agentleFS
npownpow/claude-skills/spec/SKILL.md

spec

Skill4 starsChanged 6 months agoApache-2.0View on GitHub

DEPRECATED — use `deep-design --spec` instead. Turns a conversation, idea, or discussion into an SDD-compatible spec.md. Use when the user asks to write a spec, technical spec, design doc, RFC, API design, data model, spec this out, turn this into a spec, write up the design, document this, implementation spec, spec for this 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

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

  • 0

    Common

    Most of the 145 edited versions we read keep these.

  • 3

    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. Very specific:

    When invoked, this skill delegates to deep-design --spec:

    line 28
  2. Very specific:

    If deep-design is available: invoke it with --spec flag and pass through the argument.

    line 29
  3. Distinctive:

    If not available: fall back to the inline workflow below.

    line 30
  4. Distinctive:

    Every requirement must be testable.

    line 57
  5. Very specific:

    If deep-design is unavailable, use this inline workflow:

    line 61
  6. Distinctive:

    Problem before design: Always define what and why before how.

    line 75

“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

Spec

DEPRECATED: This skill is now a thin wrapper around deep-design --spec. The standalone spec skill is maintained for backwards compatibility but all new development happens in deep-design.

Routing

When invoked, this skill delegates to deep-design --spec:

  • If deep-design is available: invoke it with --spec flag and pass through the argument.
  • If not available: fall back to the inline workflow below.

SDD-Compatible Output

The spec is written as specs/{NNN-feature-name}/spec.md following the Spec-Driven Development format:

specs/{NNN-feature-name}/
├── spec.md              # Feature specification
└── checklists/
    └── requirements.md  # Spec quality validation

Required Sections

  • User Scenarios & Testing — prioritized user stories (P1, P2, P3) with Given/When/Then acceptance scenarios. Each story must be independently testable.
  • Functional Requirements — FR-001, FR-002, etc. Each testable and unambiguous.
  • Success Criteria — SC-001, SC-002, etc. Technology-agnostic, measurable outcomes.
  • Key Entities — if data is involved (entity, attributes, relationships).
  • Assumptions — reasonable defaults documented here.
  • Edge Cases — boundary conditions and error scenarios.

Spec Quality Rules

  • Focus on WHAT and WHY, never HOW. No implementation details (languages, frameworks, APIs).
  • Success criteria must be measurable and technology-agnostic.
  • Max 3 [NEEDS CLARIFICATION] markers (scope > security > UX priority).
  • Every requirement must be testable.

Fallback Workflow

If deep-design is unavailable, use this inline workflow:

Pace: Spec authoring is load-bearing design work — choices made here propagate to implementation. Think carefully and step-by-step.

  1. Extract the core idea — identify what system, feature, or API is being specified.
  2. Ask clarifying questions if needed (batched, max 3) — present ALL as a single numbered batch.
  3. Create SDD directory — scan specs/ for next sequential prefix, create specs/{NNN-name}/.
  4. Draft spec.md — write all required sections following the SDD format above.
  5. Generate checklists/requirements.md — validate spec quality (no implementation details, testable requirements, measurable criteria, max 3 clarification markers).
  6. Self-correct — if validation fails, fix and re-validate (max 3 iterations).
  7. Report — print SDD_DIR path, spec status, and suggested next step (deep-plan or deep-design --spec for clarification).

Golden Rules

  1. Problem before design. Always define what and why before how.
  2. Non-Goals are valuable. They define the boundary of the work.
  3. Success Criteria are mandatory. Without measurable criteria there is no definition of done.
  4. Ask at most 3 clarifying questions, batched in one message.
  5. Spec serves downstream tools. The spec.md must be consumable by deep-plan for plan generation and by autopilot for the full SDD workflow.

Follow-up Skills

Next StepSkillPurpose
Clarify ambiguitiesdeep-design --specAdversarial stress-testing of the spec
Plan implementationdeep-plan --spec specs/{NNN}/spec.mdProduce plan.md + tasks.md
Build everythingautopilotFull SDD workflow: specify → plan → tasks → implement

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.