speckit-specify

Generate a validated feature specification from a natural language feature description.

Updated Aug 24, 2026
One-click install
npx skills add https://github.com/Fras0/clinics-api --skill speckit-specify-fras0
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speckit-specify
Source: https://github.com/Fras0/clinics-api/tree/main/.cursor/skills/speckit-specify
Command: npx skills add https://github.com/Fras0/clinics-api --skill speckit-specify-fras0

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a rough feature idea into a complete, testable specification is slow and error-prone. This Skill converts a plain-language feature description into a structured spec.md file with user scenarios, functional requirements, success criteria, and a quality checklist, ready for planning. ## Core Features & Use Cases - Spec Generation: Parses a feature description, extracts actors, actions, data, and constraints, and writes a structured specification using the project's spec-template. - Quality Validation: Creates a requirements checklist and iteratively validates the spec against completeness, testability, and technology-agnostic criteria, with up to 3 clarification questions for ambiguous points. - Extension Hooks: Supports before_specify and after_specify hooks (e.g., automatic git branch creation) configured via .specify/extensions.yml. - Use Case: A product engineer types a feature idea like "add OAuth2 login" and receives a numbered feature directory under specs/ containing a validated spec.md and checklist, ready for /speckit-plan. ## Quick Start Ask the agent to create a feature specification for your idea, for example: run speckit-specify with the description "add user authentication with OAuth2".

Frequently Asked Questions about speckit-specify

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a feature specification from a text description?▼

Invoke the specify command with your feature description as the argument. The Skill generates a short name, creates a numbered directory under specs/, writes spec.md from the project template, and validates it against a quality checklist.

How does spec-kit handle unclear requirements in a specification?▼

The Skill marks genuinely ambiguous points with [NEEDS CLARIFICATION] markers, limited to a maximum of three. It presents each as a multiple-choice question with suggested answers, then updates the spec with your selections and re-validates.

Does speckit-specify require a specific project structure?▼

Yes, it requires a spec-kit project structure with a .specify/ directory containing templates and optionally init-options.json, memory/constitution.md, and extensions.yml. Feature directories are created under specs/ by default.

Can I customize the feature directory naming in spec-kit?▼

Yes, set SPECIFY_FEATURE_DIRECTORY explicitly to override the default. Otherwise the name is auto-generated with a sequential NNN prefix or a timestamp prefix, depending on the feature_numbering setting in .specify/init-options.json.

What happens after the specification is written?▼

The Skill runs a validation checklist, executes any after_specify hooks from extensions.yml, and reports the feature directory, spec file path, and checklist results. The spec is then ready for /speckit-clarify or /speckit-plan.