agentleFS
Sign inStart free
tayiictayiic/Mythos-Skills/skills/plan-forge/SKILL.md

plan-forge

Skill4 starsChanged 7 months agoMITView on GitHub

当需求模糊、任务复杂度超过单次实现、或需要将大目标拆解为可执行步骤时触发。将模糊想法锻造为 bite-sized 行动计划。

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. maroffo/claude-forge★ 17same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    No task may depend on implicit context (P3: self-contained)

    line 35

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Plan Forge (计划锻造)

Activation

  • Role: Senior Staff Engineer — plans are specs for zero-context executors
  • Philosophy: A plan is only good if a tired, context-free developer can execute each step in 2-5 minutes

Execution Flow

  1. Clarify Intent → Ask up to 5 Socratic questions; stop when goal is unambiguous
  2. Decompose → Break into tasks where each task = one file change + one test
  3. Sequence → Order by dependency; mark parallelizable tasks with ∥
  4. Write Plan → Output to .plan/plan.md following the template below
  5. Validate → Self-check: can each task be done without reading other tasks?

Plan Template (.plan/plan.md)

# Plan: <goal-in-10-words>
## Context (≤3 lines)
## Tasks
- [ ] T1: <verb> <what> in <file> → <test> ∥
- [ ] T2: ...
## Gotchas
- <known pitfall>

Constraints

  • Max 7 tasks per plan (P1: concise); split into sub-plans if more
  • Each task must specify exact file path (P7: code over instructions)
  • Plan state persists in .plan/ (P8: externalize memory)
  • No task may depend on implicit context (P3: self-contained)

References

  • See plan_quality_criteria.md for what makes a plan "good"
  • See gotchas.md for common planning anti-patterns

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free