CAT
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Validation

aibtcdev/skills
121 installs6 stars
Summary

This implements ERC-8004 on-chain agent validation for Stacks L2, letting agents request validation from validators and letting validators respond with scored assessments. You get six subcommands: request and respond for write operations (which need a wallet), plus four read operations for checking status, pulling summaries, and paginating through validation lists by agent or validator. Responses are 0-100 scores that can be updated progressively, all tied to SHA-256 hashes of request and response data. The pagination works with 14-item pages and cursor-based navigation. If you're building agent reputation systems or need verifiable on-chain trust signals, this gives you the primitives to do it without rolling your own registry contract.

Install to Claude Code

npx -y skills add aibtcdev/skills --skill validation --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Files
SKILL.mdView on GitHub

Validation Skill

Provides ERC-8004 on-chain agent validation operations using the validation-registry contract. Read operations (get-status, get-summary, get-agent-validations, get-validator-requests) work without a wallet. Write operations (request, respond) require an unlocked wallet.

Usage

bun run validation/validation.ts <subcommand> [options]

Subcommands

request

Request validation from a validator for an agent in the ERC-8004 validation registry. The request hash must be a 32-byte SHA-256 hash of the request data. Requires an unlocked wallet.

bun run validation/validation.ts request --validator <address> --agent-id <id> --request-uri <uri> --request-hash <hex> [--fee <fee>] [--sponsored]

Options:

  • --validator (required) — Stacks address of the validator to request validation from
  • --agent-id (required) — Agent ID to request validation for (non-negative integer)
  • --request-uri (required) — URI pointing to the validation request data
  • --request-hash (required) — 32-byte SHA-256 hash of the request data as a hex string
  • --fee (optional) — Fee preset (low, medium, high) or micro-STX amount
  • --sponsored (flag) — Submit as a sponsored transaction

Output:

{
  "success": true,
  "txid": "0xabc...",
  "message": "Validation requested from SP2... for agent 42.",
  "validator": "SP2...",
  "agentId": 42,
  "requestUri": "ipfs://request...",
  "network": "mainnet",
  "explorerUrl": "https://explorer.hiro.so/txid/0xabc..."
}

respond

Submit a validation response for a pending validation request. Only the validator specified in the original request can call this. Response must be an integer between 0 and 100. Can be called multiple times for progressive updates. Requires an unlocked wallet.

bun run validation/validation.ts respond --request-hash <hex> --response <value> --response-uri <uri> --response-hash <hex> [--tag <tag>] [--fee <fee>] [--sponsored]

Options:

  • --request-hash (required) — 32-byte SHA-256 hash of the original request as a hex string
  • --response (required) — Validation response score (integer between 0 and 100)
  • --response-uri (required) — URI pointing to the validation response data
  • --response-hash (required) — 32-byte SHA-256 hash of the response data as a hex string
  • --tag (optional) — Classification tag for the validation response
  • --fee (optional) — Fee preset (low, medium, high) or micro-STX amount
  • --sponsored (flag) — Submit as a sponsored transaction

Output:

{
  "success": true,
  "txid": "0xdef...",
  "message": "Validation response 85 submitted for request hash a3f2b1....",
  "response": 85,
  "responseUri": "ipfs://response...",
  "tag": "security",
  "network": "mainnet",
  "explorerUrl": "https://explorer.hiro.so/txid/0xdef..."
}

get-status

Get the status of a validation request by its 32-byte request hash. Returns validator, agent ID, response score, response hash, tag, last update block, and whether a response has been submitted. Does not require a wallet.

bun run validation/validation.ts get-status --request-hash <hex>

Options:

  • --request-hash (required) — 32-byte SHA-256 hash of the validation request as a hex string

Output:

{
  "success": true,
  "requestHash": "a3f2b1...64hex",
  "validator": "SP2...",
  "agentId": 42,
  "response": 85,
  "responseHash": "b4e9c2...64hex",
  "tag": "security",
  "lastUpdate": 123456,
  "hasResponse": true,
  "network": "mainnet"
}

get-summary

Get the aggregated validation summary for an agent. Returns the total validation count and average response score. Does not require a wallet.

bun run validation/validation.ts get-summary --agent-id <id>

Options:

  • --agent-id (required) — Agent ID to query (non-negative integer)

Output:

{
  "success": true,
  "agentId": 42,
  "count": 3,
  "avgResponse": 88,
  "network": "mainnet"
}

get-agent-validations

Get a paginated list of validation request hashes for an agent. Returns request hashes as hex strings. Cursor-based pagination with page size 14. Does not require a wallet.

bun run validation/validation.ts get-agent-validations --agent-id <id> [--cursor <cursor>]

Options:

  • --agent-id (required) — Agent ID to query (non-negative integer)
  • --cursor (optional) — Pagination cursor (non-negative integer, from previous response)

Output:

{
  "success": true,
  "agentId": 42,
  "validations": ["a3f2b1...64hex", "c5d8e4...64hex"],
  "cursor": null,
  "network": "mainnet"
}

get-validator-requests

Get a paginated list of validation request hashes submitted to a validator. Returns request hashes as hex strings. Cursor-based pagination with page size 14. Does not require a wallet.

bun run validation/validation.ts get-validator-requests --validator <address> [--cursor <cursor>]

Options:

  • --validator (required) — Stacks address of the validator to query
  • --cursor (optional) — Pagination cursor (non-negative integer, from previous response)

Output:

{
  "success": true,
  "validator": "SP2...",
  "requests": ["a3f2b1...64hex", "c5d8e4...64hex"],
  "cursor": null,
  "network": "mainnet"
}

Notes

  • Read operations (get-status, get-summary, get-agent-validations, get-validator-requests) work without a wallet
  • Write operations require an unlocked wallet (bun run wallet/wallet.ts unlock)
  • --request-hash and --response-hash must be exactly 32 bytes (64 hex characters); use SHA-256
  • --response score must be an integer between 0 and 100 (inclusive)
  • respond can only be called by the validator specified in the original validation request
  • respond can be called multiple times on the same request for progressive updates
  • Pagination uses cursor-based navigation; pass the cursor from one response into the next call
  • Validation is a Stacks L2 operation — check transaction status with stx get-transaction-status after write calls
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
First SeenJun 3, 2026
View on GitHub

Recommended

caveman

juliusbrussee/caveman

Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.
203.4k
67.8k
grill-me

mattpocock/skills

Relentless interviewing skill that stress-tests plans and designs through systematic questioning.
250.9k
114.5k
improve

shadcn/improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for other models/agents to execute.
10
205
systematic-debugging

obra/superpowers

Structured debugging methodology that mandates root cause investigation before attempting any fixes.
124.6k
215.9k
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
13.9k
165.4k
find-skills

vercel-labs/skills

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities.
1.8M
21.1k