Skip to content

tibursocampos/agent-dev-toolkit / core/skills/sdd-spec

sdd-spec

Verified

Create a PRD for a new feature or change (agent PRD .md; language per LANGUAGE.md + preferences under features/). Feeds sdd-plan. Use when creating a spec or invoking /sdd-spec.

references/quality-checklist.md

View on GitHub
## Quality checklist (before handoff)

- [ ] User confirmed **sim** on canonical path (`PIPELINE.md` § Confirm before write)
- [ ] Path matches `features/**/PRD/NNN_*.md` or global `.../features/**/PRD/NNN_*.md` only
- [ ] Body follows `templates/sdd/PRD.md` (REQ-NNN ids, verifiable CA, OOS; EARS only if useful)
- [ ] `## Related` present; omit-if-absent; portable paths; PLAN cited when known (`STORAGE.md` § Navigation block / REQ-009)
- [ ] Vague AC/REQ challenged and rewritten
- [ ] Implementation DoR inputs are explicit: REQ→verifiable CA, scope/OOS, and relevant dependencies/decisions; `READY` is recorded only as clarification status and is not treated as implementation authorization (`templates/sdd/PRD.md` §2.1; `readiness-severity.md`)
- [ ] PRD DoD items describe implementation completion and evidence separately from specification readiness; do not mark implementation DoD complete during specification
- [ ] Product depth challenged: metrics (§1.3), MoSCoW (§4.3), Severity on open questions (§5.1); FEATURE/STORY sibling depth when present (`references/challenge-vagueness.md`)
- [ ] No implementation how/code in the PRD from depth challenges
- [ ] `validate-prd` exit 0 on the written path
- [ ] Brownfield: `CHANGE.md` present + `validate-change` exit 0; greenfield: no empty CHANGE forced
- [ ] No implementation code in the PRD; no production/test code edited in `spec` session
- [ ] No full memory-bank / PRD dump prescribed in this skill session
- [ ] Body follows the chat language (`LANGUAGE.md`); do not hard-code a locale
- [ ] On the story PRD: API, event, database, and domain are each present or marked not applicable in one sentence
- [ ] A sibling surface is included only when the text says why the others do not serve
- [ ] Type/method/API names in English where cited
- [ ] Status **Pronto para planejamento** (or **Ready for planning** if EN override)
- [ ] Persisted content-approval field records the explicit operator approval and date; it is not inferred from `write_confirmed`
- [ ] Handoff: `/sdd-plan - <portable-prd-path>`
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall