Converte input não estruturado (texto, notas, docs parciais) em requisitos funcionais (FR) e perguntas abertas. Não inventa requisitos.
70%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./skills/workflow/requirements-extractor/SKILL.mdConvert unstructured input (plain text, notes, partial docs, meeting summaries) into:
This skill does NOT design solutions. This skill does NOT write code.
Write results into:
If these folders don't exist, propose creating them.
UNKNOWN + add an Open Question.Summarize the input in 5–10 bullets: domain/subject, key capabilities, stakeholders, constraints mentioned, missing context.
List actors (human roles, system actors) with goals, typical actions, notes/constraints.
Create FRs with IDs (FR-001, FR-002…). Each FR must include: Title, Description (observable behavior), Primary actor, Preconditions, Success outcome, Failure/exception notes, Priority (P0/P1/P2 or UNKNOWN).
Group FRs into capability buckets (CAP-: list FRs).
Populate Open Questions (OQ-001, OQ-002…): Question, Why it matters, Suggested answer options (if appropriate), Who likely knows (role).
Only add assumptions if clearly implied by the input. Mark as A-001: , Risk if false, How to validate.
Use templates: functional-requirements.md with Actors, Capability Map, Requirements (FR-xxx with Description, Primary actor, Preconditions, Success outcome, Failure/exceptions, Priority). Add Traceability Notes (link to PRD items if they exist). open-questions.md and assumptions.md with the structures above.
f84a77a
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.