skill-orchestrator
关于
The skill-orchestrator routes complex, multi-step business challenges to the correct sequence of specialized ClawFu skills. It recommends which frameworks to combine and the execution order, managing handoffs between steps. Use it for orchestrating end-to-end projects like product launches, validation sprints, or content pipelines that require chaining multiple skills.
快速安装
Claude Code
推荐npx skills add guia-matthieu/clawfu-skills -a claude-code/plugin add https://github.com/guia-matthieu/clawfu-skillsgit clone https://github.com/guia-matthieu/clawfu-skills.git ~/.claude/skills/skill-orchestrator在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Skill Orchestrator
Route multi-step challenges to the right sequence of ClawFu skills — recommending which frameworks to combine, in what order, with explicit handoff outputs between steps.
When to Use This Skill
- Starting a new project and need the optimal skill sequence
- Complex multi-faceted challenges requiring multiple frameworks
- Team alignment on a structured approach across disciplines
- Overwhelmed by options — cut through skill paralysis
- Chaining skills where outputs from one feed into the next
Methodology Foundation
| Aspect | Details |
|---|---|
| Source | ClawFu Skills orchestration system |
| Core Principle | The right frameworks in the right order compound insights — sequencing matters more than any single skill |
| Sequencing Logic | Foundation → Analysis → Strategy → Creation → Validation → Execution |
What Claude Does vs What You Decide
| Claude Does | You Decide |
|---|---|
| Recommends skill sequences for a challenge | Which skills to skip or substitute |
| Defines input/output handoffs between steps | Final strategic direction at each step |
| Creates custom workflows from the skill library | Resource allocation and timeline |
| Identifies when to branch or loop back | Go/no-go decisions at validation gates |
Instructions
Step 1: Analyze the Challenge
Classify the challenge type and context:
| Factor | Options |
|---|---|
| Type | Launch · Validation · Content · Positioning · Decision · Sales · Video |
| Stage | Idea · Early · Growth · Mature |
| Resources | Solo · Small team · Large team |
| Timeline | Urgent · Normal · Flexible |
Step 2: Match to Workflow or Build Custom Sequence
Check pre-built workflows in WORKFLOWS.md. If none fits, build a custom sequence following this phase order:
| Phase | Skill Types | Purpose |
|---|---|---|
| 1. Foundation | first-principles, JTBD, audience-research | Understand reality |
| 2. Analysis | competitive-analysis, inversion, pre-mortem | Identify challenges |
| 3. Strategy | positioning, category-design, personas | Make strategic choices |
| 4. Creation | offers, copy, content | Build the deliverable |
| 5. Validation | six-thinking-hats, pricing-validation | Stress test |
| 6. Execution | launch-formula, sales-pitch | Go to market |
Step 3: Execute Step by Step
For each step in the sequence:
- State the skill and purpose — why this step matters now
- List inputs from previous steps
- Execute the skill fully
- Capture outputs — document key deliverables
- Validate before proceeding — verify outputs are sufficient for the next step
Validation checkpoint: Before moving to the next skill, confirm the output includes the specific artifacts the next step needs. If not, iterate or add an intermediate step.
Step 4: Synthesize Cross-Skill Insights
After completing the sequence:
- Patterns — themes emerging across multiple frameworks
- Conflicts — where Skill A says X but Skill B says Y, and how to resolve
- Compounding insights — conclusions that only emerge from the combination
Examples
Example: AI Writing Tool Launch
Challenge: Launching an AI writing tool for marketers in a competitive market (Jasper, Copy.ai)
Recommended sequence (modified Product Launch):
1. competitive-analysis → Map landscape (Jasper, Copy.ai, ChatGPT)
2. first-principles → Challenge "AI writing tool" category assumptions
3. persona-generator → Define specific segments (not just "marketers")
4. category-design → Can you own a new category?
5. positioning → Differentiate using competitive gaps
6. grand-slam-offers → Create irresistible offer structure
7. pre-mortem → What could kill the launch?
8. launch-formula → Sequence the mechanics
Handoff example: Step 3 (personas) feeds into Step 5 (positioning) — persona pain points define which competitive alternatives matter most.
See WORKFLOWS.md for all pre-built workflows (Product Launch, Customer Validation, Content Strategy, Competitive Positioning, Sales Enablement, Decision Making, AI Video Production).
Skill Boundaries
What This Skill Does Well
- Sequencing skills for maximum compounding value
- Defining explicit handoffs between framework stages
- Adapting pre-built workflows to specific contexts
What This Skill Cannot Do
- Execute the individual skills (it routes to them)
- Make strategic decisions — it structures the decision process
- Guarantee outcomes — quality depends on inputs at each step
References
- Pre-built workflows: WORKFLOWS.md
- Christensen, Clayton. "How Will You Measure Your Life?" — Job sequencing
- Rumelt, Richard. "Good Strategy Bad Strategy" — Strategic coherence
- Blank, Steve. "The Startup Owner's Manual" — Customer development sequence
Related Skills
- first-principles — Start here for foundation
- lean-canvas — Start here for validation
- positioning — Start here for differentiation
- content-strategy — Start here for content
- ai-video-concept — Start here for AI video production
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
polymarket
元这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
creating-opencode-plugins
元该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
