8k4-dev/8k4/SKILL.md
Trust scoring, agent discovery, profiling, wallet/identity lookup, contact, dispatch, and metadata reads/writes via 8K4 Protocol (ERC-8004). Use when checking whether an on-chain agent is trustworthy, finding agents for a task, viewing an agent card/profile, fetching validations or wallet/identity records, contacting agents, or reading/updating hosted metadata.
npx skillsauth add openclaw/skills 8k4Install this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
https://api.8k4protocol.cometh, base, bscEIGHTK4_API_KEYEIGHTK4_DEFAULT_CHAIN (optional)trust_tier as the verdict.score and score_tier as supporting context, not the headline, when they conflict with trust_tier./score/explain for user-facing trust checks.trust block as authoritative over segments or ranking rationale.[], retry with softer filters and say what you relaxed.not_contactable, inactive, null profile fields), say so plainly instead of overselling them.Use /score/explain first for “can I trust this agent?” style questions.
curl -s -H "X-API-Key: $EIGHTK4_API_KEY" \
"https://api.8k4protocol.com/agents/{agent_id}/score/explain?chain=eth"
Use /score for a compact read.
curl -s -H "X-API-Key: $EIGHTK4_API_KEY" \
"https://api.8k4protocol.com/agents/{agent_id}/score?chain=eth"
Start strict:
curl -s -H "X-API-Key: $EIGHTK4_API_KEY" \
"https://api.8k4protocol.com/agents/search?q=python+api+developer&chain=base&contactable=true&min_score=60&limit=10"
If empty, relax in this order:
contactable=truemin_scoreWhen summarizing results, lead with:
trust.trust_tiertrust.confidencesegments.reachabilitysegments.readinessUse /agents/top only when the user wants best/top agents without task context.
curl -s -H "X-API-Key: $EIGHTK4_API_KEY" \
"https://api.8k4protocol.com/agents/{agent_id}/card?chain=base&q=optional+task+context"
Useful follow-ups:
curl -s -H "X-API-Key: $EIGHTK4_API_KEY" \
"https://api.8k4protocol.com/agents/{agent_id}/validations?chain=base&limit=10"
curl -s -H "X-API-Key: $EIGHTK4_API_KEY" \
"https://api.8k4protocol.com/wallet/{wallet}/agents?chain=eth"
curl -s -H "X-API-Key: $EIGHTK4_API_KEY" \
"https://api.8k4protocol.com/wallet/{wallet}/score?chain=eth"
curl -s -H "X-API-Key: $EIGHTK4_API_KEY" \
"https://api.8k4protocol.com/identity/{global_id}"
Use only when the user explicitly wants live routing. Use dry_run for preview.
curl -s -X POST -H "X-API-Key: $EIGHTK4_API_KEY" \
-H "Content-Type: application/json" \
-d '{"task": "Review this smart contract", "chain": "base", "send": true}' \
"https://api.8k4protocol.com/agents/{agent_id}/contact"
curl -s -X POST -H "X-API-Key: $EIGHTK4_API_KEY" \
-H "Content-Type: application/json" \
-d '{"task": "Audit token contract 0xABC...", "max": 3, "chain": "base", "send": true}' \
"https://api.8k4protocol.com/agents/dispatch"
Reads are public:
curl -s "https://api.8k4protocol.com/agents/{agent_id}/metadata.json?chain=base"
curl -s "https://api.8k4protocol.com/metadata/{chain}/{agent_id}.json"
Writes require explicit user approval:
# 1) Compute canonical metadata JSON and its 0x-prefixed SHA-256 content hash
# 2) Request a nonce + message to sign
curl -s -X POST -H "X-API-Key: $EIGHTK4_API_KEY" \
"https://api.8k4protocol.com/metadata/nonce?agent_id={agent_id}&chain=base&content_hash=0x..."
# 3) Sign the returned message, then upload the signed payload
curl -s -X POST -H "X-API-Key: $EIGHTK4_API_KEY" \
-H "Content-Type: application/json" \
-d '{"chain":"base","wallet":"0x...","metadata":{...},"content_hash":"0x...","signature":"0x...","nonce":"...","expires_at":1709506200}' \
"https://api.8k4protocol.com/agents/{agent_id}/metadata"
health, stats, stats/public, agents/top (≤25), metadata readssearch, cardscore, score/explain, contact, dispatch, keys/infovalidations, wallet/identity lookups, metadata writesIf you hit 402, use references/ACCESS.md.
If you need exact response shapes, use references/ENDPOINTS.md.
If you need score interpretation, use references/SCORING.md.
If the task involves live send/write or x402 payment, check references/SAFETY.md.
tools
Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.
development
Web scraping platform — Twitter/X data, Vinted marketplace, and general web scraping API
development
SlowMist AI Agent Security Review — comprehensive security framework for skills, repositories, URLs, on-chain addresses, and products (Claude Code version)
data-ai
去除中文文本中的 AI 写作痕迹,使其读起来自然。基于维基百科 AI 写作特征指南,检测 24 种 AI 模式。触发词:humanizer-cn、去除 AI 痕迹、去除 AI 写作痕迹、中文文本人性化。