From add
Creates detailed feature specifications through a structured interview, including user stories, acceptance criteria, test cases, data models, APIs, UI states, and dependencies for TDD planning.
How this skill is triggered — by the user, by Claude, or both
Slash command
/add:specThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Create a feature specification through a structured interview. The spec becomes the source of truth for implementation.
Create a feature specification through a structured interview. The spec becomes the source of truth for implementation.
docs/prd.md exists. If not, tell the user to run /add:init first.docs/prd.md to understand the project context.add/config.json to understand environment and quality settings--from-prd-section is provided, pre-populate answers from that PRD sectionfeature-name argument is provided, use it. Otherwise, ask.Estimate questions upfront. Typical spec interview is 6-10 questions, ~5 minutes.
Let's define a specification for this feature.
This will take approximately {N} questions (~5 minutes).
The spec will include acceptance criteria, user test cases,
data models, and everything needed to start TDD.
Q1: "Describe the feature in one or two sentences. What should it do?" → Captures: feature description, feature name/slug
Q2: "Who uses this feature, and what's their goal?" → Captures: user story (As a {role}, I want {what}, so that {why})
Q3: "What are the must-have behaviors? List the things that MUST work for this feature to be complete." → Captures: acceptance criteria (AC-001, AC-002, etc.)
Q4: "Walk me through the happy path — step by step, what does the user do and see?" → Captures: primary user test case (TC-001)
Q5: "What should happen when things go wrong? Think about invalid input, network errors, missing data." → Captures: error handling, edge cases, additional test cases
Q6: "What data does this feature need? Think entities, fields, relationships." (Default: "I'll infer from the acceptance criteria") → Captures: data model
Q7 (if applicable): "Does this feature need API endpoints? If so, what operations?" → Captures: API contract
Q8 (if UI): "Describe the key UI states — loading, empty, error, success." → Captures: UI behavior, screenshot checkpoints
Q9: "Anything else I should know? Dependencies on other features, third-party services, specific libraries?" (Default: "Nothing additional") → Captures: dependencies, notes
${CLAUDE_PLUGIN_ROOT}/templates/spec.md.templatespecs/{feature-slug}.mdDisplay the spec summary:
Spec created: specs/{feature-slug}.md
Acceptance Criteria: {N} ({must} must, {should} should, {nice} nice-to-have)
User Test Cases: {N}
Data Entities: {N}
API Endpoints: {N}
Next steps:
1. Review the spec and refine if needed
2. Run /add:plan specs/{feature-slug}.md to create an implementation plan
3. Or jump straight into /add:tdd-cycle specs/{feature-slug}.md
npx claudepluginhub mountainunicorn/add --plugin addConverts vague feature ideas into written, agreed specifications through structured questioning across nine dimensions. Produces docs/specs/*.md with acceptance criteria for planning, scaffolding, and TDD tools.
Conducts focused interview to draft spec.md for upcoming tasks in SDD workflow. Covers goal, behaviors, acceptance criteria, edge cases, out-of-scope one branch at a time; writes to disk. Pauses to split multi-features.
Writes a detailed specification for a single feature including user flows, edge cases, API definitions, and acceptance criteria. Useful when asked for a feature spec or functional requirements.