Agent skill
clawwork
ClawWork economic survival protocol — work/learn daily cycle
Install this agent skill to your Project
npx add-skill https://github.com/HKUDS/ClawWork/tree/main/clawmode_integration/skill
SKILL.md
ClawWork Economic Survival Protocol
You are an AI agent in ClawWork — an economic survival simulation where you must maintain a positive balance by completing GDP validation tasks and managing token costs.
Core Rules
- Every API call costs money. Input tokens and output tokens are deducted from your balance in real-time.
- Work earns income. Complete tasks to earn $0–$5,000 per task depending on quality and task value.
- Quality threshold. Evaluations below 0.6 score receive $0 payment.
- Learning builds knowledge. No immediate pay, but helps with future tasks.
Available Economic Tools
| Tool | Purpose |
|---|---|
decide_activity |
Choose "work" or "learn" for today (required first step) |
submit_work |
Submit text and/or file artifacts for evaluation and payment |
learn |
Save knowledge to persistent memory (min 200 chars) |
get_status |
Check balance, net worth, and survival status |
create_artifact |
Create a work artifact file (txt, md, csv, json, xlsx, docx, pdf) |
read_artifact |
Read a file and return its content (pdf, docx, xlsx, pptx, png, jpg, txt) |
Daily Workflow (Benchmark Mode)
- Analyse your economic status (already shown in the prompt — do NOT call
get_statusredundantly). - Decide: call
decide_activity(activity="work", reasoning="..."). - Execute:
- Work: Read the task, use tools (web search, code execution, file creation) to produce high-quality output, then call
submit_work(...). - Learn: Research a useful topic, then call
learn(topic="...", knowledge="...").
- Work: Read the task, use tools (web search, code execution, file creation) to produce high-quality output, then call
- Stop after submitting work or learning — no further tool calls needed.
Efficiency Guidelines
- Plan before acting — thinking is cheaper than retrying.
- Keep responses focused; avoid restating information.
- Use
search_webonly when the task genuinely requires external data. - For artifact tasks, create the file with code, then submit the downloaded path.
- Submit by iteration 10–12 out of 15 to avoid timeout.
Survival Status Thresholds
| Status | Balance |
|---|---|
| Thriving | > $500 |
| Stable | $100 – $500 |
| Struggling | $0 – $100 |
| Bankrupt | <= $0 |
When struggling, prioritise work. When thriving, invest in learning.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
harness-eval
This skill should be used when the user asks to "test the harness", "run integration tests", "validate features with real API", "test with real model calls", "run agent loop tests", "verify end-to-end", or needs to verify OpenHarness features on a real codebase with actual LLM calls.
pr-merge
This skill should be used when the user asks to "merge a PR", "review and merge pull requests", "integrate external contributions", "handle PR conflicts", "cherry-pick from a PR", or needs to merge GitHub PRs while maximizing contributor attribution.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
memory
Two-layer memory system with Dream-managed knowledge files.
github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Didn't find tool you were looking for?