Interview the stakeholder. Ask ONE question at a time. Wait for the answer before asking the next question. Prioritize questions by impact — ask about scope and core behavior first, edge cases second.
Good questions are specific and bounded:
"Should the API return a 404 or an empty list when no results match?"
"Is this endpoint authenticated, and if so, which roles have access?"
Bad questions are open-ended or bundled:
"What should the API do?" (too vague)
"What about errors, pagination, auth, and rate limits?" (too many at once)
Summarize requirements. After all questions are answered, present a concise summary of the clarified requirements back to the stakeholder for confirmation.
Get explicit approval. Do not proceed until the stakeholder confirms the summary is accurate. If they correct anything, update the summary and re-confirm.
Output
A confirmed requirements summary ready to be turned into specs by spec-writer. The summary should include:
Scope: what's included and excluded
Core behavior: the happy path
Edge cases: boundary conditions and error handling
1---2name: tesslio-spec-driven-development-tile-spec-driven-development3description: Requirement Gathering4---56# Requirement Gathering78Structured interview process that turns vague requests into clear, actionable requirements.910## When to use1112- A new task arrives from a stakeholder (feature, bugfix, refactor)13- The request has ambiguous or missing acceptance criteria14- Existing specs don't cover the requested change15- Before running `spec-writer` to create or update specs1617## Rules1819- Ask ONE question at a time (see `one-question-at-a-time` rule)20- Never begin implementation until requirements are confirmed21- Base questions on gaps found in existing specs, not assumptions2223## Inputs2425- The stakeholder's initial request26- Existing specs in the project's `specs/` folder (if any)2728## Steps29301. **Review existing specs.** Scan the `specs/` directory for any specs related to the request. Note what's already documented and what's missing.31322. **Identify gaps.** List the ambiguous or underspecified areas:33 - Unclear scope boundaries (what's in vs. out)34 - Missing edge cases or error handling expectations35 - Unspecified behavior for boundary conditions36 - Unclear integration points with existing functionality37 - Missing non-functional requirements (performance, security)38393. **Interview the stakeholder.** Ask ONE question at a time. Wait for the answer before asking the next question. Prioritize questions by impact — ask about scope and core behavior first, edge cases second.4041 Good questions are specific and bounded:42 - "Should the API return a 404 or an empty list when no results match?"43 - "Is this endpoint authenticated, and if so, which roles have access?"4445 Bad questions are open-ended or bundled:46 - "What should the API do?" (too vague)47 - "What about errors, pagination, auth, and rate limits?" (too many at once)48494. **Summarize requirements.** After all questions are answered, present a concise summary of the clarified requirements back to the stakeholder for confirmation.50515. **Get explicit approval.** Do not proceed until the stakeholder confirms the summary is accurate. If they correct anything, update the summary and re-confirm.5253## Output5455A confirmed requirements summary ready to be turned into specs by `spec-writer`. The summary should include:56- Scope: what's included and excluded57- Core behavior: the happy path58- Edge cases: boundary conditions and error handling59- Constraints: performance, security, compatibility requirements6061## Success criteria6263- Zero ambiguous requirements remain after the interview64- Stakeholder explicitly confirmed the summary65- No implementation work began before confirmation6667---68> Source: [tesslio/spec-driven-development-tile](https://github.com/tesslio/spec-driven-development-tile) — distributed by [TomeVault](https://tomevault.io).69<!-- tomevault:4.0:skill_md:2026-06-21 -->
Run npx skillmds@latest add tomevault-io/tesslio-spec-driven-development-tile-spec-driven-development 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.
Requirement Gathering It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. 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.