Skip to content

LeoYeAI/agent-master-skills / skills/ai-workforce

ai-workforce

Verified

Turn 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.

references/operational.md

View on GitHub
# Operational Patterns

## Worker Specialization

Track what works. Over time, worker configurations develop profiles in `bank/experience.md`:

```
## Worker Patterns That Work
- Research tasks: Sonnet + web_search + "cite all sources" → 90% usable first try
- Content drafts: Sonnet + org-knowledge + style-guide → needs tone fixes 40% of time
- Data extraction: Haiku + specific format instructions → 95% accurate
- Competitor analysis: Sonnet + web_search + web_fetch → good but slow, consider parallel

## Worker Patterns That Don't Work
- Vague research prompts with Haiku → hallucinations
- Long content tasks without style-guide → always needs rewrite
- Multiple questions in one worker task → misses later items
```

Use these patterns to improve future delegations. During weekly reflection, review worker success rates and update patterns.

## Memory Decay Rules

Not all memories age equally. During reflection, apply decay:

- **Referenced this week** → keep, full relevance
- **Referenced this month** → keep, review during monthly consolidation
- **Not referenced in 30+ days** → flag as stale in bank/index.md
- **Not referenced in 60+ days** → archive to memory/archive/ (daily logs) or bank/archive/ (entities)
- **Not referenced in 90+ days** → aggressive pruning from MEMORY.md

**Exceptions (never decay):**
- Business rules and constraints (bank/world.md)
- Trust history (bank/trust.md)
- Human preferences and personal context (USER.md, bank/entities/<human>.md)
- Active processes (bank/processes.md entries used in last 60 days)

**Confidence-weighted:** Opinions in bank/opinions.md with confidence < 0.3 that haven't been updated in 30+ days → remove. The Chief should hold fewer, higher-confidence opinions over time.

## Audit Trail Format

Log significant actions in `memory/YYYY-MM-DD.md` with accountability context:

```
## 14:30 — Sent competitor analysis to human
- Trust level: notify (research tasks)
- Workers used: 2 (web research)
- Reviewed: yes, rewrote summary for brevity
- Cost: ~$0.15

## 15:45 — Proposed email draft to Client X
- Trust level: propose (external communications)
- Awaiting human approval
- Flagged because: first contact with this client
```

When trust is earned through track record, the track record needs to be auditable. During reflection, these logs feed trust progression decisions.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall