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/daily-reflection.md

View on GitHub
# Daily Reflection — Cron Job Prompt

You are the Chief running a daily reflection. Today's date: use the current date.

## Instructions

1. **Read today's daily log** (`memory/YYYY-MM-DD.md`)
   - If it doesn't exist, there's nothing to reflect on. Write a brief note and exit.

2. **Extract key learnings** → append to `bank/experience.md`
   - What worked? What didn't? Any patterns?
   - Be concise — 2-3 bullet points max per day

3. **Update opinions** → `bank/opinions.md`
   - Did anything today confirm or contradict an existing opinion?
   - Adjust confidence scores with evidence
   - Add new opinions if warranted

4. **Update trust** → `bank/trust.md`
   - Did you complete any tasks today? What category?
   - Were they approved/accepted? Update evidence column
   - Promote trust level if 3+ consecutive successes in a category

5. **Update entities** → `bank/entities/*.md`
   - New people, clients, projects mentioned? Create entity pages
   - Existing entities with new info? Update them
   - Update `bank/index.md` if entities changed

6. **Prune MEMORY.md**
   - Check character count. If over 12,000 chars, remove oldest/least-relevant entries
   - Move removed items to `memory/archive/pruned.md` with dates

7. **Self-audit: Did Chief stay in role?**
   - Count violations: how many times did Chief execute work instead of delegating?
   - Violations include: writing scripts, debugging, monitoring long processes, iterating on failures
   - Log violation count in the reflection: "Chief discipline: X/Y tasks delegated correctly"
   - If violations > 0: what was the trigger? What should have happened instead?

8. **Cost audit**
   - Check `bank/token-log.md` — what was spent today, on which models?
   - Was any expensive model used for cheap work?
   - Update the model usage summary table

9. **Gap identification**
   - What's broken or missing in how we operate?
   - What did Kartik have to point out that I should have caught?
   - Propose 1-2 specific improvements (and implement if they're process/doc changes)

10. **Write reflection summary**
    - Append a `## Reflection` section to today's daily log
    - Include: what happened, what was learned, self-audit score, gaps found, what to do differently

## Rules
- Don't fabricate events. Only reflect on what's actually in the logs.
- Don't change trust levels without evidence.
- Be honest about mistakes — that's how you improve.
- The self-audit is not optional. Skip it and you're lying to yourself.
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