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/req-tracking.md

View on GitHub
## REQ-NNN tracking (required / strongly recommended)

| Rule | Detail |
|------|--------|
| Format | Stable `REQ-NNN` (three digits, e.g. `REQ-001`) in §4 table and inline where cited |
| Coverage | Every functional behavior → ≥1 REQ → ≥1 verifiable CA |
| Decision projection | When a material decision feeds a REQ/CA, compare the actual normative wording with the current decision; an ID, link, or envelope alone does not prove semantic agreement. Apply `skills/_shared/sdd-artifacts/SEMANTIC-SUFFICIENCY.md` and retain the existing decision owner. |
| Supersession | Keep superseded decisions as history; do not carry their old behavior as an active REQ or CA. |
| Applicable gaps | Include material rules, failures, compatibility/preservation, OOS, and evidence limits only when relevant. A generic CA or missing material behavior/failure remains a question, not inferred `agreed` text. |
| External IDs | Issue/US/TS ids may appear in header **Rastreamento**; still assign REQ-NNN in §4 for PLAN handoff |
| PLAN/develop | REQ-NNN is the cross-artifact tracking key — do not rename after `/sdd-plan` |

`validate-prd` exit 0 requires at least one REQ-NNN plus required structural sections (Execution policy, acceptance, requirements, OOS).

- **SDDW-10 (criterion text change):** Changing the text of a CA, REQ, or CT requires one dated row in the PRD `## Histórico de alterações` (or `Change history`) that names the changed id and records the operator approval (`operador` or `operator`). Without that row the approved text stays as it is. Reconciliation: list each changed id against the history rows before reporting the PRD changed.
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