agentleFS
egoxx1egoxx1/unified-master-harness/.agents/skills/dev-plan/SKILL.md

dev-plan

Skill1 starsChanged 16 days agoMITView on GitHub

Create a compact product/implementation spec for large, cross-subsystem, migration, architecture, public-contract, significant UX, or materially ambiguous changes before coding. Do not use for small or ordinary localized work.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use dev-brainstorm.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • phdengSkill

    dev-brainstorm

    结构化开发头脑风暴助手。用于:(1) 新项目/功能的需求分析与方案设计,(2) 技术选型讨论与权衡分析,(3) 架构设计与系统拆解,(4) 问题解决与调试思路梳理,(5) 代码重构与优化方向探索。当用户说"帮我想想"、"头脑风暴"、"怎么设计"、"技术方案"、"架构讨论"时触发。

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when a wrong interpretation would be expensive or hard to unwind.

    line 8
  2. Distinctive:

    Do not turn the plan into a transcript of obvious coding steps.

    line 13
  3. Very specific:

    If PROJECT.md applies, align with it explicitly.

    line 36
  4. Distinctive:

    If open product decisions materially change the result, get human confirmation before implementation.

    line 37
  5. Distinctive:

    No speculative extension points.

    line 57
  6. Distinctive:

    Prefer vertical, independently verifiable slices.

    line 58
  7. Very specific:

    Do not force TDD for copy/styling/static configuration.

    line 59

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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

Development Spec and Plan

Use this skill when a wrong interpretation would be expensive or hard to unwind.

Goal

Give the human a short document they can review without needing to read code, then give the implementing agent the decisions it cannot safely infer. Do not turn the plan into a transcript of obvious coding steps.

1. Product contract

Capture:

## Goal
What changes for the user/system and why.

## Acceptance criteria
Concrete observable outcomes.

## Must preserve
Existing behavior/contracts that cannot regress.

## Out of scope
Tempting adjacent work intentionally excluded.

## Open product decisions
Only choices that would lead to materially different outcomes.

If PROJECT.md applies, align with it explicitly. If open product decisions materially change the result, get human confirmation before implementation. Otherwise proceed.

2. Technical plan

Inspect affected architecture and record only decisions that matter:

## Existing contracts / constraints
## Files and interfaces affected
## Decisions and rationale
## Implementation order
## Verification plan
## Risks / rollback (only when relevant)

For long or multi-session work, save to docs/agent/plans/ or the repository's existing spec system. For work that will finish in the current session, a compact task artifact under .agent-state/<task>/ is sufficient.

Rules

  • No speculative extension points.
  • Prefer vertical, independently verifiable slices.
  • Do not force TDD for copy/styling/static configuration.
  • A plan longer than the decisions it captures is too detailed.
  • A vague line such as "handle edge cases" is not a decision; name the actual behavior or omit it.
  • Planning does not authorize push, merge, deploy, publish, or destructive operations.

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.