agentleFS
Sign inStart free
Codagent-AICodagent-AI/agent-skills/skills/spec/SKILL.md

spec

Skill31 starsChanged 6 months agoMITView on GitHub

Drives interactive requirement discovery to produce spec files. Use when the user says "spec this", "write specs", "create specs", or "run the spec skill".

We split this skill into the rules it gives an agent

9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 133 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not write a capability's spec until you have presented its proposed requirements and scenarios and the user has approved them.

    line 13
  2. Distinctive:

    Read the proposal and related existing specifications.

    line 18
  3. Distinctive:

    After approval, write the spec file using the format below.

    line 33
  4. Very specific:

    If behavior depends on an unresolved architectural choice, specify as much as is currently knowable and add <!-- deferred-to-design: …

    line 36
  5. Very specific:

    Use one file per capability: specs/<capability>/spec.md.

    line 44
  6. Distinctive:

    Write normative requirements with SHALL or MUST.

    line 45
  7. Very specific:

    Use ### Requirement: <name> and at least one #### Scenario: <name> per requirement.

    line 46
  8. Distinctive:

    Avoid scenarios about file contents, configuration structure, or skill text unless those are the actual public contract.

    line 49
  9. Distinctive:

    Use delta sections as applicable:

    line 52

“Common” is measured: kept by at least 6 in 10 of the 133 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

Spec

Turn the proposal's capabilities into testable behavioral requirements through collaborative discovery. Specifications define observable behavior, not architecture or implementation.

Do not write a capability's spec until you have presented its proposed requirements and scenarios and the user has approved them.

Process

  1. Read the proposal and related existing specifications. Use the proposal's capability names to determine the new or modified spec files. For modified capabilities, locate the current requirement blocks before drafting the delta.
  2. Work through capabilities one at a time. Use codagent:ask-questions to resolve material behavior, boundaries, errors, and edge cases. Ask only questions that affect observable behavior or scope, recommend a default when useful, and do not use a generic approval question as discovery.
  3. Present the complete proposed requirements and scenarios for that capability, including consequential assumptions or defaults inferred from context. When asking for approval of the first capability, also offer a shorter version; make the offer only once.
    • The shorter version gives one plain-language line per requirement and no scenarios, followed by the defaults you inferred and any decision that needs the user's call.
    • Once the user asks for it, use it for the remaining capabilities unless they ask for full detail.
    • Approving a shorter version approves the requirements it summarizes. Derive the written scenarios only from those lines and the listed defaults, adding no new behavior. If the user later asks for the full version, show it and revise the spec file to match their feedback.
  4. After approval, write the spec file using the format below. Continue until each proposal capability has a corresponding spec.

If behavior depends on an unresolved architectural choice, specify as much as is currently knowable and add <!-- deferred-to-design: <reason> --> to the affected scenario. The design phase will complete or revise it. Do not ask architecture or implementation questions during specification.

Report the relative paths created. Do not invoke another lifecycle skill.

OpenSpec format

  • Use one file per capability: specs/<capability>/spec.md.
  • Write normative requirements with SHALL or MUST.
  • Use ### Requirement: <name> and at least one #### Scenario: <name> per requirement.
  • Scenarios describe observable WHEN/THEN behavior. Exactly four hashes on scenario headings are required by the parser.
  • Avoid scenarios about file contents, configuration structure, or skill text unless those are the actual public contract.

Use delta sections as applicable:

  • ## ADDED Requirements for new behavior.
  • ## MODIFIED Requirements for changed behavior. Copy the entire existing requirement block and all scenarios before editing it.
  • ## REMOVED Requirements with Reason and Migration.
  • ## RENAMED Requirements with FROM and TO.
## ADDED Requirements

### Requirement: <name>
<normative behavior>

#### Scenario: <name>
- **WHEN** <condition>
- **THEN** <observable result>

Download now (ZIP)

  • Other versions154 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 154

    1. garrytan/gstack★ 139ksame name
    2. getsentry/sentry-react-native★ 1.8ksame name
    3. JuliusBrussee/cavekit★ 1.1ksame name
    4. kdlbs/kandev★ 1ksame name
    5. getsentry/sentry-dart★ 877same name
    6. poshan0126/dotclaude★ 871same name
    7. SparkDevNetwork/Rock★ 696same name
    8. hyperlink-academy/leaflet★ 527same name
    9. strands-agents/box★ 490same name
    10. menkesu/awesome-pm-skills★ 441same name

    144 more not listed

    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.

  • Used alongsideProjects 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

      benchmark-models

      Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".

      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 6 projects that use this

    • +3 more from Saqlain-811
    • +3 more from ShreyRavi
  • In this repository30 other files it gives its agents.

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