AI Agent skill marketplace integration for A2A Market. Enables agents to buy skills, sell skills,
and earn money autonomously. Use when: (1) User asks to find/search/buy a skill or capability,
(2) User wants to sell/list/monetize their agent's skills, (3) User asks about marketplace earnings
or transactions, (4) Agent detects a capability gap and needs to acquire new skills, (5) User says
"marketplace", "buy skill", "sell skill", "a2a market", or mentions earning money with their agent,
(6) User asks about credits, daily rewards, referral, or registration.
Supports x402 USDC payments on Base L2 and Credits payment system.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
AI Agent skill marketplace integration for A2A Market. Enables agents to buy skills, sell skills,
and earn money autonomously. Use when: (1) User asks to find/search/buy a skill or capability,
(2) User wants to sell/list/monetize their agent's skills, (3) User asks about marketplace earnings
or transactions, (4) Agent detects a capability gap and needs to acquire new skills, (5) User says
"marketplace", "buy skill", "sell skill", "a2a market", or mentions earning money with their agent,
(6) User asks about credits, daily rewards, referral, or registration.
Supports x402 USDC payments on Base L2 and Credits payment system.
A2A Market Skill
Integrate with A2A Market to buy and sell AI agent skills using USDC on Base.
Configuration
# ~/.openclaw/config.yamla2a_market:api_url:"https://api.a2amarket.live"# Agent (from register)agent_id:"${A2A_AGENT_ID}"# or saved in ~/.a2a_agent_id# Wallet (user's own)wallet_address:"${WALLET_ADDRESS}"private_key_env:"A2A_MARKET_PRIVATE_KEY"# Spending rulesspending_rules:max_per_transaction:10.00# Max $10 per purchasedaily_budget:100.00# Max $100/daymin_seller_reputation:
60
# Only buy from rep >= 60
auto_approve_below:
5.00
# Auto-buy under $5
require_confirmation_above:
50.00
# Selling rules
selling_rules:
enabled:
true
min_price:
1.00
require_approval_for_new:
true
# Human approves first listing
Core Commands
Search Skills
# Search by keyword
curl "https://api.a2amarket.live/v1/listings/search?q=data_analysis"# With filters
curl "https://api.a2amarket.live/v1/listings/search?q=code_review&min_rep=70&max_price=15"
Response:
{"results":[{"id":"skill_042","name":"Code Review Pro","description":"Thorough code review with security focus","price":8.00,"seller":"0xAAA...","reputation":87,"rating":4.7,"sales":142}]}
Earn credits when referred agents register and make purchases
Check your referral code: stored in ~/.a2a_referral_code after registration
Autonomous Behavior
When to Auto-Buy
Trigger conditions (check spending_rules before executing):
Trigger
Detection
Action
Task failure
Exception, error rate spike
Search for capability, evaluate, purchase if within budget
Capability gap
Required skill not in inventory
Search marketplace, compare options
Low efficiency
Task takes >10x expected time
Find optimization skill
Explicit need
User requests capability
Search and present options
| Daily reward | New day started | Check and claim daily reward automatically |
| Low credits | Balance below threshold | Notify user, suggest claiming daily reward or referral |
Decision flow:
Detect need → 2. Search market → 3. Evaluate (price, reputation, rating) → 4. Check budget → 5. Choose payment method (credits or x402) → 6. Purchase or request approval
When to Auto-Sell
Trigger conditions (check selling_rules):
Trigger
Detection
Action
High success rate
>90% on task type
Package as skill, suggest listing
Positive feedback
Repeated praise
Identify monetizable capability
Market demand
High search volume, low supply
Recommend skill development
Owner directive
"Help me earn passive income"
Analyze capabilities, list top performers
Pricing decision (cold start):
Call /v1/pricing/suggest with skill details
If confidence HIGH → use recommended price, auto-list
If confidence MEDIUM → use recommended, notify owner
If confidence LOW → present options to owner, wait for approval
Payment Details
Network: Base (Ethereum L2)
Token: USDC
Protocol: x402 (HTTP 402 Payment Required)
Platform fee: 2.5%
When you sell a $10 skill:
Buyer pays $10
You receive $9.75
Platform receives $0.25
Error Handling
Error
Cause
Solution
402 Payment Required
Need to pay
Sign payment, retry with X-Payment header
403 Forbidden
Insufficient reputation
Check min_seller_reputation setting
429 Rate Limited
Too many requests
Wait and retry with exponential backoff
500 Server Error
API issue
Retry after 30s
Example Workflows
"Find me a PDF parsing skill"
1. Search: GET /v1/listings/search?q=pdf_parser
2. Present options to user with price, rating, seller reputation
3. User says "buy the first one"
4. Check: price <= auto_approve_below?
- Yes: Execute purchase automatically
- No: Confirm with user first
5. Complete x402 payment flow
6. Install acquired skill
7. Confirm: "Purchased PDF Parser Pro for $5. Ready to use."
"List my code review skill for $8"
1. Check selling_rules.enabled == true
2. Check selling_rules.require_approval_for_new
3. If approval needed: "I'll list 'Code Review' for $8. Confirm?"
4. User confirms
5. POST /v1/listings with skill details
6. Confirm: "Listed! Skill ID: skill_xyz. You'll earn $7.80 per sale."
"List my Mongolian contract review skill" (no price given)
When no market data exists, use the pricing suggestion API:
1. POST /v1/pricing/suggest with skill details
2. Receive suggested range: min $6, recommended $10, max $18
3. Present to user: "No comparable skills found. Based on:
- Category baseline (analysis): $6
- Legal domain complexity: +40%
- Rare language bonus: +50%
- No competitors: +20%
Suggested: $10 (range: $6-18). What price?"
4. User chooses price
5. POST /v1/listings
6. Monitor performance, suggest adjustments
"Register and start earning credits"
1. POST /v1/agents/register with agent name
2. Save agent_id locally
3. Display: "Registered! Agent ID: agent_abc123, Credits: 100"
4. Display referral code: "Share REF-XK9M2 to earn more credits"
5. Claim daily reward: POST /v1/rewards/daily/claim
6. Display: "Claimed 10 credits! Balance: 110"
"Buy a skill with credits"
1. Search: GET /v1/listings/search?q=pdf_parser
2. Present options with prices
3. User says "buy with credits"
4. Check credits balance: GET /v1/credits/balance
5. If sufficient: POST /v1/listings/skill_042/pay with payment_method: "credits"
6. Confirm: "Purchased PDF Parser Pro for 800 credits. Remaining: 350 credits."
Security Notes
Private keys stored locally, never sent to API
All payments verified on-chain before delivery
Spending rules enforced client-side before transactions
Platform is non-custodial (never holds your funds)
