agentleFS
Sign inStart free
tamesystemstamesystems/intent-engineering-skills/skills/specify/SKILL.md

specify

Skill0 starsChanged 39 days agoMITView on GitHub

Turn an intent, problem, or request into observable and falsifiable success conditions without prematurely choosing implementation. Use when desired outcomes, acceptance criteria, constraints, invariants, or the distinction between solution and objective are unclear.

29 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use discovery, discover and 8 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.
  • robzolkosSkill

    discovery

    Quick user-centric interview to capture requirements from a time-poor stakeholder.

    Also in 3 projects that use this

  • anombyte93Skill

    discover

    Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

    Also in 4 projects that use this

  • MicrosoftSkill

    spec-review

    Independent, multi-model review of a design or spec **before** any code is written, for the microsoft/winappcli repo. Activate when a contributor asks to "review this spec", "review my design", "review this design doc", "validate this approach", "should we build this", "spec review", "design review", or "feature review". Fans out parallel sub-agents — each doing its OWN research against the real codebase and ecosystem rather than trusting the spec — covering necessity & scope, approach & alternatives, feasibility vs reality, risks & unknowns, DX & user impact, and a different-model-family cross-check. Emits a decision-oriented recommendation (proceed / proceed-with-changes / reconsider) to stdout. This is the PRE-CODE companion to the pr-review skill (which reviews code already written); use spec-review at the design/spec stage, not on an implemented diff. Does NOT write code or edit the spec.

    Also in 3 projects that use this

  • MicrosoftSkill

    init

    Also in 5 projects that use this

  • MetaSkill

    roadmap

    Build, continue, inspect, or visualize a source-grounded mathematical roadmap and theorem DAG in an existing Autoform Markdown blueprint. Use for source research, repository-wide inventories of existing and planned mathematics, scope, coverage, milestones, and roadmap articles; do not create repository infrastructure or prove Lean declarations.

    Also in 3 projects that use this

  • sahinSkill

    execute

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Recover the governing intent: Ask what real-world outcome is desired.

    line 12
  2. Distinctive:

    Expose ambiguity: If an unanswered question materially changes the solution space, mark it for investigation or human clarification rather …

    line 18

“Common” is measured: kept by at least 6 in 10 of the 27 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

Specify

Define what must become true before deciding how to make it true.

Work

  1. Recover the governing intent. Ask what real-world outcome is desired. Preserve proposed solutions as context, but do not mistake them for the objective.
  2. Name affected actors and boundaries. Identify who experiences the outcome, what systems participate, and what existing behavior must remain true.
  3. Make success observable. Translate vague qualities into falsifiable conditions. Do not invent numerical targets without evidence.
  4. Separate constraints from preferences. Record compatibility, security, architecture, performance, operational, migration, cost, or policy constraints only when justified.
  5. State invariants and non-goals. Make preservation requirements and scope boundaries explicit.
  6. Define proof. Distinguish verification (conformance to specification) from validation (satisfaction of intent).
  7. Expose ambiguity. If an unanswered question materially changes the solution space, mark it for investigation or human clarification rather than fabricating precision.

Return

  • Intent
  • Desired outcomes
  • Acceptance criteria
  • Invariants
  • Constraints
  • Non-goals
  • Verification conditions
  • Validation conditions
  • Open questions

Failure signals

Watch for solution-shaped requirements, untestable adjectives, proxy metrics becoming the objective, arbitrary targets, and requirements with no traceable reason to exist.

Done when

A capable independent reviewer could determine whether a result satisfies the specification without asking what the author meant, and important criteria trace back to the governing intent or a real constraint.

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