菜单
Use when you have a spec or requirements for a multi-step task, before touching code. Enforces bite-sized task granularity.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | writing-plans |
| description | Use when you have a spec or requirements for a multi-step task, before touching code. Enforces bite-sized task granularity. |
| type | skill |
| version | 1.0.0 |
| category | design |
| agents | ["system-architecture-specialist","python-ai-specialist","master-system-orchestrator"] |
Use this skill when you have a spec or requirements for a multi-step task, before touching code. It enforces bite-sized task granularity.
The process involves writing a comprehensive implementation plan that decomposes a design into 2-5 minute tasks.
Every task should be one small, verifiable bit of progress:
Follow these best practices to ensure high-quality, verifiable implementation plans.
# [Feature Name] Implementation Plan
**Goal**: [One sentence]
**Architecture**: [2-3 sentences]
---
### Task 1: [Component Name]
**Files**: `path/to/file.py`
**Steps**:
- [ ] Step 1: Write failing test
- [ ] Step 2: Run test (Verify FAILURE)
- [ ] Step 3: Write implementation
- [ ] Step 4: Run test (Verify PASS)
- [ ] Step 5: Commit
@Bug-Hunter or @Architect).Automated governance, hook installation, pre-commit validation, branch isolation, and safe commit operations.
Enforcement of safety guardrails, axiom verification, secret scanning, and mutability protections.
Building and managing premium statistical dashboards, RAG explorer UIs, warehouse log monitors, and real-time visualization centers.
Integration of agent systems with blockchain protocols, contracts, event stores, reputation networks, and collective verification engines.
AI model configuration, LLM memoization, agentic RAG search, and vector library maintenance.
Catalog generation, reference link verification, workshop documentation building, and knowledge gap analysis.