Skip to content
Back to skills

Feat Feature

ASecurity

Use when the user wants a full feature action plan (backend + frontend + tests) with the PWDEVIA 7-question method before any code is written — 'planejar a feature X', 'criar plano de feature', 'plan the user CRUD'. Interviews the human (max 2 rounds) and writes .planning/feat/features/{slug}/plan.md. Do NOT use to write code (feat-exec), for small 1–3 file changes (feat-quick), backend-only or UI-only scope (feat-backend / feat-frontend), tests for existing code (feat-test) or code review (f...

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 28, 2026
testingtestingapifrontendbackenddocumentation

Works with

  • cli
  • api

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 28, 2026

npx -y skills add pwdev-solucoes/pwdev-claude-marketplace --skill feat-feature --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Feat Feature?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Feat Feature
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/pwdev-solucoes-feat-feature/badge)](https://www.skillsdirectory.com/skills/pwdev-solucoes-feat-feature)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: feat-feature
description: >
  Use when the user wants a full feature action plan (backend + frontend + tests) with the
  PWDEVIA 7-question method before any code is written — 'planejar a feature X', 'criar plano
  de feature', 'plan the user CRUD'. Interviews the human (max 2 rounds) and writes
  .planning/feat/features/{slug}/plan.md. Do NOT use to write code (feat-exec), for small
  1–3 file changes (feat-quick), backend-only or UI-only scope (feat-backend / feat-frontend),
  tests for existing code (feat-test) or code review (feat-review).
metadata:
  version: 3.2.1
---

# Feature plan

Plan type **feature** — full scope: backend, frontend, tests and documentation as applicable,
split into clearly ordered Execution Steps. You run in the MAIN session: you interview the
human, so never delegate this skill to a subagent.

## Procedure

1. **Language** — resolve `lang` (`references/language.md`).
2. **Method** — follow `references/pwdevia-method.md` end to end: read context (project
   instructions file, `.planning/feat/codebase.md`, all four `.planning/feat/context/*.md`,
   map staleness, memory), interview (max 2 rounds), answer the 7 questions, render
   `templates/plan.md` with `plan_type: feature`, lint it, present the summary.
3. **Focus for this type**
   - Persona: full-stack engineer on the project's real stack (from the context documents).
   - Order the steps: data/migrations → domain/services → API → UI → tests → docs.
   - Every business rule becomes at least one `AC-*`; every AC has a verification.
   - With UI (`**UI:** yes`): include the E2E scenario files
     (`<tests-dir>/e2e/scenarios/E2E-nnn-*.scenario.json`) and their exported specs
     (`<tests-dir>/e2e/generated/E2E-nnn-*.spec.ts`) in §4 and `playwright-cli` checks
     in §5 — `references/testing.md`.
   - Consider validation, error handling, authorization and migrations explicitly.

## Prohibitions

- Never write code — only the plan.
- Never skip any of the 7 questions or leave an AC without verification.
- Never create a plan with more than 10 steps — split into several plans.

Language: resolve `lang` per `references/language.md` before any human-facing output. Safety: never read or expose `.env*` (except `.env.example`/`.template`/`.sample`), keys, certificates or credentials — `references/safety.md`. Paths `references/`, `scripts/`, `templates/`, `schemas/` are relative to the plugin root (`references/runtime.md`).

Files in this skill

  • SKILL.md2.4 KB
  • agents/openai.yaml179 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…