跳到正文
cccskills
免费在 GitHub 公开

planning-patterns

Structured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md1.7 KB
  • README.md213 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

  • Search for existing solutions and patterns
  • Identify relevant libraries and tools
  • Find best practices in the domain
  • Check for known pitfalls

2. Brainstorming Phase

  • Generate at least 3 alternative approaches
  • Evaluate trade-offs: complexity, time, risk, scalability
  • Consider build-vs-buy decisions
  • Rank by feasibility and alignment

3. Plan Creation

  • Structure with phases, tasks, and milestones
  • Define acceptance criteria per phase
  • Map dependencies between tasks
  • Include risk assessment with mitigations
  • Define TDD strategy per coding phase
  • Estimate effort and timeline

4. Review Gate

  • Verify completeness against original request
  • Validate logical phase ordering
  • Check actionability of risk mitigations
  • Score plan completeness (>=80 to pass)

Plan-to-Build Continuity

  • Save plans to docs/plans/ directory
  • Reference plan file in session memory
  • BUILD workflow reads plan during requirements clarification
  • Component-builder follows documented phases

When to Use

  • PLAN workflow (primary)
  • Any task requiring strategic thinking before execution

Agents Used

  • planner (primary consumer)
  • github-researcher (research phase)

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Provide implementations of advanced data structures

中文简介正在准备中。当前显示原文说明。

a5c-ai/babysitter18602026年9月17日 更新

Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.

中文简介正在准备中。当前显示原文说明。

a5c-ai/babysitter18602026年9月17日 更新

WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.

中文简介正在准备中。当前显示原文说明。

a5c-ai/babysitter18602026年9月17日 更新

Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.

中文简介正在准备中。当前显示原文说明。

a5c-ai/babysitter18602026年9月17日 更新

Generate visual representations of algorithm execution

中文简介正在准备中。当前显示原文说明。

a5c-ai/babysitter18602026年9月17日 更新

Hierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.

中文简介正在准备中。当前显示原文说明。

a5c-ai/babysitter18602026年9月17日 更新

查看 a5c-ai 的全部技能

报告此技能的问题