Skip to content

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

sdd-plan

Verified

Create a baby-step PLAN from an existing PRD (agent PLAN .md; language per LANGUAGE.md + preferences). Feeds sdd-develop. Use when creating a plan or invoking /sdd-plan.

references/challenge-vagueness.md

View on GitHub
## Challenge vagueness (Aceite + step titles)

Before finalizing steps: rewrite Aceite lines that say "works", "ok", "as expected", "funciona", "como esperado". Prefer observable checks (tests named, script exit, checklist item).

### Non-vague Aceite (required)

Every step **Aceite** must:

1. Cite at least one **REQ-NNN** and/or **CA** from the PRD.
2. State a **verifiable** outcome (named test, script exit code, checklist item, or measurable behavior) — not "done", "ok", or "implementado".
3. Map to Prior context when present: **cite** portable paths to story `ARCH/` and/or `ANALYSIS/` (and SEC when relevant) instead of pasting bodies (`SELECTIVE-RETRIEVAL.md` / `SR-NO-FULL-DUMP`).

### Anti file-named steps

Step titles and Aceite must **not** be only a file, class, script, or path name.

| Forbidden (file-named / task-shaped) | Prefer (behavior / outcome) |
|--------------------------------------|-----------------------------|
| "`OrderValidator.cs`" | "Validate empty optional field on create-order command" |
| "Add `validate-foo.ps1`" | "Fail Assert when fixture FEATURE omits Goals" |
| "Update Application layer" | "Expose export-by-date API with authorization check" |

Lazy-load when sizing or rewriting titles: `story-sizing.md` (step title ≠ file/class only) and `anti-task-shatter.md` (verb+file/class/script stays a task under an outcome step — do not invent a US-shaped PLAN step per file). Checklist: `references/baby-step-sizing.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: 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