going further.
While preparing the plan:
- Keep docs and code comments up to date. Treat the documentation and comment updates the change requires as explicit steps in the plan, not an afterthought.
- Ask rather than guess. Whenever you are unsure about a decision or the user's intent and the answer would change the plan, ask.
- Make committing the implemented changes the final step of the proposed plan.
- Check the plan before presenting it. Review it skeptically for steps that are wrong, risky, or larger than the task needs, and revise it. Raise any concern you cannot resolve as a question. Review it yourself by default; for a large or risky plan, give the task and the plan to a fresh-context subagent when the harness provides one.
- Present the plan when ready. Do not start implementing until the user has seen and accepted it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.