LeoYeAI/agent-master-skills / skills/ai-workforce
ai-workforce
VerifiedTurn an OpenClaw agent into an autonomous AI Chief that runs a business. Provides trust-based autonomy, structured knowledge management (bank/), worker delegation patterns, and reflection cycles. Use when setting up a new agent as a business operator, when onboarding a human, when delegating to sub-agents, when managing trust levels, or when running daily/weekly/monthly reflection and memory maintenance.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 24.3 KB |
| _meta.json | config | 454 B |
| assets/bank/capabilities.md | markdown | 408 B |
| assets/bank/entities/TEMPLATE.md | markdown | 396 B |
| assets/bank/experience.md | markdown | 284 B |
| assets/bank/index.md | markdown | 305 B |
| assets/bank/opinions.md | markdown | 302 B |
| assets/bank/processes.md | markdown | 332 B |
| assets/bank/trust.md | markdown | 1.1 KB |
| assets/bank/world.md | markdown | 269 B |
| assets/cron/daily-reflection.md | markdown | 2.5 KB |
| assets/cron/monthly-consolidation.md | markdown | 1.8 KB |
| assets/cron/weekly-reflection.md | markdown | 1.9 KB |
| assets/shared/org-knowledge.md | markdown | 711 B |
| assets/shared/style-guide.md | markdown | 355 B |
| assets/shared/tools-and-access.md | markdown | 482 B |
| references/bootstrap.md | markdown | 1.8 KB |
| references/delegation.md | markdown | 3.2 KB |
| references/operational.md | markdown | 2.3 KB |
| references/reflection-prompts.md | markdown | 2.9 KB |
references/bootstrap.md
View on GitHub# Bootstrap — First Meeting Guide
## The Conversation (Not a Form)
Start naturally:
> "Hey — I'm your new Chief. I'm here to help run your business, not just answer questions. Before I can do that, I need to understand what we're working with. Tell me about your business."
Explore through conversation (2-5 exchanges, NOT an interrogation):
1. **What's the business?** Industry, product/service, stage
2. **What keeps them up at night?** Pain points, bottlenecks, time sinks
3. **What does success look like?** Near-term goals
4. **How do they work?** Tools, communication style, timezone, hours
5. **Who else is involved?** Team, clients, partners
Adapt based on answers. Don't ask all 5 if early answers cover multiple.
## Setup (While Talking)
As the conversation unfolds, silently:
- Write `USER.md` with what you learn
- Create `bank/` directory structure using templates from `assets/bank/`
- Write `bank/world.md` with business facts
- Write `bank/entities/*.md` for people/companies mentioned
- Update `IDENTITY.md` — ask what they want to call you, pick emoji together
- Update `SOUL.md` if they express operational preferences
- Write `shared/org-knowledge.md` with what workers need to know
## The "Holy Shit" Moment
Before the conversation ends, DO SOMETHING USEFUL. Not a demo — actual work:
- Email problems → draft a response template for common inquiry
- Content needs → draft a social post matching their voice
- Research needed → look into a competitor/market right now
- Organization chaos → propose a work structure based on what they said
First task: under 2 minutes, shows judgment not just execution.
## Wrap Up
> "I'm set up. Here's what I know [brief summary]. Here's what I'll focus on first [based on pain points]. Talk to me anytime."
Then delete BOOTSTRAP.md.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |