agentleFS
PeanutGTPeanutGT/NutsSkills/skills/spec/SKILL.md

spec

Skill3 starsChanged 19 days agoApache-2.0View on GitHub

Use when requirements are agreed and need to become a written spec with testable acceptance criteria, before planning or implementing a feature.

168 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use backprop, ios-clean and 10 more.

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.
  • JuliusBrusseeSkill

    backprop

    Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

    Also in 4 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • Saqlain-811Skill

    ios-fix

    Autonomous iOS bug fixer. (gstack)

    Also in 5 projects that use this

  • bastosSkill

    ios-design-review

    Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".

    Also in 5 projects that use this

  • ShreyRaviSkill

    plan-tune

    Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.

    Also in 7 projects that use this

  • timurgaleevSkill

    document-generate

    Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.

    Also in 6 projects that use this

  • +2 more from Saqlain-811

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 145 edited versions we read keep these.

  • 1

    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. Very specific:

    Start from the decisions made in clarify.

    line 17
  2. Distinctive:

    Write the spec with the template below.

    line 18
  3. Very specific:

    Builder check: Before handing it over, read it as someone who has seen only this document (or give it to a fresh-context reviewer.

    line 21

“Common” is measured: kept by at least 6 in 10 of the 145 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

Write a spec

Core rule: A builder who was not in the conversation must be able to build from it, and every acceptance criterion must be checkable by a test or one observable action.

Process

  1. Start from the decisions made in clarify. If none exist and the request is non-trivial, run clarify first.
  2. Write the spec with the template below. Keep it short: one page for most features.
  3. Acceptance criteria as Given / When / Then, one behavior each.
  4. Mark anything unresolved as OPEN:. Mark choices you made yourself as Our call: so the user can check them.
  5. Builder check. Before handing it over, read it as someone who has seen only this document (or give it to a fresh-context reviewer; see fresh-eyes). Sort every question that comes up into three piles:
    • Already answered in the conversation or the code → write the answer into the spec.
    • Minor — a sensible builder could settle it without changing what gets built → decide, mark Our call:.
    • Theirs — only the user can answer, and the answer changes what gets built → ask them, most important first, in one message.
  6. Get approval. Save where the project keeps docs (default docs/specs/<feature>.md).

Template

# <Feature name>

## Goal
One or two sentences: the problem and who has it.

## Scope
- In: ...
- Out (non-goals): ...

## Approach
The option chosen and why; the alternatives considered in one line each.

## Acceptance criteria
- AC1: Given <state>, when <action>, then <observable result>.
- AC2: ...

## Edge cases and errors
- <input or condition> → <expected behavior>

## Constraints
Performance, security, compatibility, dependencies.

## Open questions and our calls
- OPEN: ...
- Our call: ... (because ...)

Good acceptance criteria

WeakStrong
"Search is fast""Given 10k records, search returns in < 200 ms (p95)"
"Handles bad input""Given an email without '@', submit shows 'Invalid email' and nothing is saved"
"Users can log in"Split: valid login, wrong password, locked account, expired session

Done when

  • Every AC is testable and covers one behavior
  • Scope and non-goals are explicit
  • Builder check done; no OPEN: items left, or the user accepted them
  • User approved the spec

Next: plan.

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.