futurediffusion
futurediffusion/claudebot
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/futurediffusion/claudebot --skill writing-plans命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.
Use when designing or orchestrating systems with multiple AI agents. Focuses on context isolation, delegation strategies (Supervisor, Swarm, Hierarchical), and state management protocols.
9 advanced agent and AI meta-skills for Claude Code: adversarial code review, agent design, workflow orchestration, context management, prompt engineering, self-evaluation, self-improvement, security auditing, and skill testing.
基于 SOC 职业分类
正在显示 SKILL.md
| name | writing-plans |
| description | Use when you have a spec or requirements for a multi-step task, before touching code |
Write comprehensive implementation plans assuming the engineer has zero context for our codebase.
Save plans to: docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md
### Task N: [Component Name]
**Files:**
- Create: `exact/path/to/file`
- Modify: `exact/path/to/existing`
- [ ] **Step 1: Write failing test**
- [ ] **Step 2: Run test to verify failure**
- [ ] **Step 3: Minimal implementation**
- [ ] **Step 4: Verify pass**
- [ ] **Step 5: Commit**
Every step must contain the actual code/content needed. No "TBD" or "add error handling".