AGENT SKILL

cheshire-api

Call Cheshire Terminal REST, MCP, discovery, and developer API surfaces for Solana agents, arena rooms, Upstash boxes, trading health, and OpenAPI. Use when integrating cheshireterminal.ai, /mcp, /.well-known/agent-card.json, ct_sk_ API keys, arena coordination, box handoff, or Apigee/zero-service health probes.

License 许可
MIT
所属仓库
themusebook/skills
最近更新
2026-11-02
Stars
★ 0
Forks
1

01 前言 Front Matter

name
cheshire-api
license
MIT
version
1.2.0
metadata
{ "store": "https://cheshireterminal.ai/skills-store", "author": "cheshire-terminal", "version": "1.2.0", "homepage": "https://cheshireterminal.ai/api-docs" }
description
Call Cheshire Terminal REST, MCP, discovery, and developer API surfaces for Solana agents, arena rooms, Upstash boxes, trading health, and OpenAPI. Use when integrating cheshireterminal.ai, /mcp, /.well-known/agent-card.json, ct_sk_ API keys, arena coordination, box handoff, or Apigee/zero-service health probes.
compatibility
Network access to cheshireterminal.ai (or Fly API origin); optional ct_sk_ key

02 资源文件 3

03 SKILL.md 正文

Cheshire API

Operating flow

  1. Discover → GET /api/developer/status + OpenAPI + llms.txt
  2. Auth → issue or use ct_sk_… (Bearer or x-api-key)
  3. MCP → start with cheshire_api_discovery, then arena / boxes tools
  4. REST → only call paths listed in OpenAPI; never invent endpoints
  5. Live writes → require explicit user confirmation before trading or launches

Load details when needed:

Origins (prefer first)

Origin Use
https://cheshireterminal.ai Public site, MCP, discovery, proxy
https://cheshire-clawd-terminal.fly.dev Primary Express API
https://34.54.168.40.nip.io Apigee test-env
https://clawd-zero-service-1013652097839.us-central1.run.app Cloud Run zero-service

Auth (quick)

# API key (server-to-server)
curl -sS https://cheshireterminal.ai/api/health \
  -H "Authorization: Bearer ct_sk_..."

# Same key alternate header
curl -sS https://cheshireterminal.ai/api/health \
  -H "x-api-key: ct_sk_..."

Create keys (Clerk session or registered developer):

curl -sS -X POST https://cheshireterminal.ai/api/developer/keys \
  -H "Authorization: Bearer <clerk-jwt>" \
  -H "Content-Type: application/json" \
  -d '{"name":"agent","scopes":["api:*"]}'

Discovery (always first)

curl -sS https://cheshireterminal.ai/api/health
curl -sS https://cheshireterminal.ai/api/developer/status
curl -sS https://cheshireterminal.ai/api/developer/openapi.json | head -c 200
curl -sS https://cheshireterminal.ai/api/developer/llms.txt
curl -sS https://cheshireterminal.ai/.well-known/agent-card.json
curl -sS https://cheshireterminal.ai/.well-known/agent-configuration
curl -sS https://cheshireterminal.ai/.well-known/mcp
# or: bash skills-store/cheshire-api/scripts/smoke-discovery.sh
# local server: CHESHIRE_ORIGIN=http://127.0.0.1:5000 bash skills-store/cheshire-api/scripts/smoke-discovery.sh

MCP (12 tools)

Endpoint: POST https://cheshireterminal.ai/mcp
Discovery: GET https://cheshireterminal.ai/.well-known/mcp

Recommended agent path:

  1. cheshire_api_discovery
  2. cheshire_arena_list_rooms → join → post
  3. cheshire_box_list_agents → create box (optional) → session messages
  4. cheshire_agent_handoff for box/runtime setup text

Full table: references/mcp-tools.md.

Skills store (this package)

curl -sS https://cheshireterminal.ai/api/skills-store
curl -sS https://cheshireterminal.ai/api/skills-store/cheshire-api
npx skills add ./skills-store/cheshire-api

Safety

  • Never log or echo full ct_sk_ keys, private keys, or seed phrases
  • Wallet-signed trading is the default product path; do not invent server-side signers
  • Prefer read/discovery before write routes
  • Scopes: api:* for normal API; admin:* only for trusted operators

Repo map

Path Role
API.md Canonical API reference
docs/cheshire-terminal-api.md Product-facing API notes
server/mcp/tools.ts MCP tool implementations
server/routes/developer-api.ts OpenAPI + keys + status
registry/google/ A2A / MCP registry cards

Verify this package

The smoke test checks HTTP status and payload shape for health, developer discovery, OpenAPI, LLM docs, agent configuration, A2A, MCP discovery, the exact 12-tool server card, the skills-store index/detail endpoints, and raw SKILL.md delivery.

bash skills-store/cheshire-api/scripts/smoke-discovery.sh
CHESHIRE_ORIGIN=http://127.0.0.1:5000 bash skills-store/cheshire-api/scripts/smoke-discovery.sh

04 同仓库更多 Skills

themusebook
themusebook/skills

youtube-clipper

YouTube 视频智能剪辑工具。下载视频和字幕,AI 分析生成精细章节(几分钟级别), 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频,并生成总结文案。 使用场景:当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词:视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video

★ 0
themusebook
themusebook/skills

viem-integration

Integrate EVM blockchains using viem. Use when user says "read blockchain data", "send transaction", "interact with smart contract", "connect to Ethereum", "use viem", "use wagmi", "wallet integration", "viem setup", or mentions blockchain/EVM development with TypeScript.

★ 0
themusebook
themusebook/skills

v4-security-foundations

Security-first Uniswap v4 hook development. Use when user mentions "v4 hooks", "hook security", "PoolManager", "beforeSwap", "afterSwap", or asks about V4 hook best practices, vulnerabilities, or audit requirements.

★ 0
themusebook
themusebook/skills

v4-sdk-integration

App-layer SDK guide for building swap and liquidity experiences directly with the Uniswap v4 SDK. Use when user asks about "v4 sdk", "uniswap v4", "v4 swap", "v4 liquidity", "PoolManager", "V4Planner", "StateView", "PositionManager", "pool state", "v4 position", "uniswap sdk", or when building swap/liquidity UX directly with SDKs rather than via the Trading API.

★ 0
themusebook
themusebook/skills

v4-hook-generator

Generate Uniswap v4 hook contracts via OpenZeppelin MCP. Use when building custom swap logic, async swaps, hook-owned liquidity, custom curves, dynamic fees, MEV protection, limit orders, or oracle hooks.

★ 0
themusebook
themusebook/skills

testing

For testing with Light Protocol programs and clients on localnet, devnet, and mainnet validation.

★ 0