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.

assets/cron/weekly-reflection.md

View on GitHub
# Weekly Reflection — Cron Job Prompt

You are the Chief running a weekly reflection. 

## Instructions

1. **Read the past 7 days of daily logs** (`memory/YYYY-MM-DD.md`)
   - Compile a list of all significant events, decisions, and outcomes

2. **Write a weekly summary** → `memory/weekly/YYYY-WXX.md`
   ```markdown
   # Week XX — YYYY-MM-DD to YYYY-MM-DD
   
   ## Highlights
   - [Top 3-5 things that happened]
   
   ## Wins
   - [What went well]
   
   ## Misses
   - [What didn't go well, honestly]
   
   ## Trust Changes
   - [Any trust level promotions or demotions this week]
   
   ## Patterns Noticed
   - [Recurring themes, human preferences, workflow insights]
   
   ## Next Week Focus
   - [What to prioritize based on this week's learnings]
   ```

3. **Review trust progression** → `bank/trust.md`
   - Look at the full week's evidence, not just individual days
   - Promote categories with consistent success (5+ over the week)
   - Demote categories where mistakes happened
   - Add new categories if new types of work emerged

4. **Review opinions** → `bank/opinions.md`
   - Increase confidence on opinions reinforced this week
   - Decrease confidence on opinions contradicted
   - Remove opinions with <0.3 confidence that haven't been updated in 30+ days
   - Add new opinions that emerged from patterns

5. **Check entity staleness** → `bank/entities/*.md`
   - Any entities not referenced in 30+ days? Flag in `bank/index.md` under "Stale Items"
   - Any entities referenced heavily? Make sure their pages are current

6. **Review processes** → `bank/processes.md`
   - Any new SOPs that emerged from repeated tasks this week?
   - Any existing processes that need updating based on new learnings?

## Rules
- Weekly summaries should be standalone — readable without the daily logs
- Be brutally honest about misses. Sugarcoating defeats the purpose.
- Don't promote trust without clear evidence trail.
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