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.

reference.md

View on GitHub
# sdd-spec — reference index

Extended detail for `skills/sdd-spec/SKILL.md`. **Do not Read this file for procedural detail** when a section file exists — load `references/<section>.md` per Process step or Reference routing.

Contract: `SKILL-REFERENCE-RETRIEVAL.md`. Brownfield CHANGE gate: `CHANGE.md` / `CHANGE-CONTRACT.md` (`references/validate-change.md`). **Greenfield** must **not** force an empty CHANGE stub. Structural gate: REQ-NNN + `validate-prd` (`references/validate-prd.md`). Selective retrieval: `SELECTIVE-RETRIEVAL.md` / `SR-NO-FULL-DUMP`. Product depth challenge (metrics/MoSCoW/Severity; FEATURE/STORY siblings): `references/challenge-vagueness.md` + lazy `backlog-item-types/` (no preload).

| Section | Path |
|---------|------|
| Command playbook (step discovery) | `references/command.md` |
| Filename and numbering | `references/filename-numbering.md` |
| Storage and .gitignore | `references/storage-gitignore.md` |
| Product documentation language | `references/product-docs-language.md` |
| REQ-NNN tracking | `references/req-tracking.md` |
| Template usage | `references/template-usage.md` |
| Challenge vagueness | `references/challenge-vagueness.md` |
| Selective retrieval | `references/selective-retrieval.md` |
| English override | `references/english-override.md` |
| Structural validate (validate-prd) | `references/validate-prd.md` |
| Brownfield CHANGE (validate-change) | `references/validate-change.md` |
| Quality checklist | `references/quality-checklist.md` |
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: 468kUpdated 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: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated 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: 321kUpdated Claude CodeCodexVerifiedInstall