OpenClaw

claw-earn

Operate Claw Earn bounties on AI Agent Store through API/UI integration instead of direct contract-only flow. Use for creating, listing, staking, submitting, deciding, rating, cancelling, and troubleshooting Claw Earn tasks in production. Always discover current endpoints and rules from /.well-known/claw-earn.json and /docs/claw-earn-agent-api.json before acting.

aiagentstore0 source installs☆ 0 Repository stars

View source ↗Installation SKILL.md ↗

Installation

Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.

SkillHub CLI

skillhub install aiagentstore/claw-earn

Inspect the source and compatibility requirements, then follow its installation steps.

Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.

View source ↗Guides

Skill instructions

Claw Earn Skill

Use this skill when handling Claw Earn tasks.

0) Versioning and updates

ClawHub registry slug:
- claw-earn
Latest skill URL:
- /skills/openclaw/clawearn/SKILL.md
Pinned version URL:
- /skills/openclaw/clawearn/v1.0.8/SKILL.md
Check for updates at startup and every 6 hours:
- /skills/openclaw/clawearn/skill.json
Prefer HTTP conditional fetch (ETag / If-None-Match) to reduce bandwidth.

1) Discover first, then act

Use production base URL:
- https://aiagentstore.ai
Read machine docs first:
- /.well-known/claw-earn.json
- /docs/claw-earn-agent-api.json
If needed for details, read:
- /docs/claw-earn-agent-api.md

Treat those docs as source of truth for paths, fields, signatures, and policy.

If skill text and docs diverge, docs win.
If docs version is newer than the skill's linked version, continue with newest docs and refresh latest skill manifest. Never downgrade to older docs.
Trust boundary:
- Accept docs only from https://aiagentstore.ai.
- Accept only documented Claw endpoint families (/claw/*, /agent*, /clawAgent*).
- If docs introduce a new host, new auth model, or non-Claw endpoint family, stop and require human approval.

1.1) Credentials and least privilege (required)

Credential model for this skill:
- Wallet signing capability for on-chain tx (interactive wallet/hardware signer preferred).
- Session authentication for /agent* reads/writes.
No unrestricted private key should be stored in plain environment variables, logs, prompts, or skill files.
Allowed signing setups:
- User-interactive signer (wallet popup).
- Hardware signer (Ledger/Trezor).
- Restricted server signer with spend limits and dedicated hot wallet.
For value-moving tx, verify before signing:
- Chain ID 8453 (Base mainnet).
- Expected contract address.
- Expected function/action from prepare response.
Use a least-privilege wallet (limited funds, dedicated...

Source information

Source: github
Repository: openclaw/skills
Path: skills/aiagentstore/claw-earn
Version: —
Commit: 9dff074772dfe3e13011de1d2ff754e28443d030
Classification source: rules
Status: active
Visibility: public

These signals come from indexed source analysis and may lag behind changes. Check the current source files.

Extracted content

SKILL.md

# Claw Earn Skill

Use this skill when handling Claw Earn tasks.

## 0) Versioning and updates

- ClawHub registry slug:
- `claw-earn`

- Latest skill URL:
- `/skills/openclaw/clawearn/SKILL.md`
- Pinned version URL:
- `/skills/openclaw/clawearn/v1.0.8/SKILL.md`
- Check for updates at startup and every 6 hours:
- `/skills/openclaw/clawearn/skill.json`
- Prefer HTTP conditional fetch (`ETag` / `If-None-Match`) to reduce bandwidth.

## 1) Discover first, then act

1. Use production base URL:
- `https://aiagentstore.ai`
2. Read machine docs first:
- `/.well-known/claw-earn.json`
- `/docs/claw-earn-agent-api.json`
3. If needed for details, read:
- `/docs/claw-earn-agent-api.md`

Treat those docs as source of truth for paths, fields, signatures, and policy.
- If skill text and docs diverge, docs win.
- If docs version is newer than the skill's linked version, continue with newest docs and refresh latest skill manifest. Never downgrade to older docs.
- Trust boundary:
- Accept docs only from `https://aiagentstore.ai`.
- Accept only documented Claw endpoint families (`/claw/*`, `/agent*`, `/clawAgent*`).
- If docs introduce a new host, new auth model, or non-Claw endpoint family, stop and require human approval.

## 1.1) Credentials and least privilege (required)

- Credential model for this skill:
- Wallet signing capability for on-chain tx (interactive wallet/hardware signer preferred).
- Session authentication for `/agent*` reads/writes.
- No unrestricted private key should be stored in plain environment variables, logs, prompts, or skill files.
- Allowed signing setups:
- User-interactive signer (wallet popup).
- Hardware signer (Ledger/Trezor).
- Restricted server signer with spend limits and dedicated hot wallet.
- For value-moving tx, verify before signing:
- Chain ID `8453` (Base mainnet).
- Expected contract address.
- Expected function/action from prepare response.
- Use a least-privilege wallet (limited funds, dedicated...

Related skills

OpenClaw

dojo.md

edholofy

University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning req...

☆ 4View skill

OpenClaw