agentleFS
agent-ixagent-ix/spec-skills/specify/SKILL.md

specify

Skill1 starsChanged 6 months agoMITView on GitHub

Initialize and manage requirements specifications with component-type instructions.

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 9 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

    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

  • Microsoft AzureSkill

    validate

    Run the full CI validation workflow locally before submitting a PR. Use this as a final check to ensure all Azure DevOps CI pipeline steps will pass.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create the spec.md and manage the requirements lifecycle.

    line 8
  2. Distinctive:

    Create typed FRs for entities, events, state machines, processes.

    line 22
  3. Distinctive:

    Create architecture FRs for API endpoints, queues, schemas, UI components.

    line 23
  4. Distinctive:

    Create operational FRs for configuration, migrations.

    line 24

“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

Create Requirements Specification

Create the spec.md and manage the requirements lifecycle.

Workflow

  1. Initialize: Create spec.md from assets/spec-template.md.
  2. Capture Requirements:
    • spec-write-str: Stakeholder needs.
    • spec-write-us: User stories.
  3. Specify Behavior:
    • spec-us-to-fr: Derive FRs from stories.
    • spec-write-fr: System behavior.
    • spec-write-nfr: Quality constraints.
  4. Define Domain Model:
    • Identify domain objects from master spec § 8-9.
    • Create typed FRs for entities, events, state machines, processes.
    • Create architecture FRs for API endpoints, queues, schemas, UI components.
    • Create operational FRs for configuration, migrations.
    • See spec-write-fr object-type-guide.md.
  5. Verify Coverage:
    • spec-matrix: Test matrix.
  6. Review (required):
    • spec-review: Validate quality.

Process

  1. Check prerequisites:
    • Single Repo: spec/
    • Multi-Repo: specs/<category>/<component>/spec/
  2. Copy template: assets/spec-template.md
  3. Set frontmatter:
    • artifact_type: Must be master-requirements.
    • name: Component name matching the repo.
    • org: Organization owning the component.
    • component_type: Authoritative type (e.g., fastapi-service, react-lib).
    • tags: Optional capabilities (e.g., [postgres, sqlmodel]).
    • relationships: Structured array of relationship objects (target, type, cardinality). Do NOT use depends_on. Specify exact semantic linkages such as calls, implements, publishes, consumes, reads, writes, triggers, or requires.

[!IMPORTANT] Individual artifacts (FR, NFR, StR, US, IT) also require YAML frontmatter with id, title, and type. See each writing skill's Frontmatter section.

  1. Customize: Processes, states, diagrams.
  2. Apply component instructions from golden-path/components/<component-type>/agent-instructions.md.

Repository Structure

spec/
├── spec.md                     # Master specification
├── stakeholder/                # StR-XXX
├── usecase/                    # US-XXX
├── functional/                 # FR-XXX (behavioral + domain-typed)
├── non-functional/             # NFR-XXX
├── tests.md                    # Test Matrix
└── assets/                     # Diagrams, POCs

ID Schema

  • Stakeholder: StR-XXX
  • User Story: US-XXX
  • Functional: FR-XXX
  • Non-Functional: NFR-XXX
  • Test Case: TC-XXX

Application-Type Specifications

[!IMPORTANT] When component_type: application, use assets/app-spec-template.md instead of assets/spec-template.md. The application spec standard is fundamentally different from a service or library spec.

What the Application Spec Owns

An application spec describes how multiple component repositories compose into a coherent system. It owns only cross-service concerns — things that cannot be expressed within any single component's spec.

SectionWhat to Write
Architecture Rationale (ADRs)Why this architecture? Why these trade-offs? One ADR entry per major decision that shaped the system shape.
Cross-service Sequence DiagramsEnd-to-end flows that span >1 service (Login, Checkout, Deploy). No single service can own these.
System-level NFRsSLA/uptime, scale limits, RTO/RPO — targets for the composed system, not individual services.
External Consumer ContractHow does an integrating engineer use this application as a whole? Aggregate "quickstart" across components.
Scope BoundariesWhat the system explicitly does NOT do. Deliberate exclusions, not future work.
Security ModelActor roles, trust hierarchy, capability matrix. Cross-cutting — not owned by any single service.
Deployment TopologyNamespace layout, ingress routes, service discovery, shared secrets/config.
Observability StrategyDashboard names, alert policies for the system. Per-service metrics stay in service specs.

What Stays at Service Level

  • Per-endpoint API contracts (routes, schemas)
  • Database schema and data models
  • Per-service latency/throughput NFRs
  • Events and signals (defined at service or domain level — never pulled to app level)
  • Per-service error codes and test matrix
  • Environment variables beyond shared/cross-service ones

Required Functional Requirements

For component_type: application, every spec MUST include:

FR Object TypePurposeExample
domainBounded context, ER diagram, subdomain mapFR-001 Auth Domain
processOne FR per major cross-service workflowFR-002 Login Process
configurationShared config across multiple servicesFR-006 Auth Configuration
integrationExternal consumer contract (how to integrate)FR-007 Consumer Integration Contract

Required Non-Functional Requirements

NFRPurpose
Security ConstraintsCryptography, transport, error handling standards
System ReliabilityUptime SLA, p99 latency, scale limits, RTO/RPO
Deployment TopologyNamespace, ingress, service discovery, secret mounts

Reference Implementation

Refer to a known well-formed application spec in your org as a model when authoring a new one.

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.