AGENT SKILL

implement-plan

Implement an approved plan wave-by-wave with verification gates. Use when a plan path is given, when resuming after /clear, or when create-plan output is ready to build.

License 许可
Apache-2.0
最近更新
2026-11-14
Stars
★ 0
Forks
0

01 前言 Front Matter

name
implement-plan
description
Implement an approved plan wave-by-wave with verification gates. Use when a plan path is given, when resuming after /clear, or when create-plan output is ready to build.

02 资源文件 2

03 SKILL.md 正文

Implement Plan

Implement an approved technical plan. Plans live in thoughts/shared/plans/ (where create-plan writes) or v2/docs/plans/ (project-canonical for new plans). Each plan has waves with specific changes and success criteria.

Steps

  1. Get the plan path. If none was provided, ask for one.
  2. Read the plan completely. Note existing checkmarks (- [x]); the first unchecked wave is where you start.
  3. Read the context. The original ticket, every file the plan mentions, and any CONTEXT.md in directories you will modify.
  4. Pick the execution mode by plan size (see reference/execution-modes.md): 1 wave / ≤3 tasks → Mode 1; 2-3 waves → Mode 2; 4+ waves → Mode 3.
  5. Create a todo list to track progress.
  6. Execute the current wave following the protocol in reference/execution-modes.md (load context → run parallel tasks → adapt to reality → update checkmarks).
  7. Pass the verification gate before marking the wave complete — backend tests, Pyright, and frontend lint/typecheck (see reference/verification-gate.md).
  8. Transition. Commit if the wave is independently valuable (CP-06). If context > 70%, save the continuity ledger (continuity-ledger skill) and suggest /clear. Repeat from step 6 for the next unchecked wave.

Done when every wave is checked and the verification gate passes.

Reference

  • reference/execution-modes.md — the three modes, wave protocol, and Mode-3 transition script.
  • reference/verification-gate.md — the gate commands, AS-specific implementation rules, and error recovery.

04 同仓库更多 Skills

matheusnorjosa
matheusnorjosa/aprender_sistema

writing-standards

Apply AS v2 technical-writing standards (clarity, brevity, active voice, Python/Django conventions). Use when writing a README, a docstring (PEP 257), a commit message, a PR description, an error message, or any technical doc.

内容创作者写作与文案
★ 0
matheusnorjosa
matheusnorjosa/aprender_sistema

verification-gate

Verify before claiming success. Use when about to say something works/is done, after implementing a feature, after a bugfix, or before pushing — run the proof command and confirm output first.

★ 0
matheusnorjosa
matheusnorjosa/aprender_sistema

test-driven-development

Write the failing test before the implementation in AS v2 (pytest + Django/DRF). Use when implementing a feature or fixing a bug, before any production code is written.

测试与质量
★ 0
matheusnorjosa
matheusnorjosa/aprender_sistema

subagent-development

Orquestra subagents no AS v2 — decompõe a tarefa em domínios independentes, paraleliza e revisa em 2 estágios. Use ao delegar exploração, implementação ou validação cross-arquivo para acelerar o trabalho e poupar o contexto principal.

★ 0
matheusnorjosa
matheusnorjosa/aprender_sistema

security-scan

Automated security scanning for AS v2. Use before commits or when reviewing changes for vulnerabilities. Runs dependency audit (pip-audit, npm audit), secret detection (grep patterns), and code pattern scanning (SQL injection, XSS, eval, pickle, hardcoded secrets). Integrates with project hooks system.

★ 0
matheusnorjosa
matheusnorjosa/aprender_sistema

resume-handoff

Resume work from a saved handoff document, validating its state against the current codebase before continuing. Use when resuming work from a saved handoff after a context clear or in a new session (path, session name, or GitHub issue).

人力资源
★ 0