Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: ahgraber-skills-spec-kit-specify3description: Spec Kit Specify4---56# Spec Kit Specify78Create or refresh the feature specification for the active Spec Kit feature.910## Invocation Notice1112- Inform the user when this skill is being invoked by name: `spec-kit-specify`.1314## When to Use1516- Start a new feature and create the first `spec.md`.17- Convert free-form requirements into a structured, testable, implementation-agnostic specification.18- Rework an existing spec draft so it is ready for `spec-kit-clarify` or `spec-kit-plan`.1920## When Not to Use2122- Clarify ambiguity in an already-written spec without redrafting it (`spec-kit-clarify`).23- Generate design artifacts or tasks from an approved spec (`spec-kit-plan`, `spec-kit-tasks`).24- Reconcile cross-artifact drift in an existing feature (`spec-kit-reconcile`).2526## Router Fit2728- Primary route from `spec-kit` when `spec.md` does not exist yet.29- Downstream: hand off to `spec-kit-clarify` (if high-impact ambiguity remains) or `spec-kit-plan` (if spec is ready).3031## Preconditions3233- User provided a non-empty feature description.34- Run from repository root (or a subdirectory inside the repository).3536## Workflow373801. Normalize input:3940 - Treat the full user request as the feature description.41 - If empty, stop: `ERROR: No feature description provided`.424302. Generate a short branch suffix (2-4 words, kebab-case):4445 - Preserve meaningful technical terms/acronyms.46 - Prefer action-noun phrasing (for example `user-auth`, `bulk-export-audit-log`).474803. Bootstrap feature branch and spec exactly once:4950 - Run `scripts/create-new-feature.sh --json --short-name "<short-name>" "<feature description>"`.51 - Do not manually pre-compute branch numbers; let the script assign the next number.52 - Parse JSON output and capture:53 - `BRANCH_NAME`54 - `SPEC_FILE`55 - `FEATURE_NUM`56 - Derive `FEATURE_DIR` as `dirname(SPEC_FILE)`.575804. Load template context:5960 - Preferred template: `{REPO_ROOT}/templates/spec-template.md`.61 - Fallback template: `assets/spec-template.md`.62 - Preserve heading order from the selected template.636405. Draft `spec.md` content (focus on WHAT/WHY, not HOW):6566 - Fill prioritized user stories with independent tests and acceptance scenarios.67 - Write testable functional requirements.68 - Add edge cases and scope boundaries.69 - Add measurable, technology-agnostic success criteria.70 - Include key entities when data is central.71 - Use reasonable defaults and document assumptions when needed.727306. Clarification policy while drafting:7475 - First, make informed defaults using domain norms.76 - Add `[NEEDS CLARIFICATION: ...]` only for high-impact uncertainty.77 - Hard limit: at most 3 clarification markers.78 - Prioritize by impact: scope > security/privacy > UX > technical detail.798007. Write the spec to `SPEC_FILE`.818208. Create and run requirements quality validation:8384 - Create `FEATURE_DIR/checklists/requirements.md`.85 - Validate spec against this checklist:86 - No implementation details (frameworks, languages, APIs, internal architecture).87 - Mandatory sections are complete.88 - Requirements are unambiguous and testable.89 - Success criteria are measurable and technology-agnostic.90 - User scenarios and edge cases are covered.91 - Scope boundaries, dependencies, and assumptions are explicit.92 - No unresolved `[NEEDS CLARIFICATION]` markers for plan-ready specs.93 - If non-clarification issues fail, revise spec and re-validate (max 3 passes).949509. If clarification markers remain after validation:9697 - Ask up to 3 numbered clarification questions total.98 - For each question, present 2-3 concrete options plus a short custom answer path.99 - Wait for user responses, update `spec.md`, then re-run validation.10010110. Report completion:102103- Branch name.104- `spec.md` path.105- `requirements.md` path and pass/fail summary.106- Recommended next step:107 - `spec-kit-clarify` if high-impact ambiguity remains.108 - `spec-kit-plan` if ready.109110## Output111112- Active feature branch from `scripts/create-new-feature.sh`113- `specs/<feature>/spec.md`114- `specs/<feature>/checklists/requirements.md`115- readiness handoff for `spec-kit-clarify` or `spec-kit-plan`116117## Common Mistakes118119- Writing implementation design into the spec instead of user-visible behavior and outcomes.120- Leaving vague requirements that cannot be acceptance-tested.121- Asking too many clarification questions instead of making reasonable defaults.122- Running feature bootstrap script multiple times for one request.123124## References125126- `references/spec-kit-workflow.dot`127- `scripts/create-new-feature.sh`128- `assets/spec-template.md`129- `https://github.com/github/spec-kit/blob/9111699cd27879e3e6301651a03e502ecb6dd65d/templates/commands/specify.md`130131---132> Converted and distributed by [TomeVault](https://tomevault.io/claim/ahgraber) — claim your Tome and manage your conversions.133<!-- tomevault:4.0:skill_md:2026-04-13 -->
Run npx skillmds@latest add tomevault-io/ahgraber-skills-spec-kit-specify in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Spec Kit Specify It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.