← 返回 Skills 市场
ice-coldbell

easyclaw

作者 ColdBell · GitHub ↗ · v0.0.2
cross-platform ⚠ suspicious
514
总下载
0
收藏
2
当前安装
2
版本数
在 OpenClaw 中安装
/install easyclaw
功能描述
Run user-facing EasyClaw DEX actions from a self-contained skill folder. Use when an agent needs to submit user orders or check wallet/margin/order balances...
使用说明 (SKILL.md)

EasyClaw User DEX Skill

Run only user workflows:

  • balance and open-order checks
  • order submission (place order)
  • backend position/order/fill/history/orderbook/chart queries
  • authenticated agent/strategy controls and safety kill-switch
  • realtime websocket monitoring and signal-driven auto order execution

Do not run admin/bootstrap/keeper workflows in this skill.

Runtime & Credential Requirements

  • Wallet signer source: KEYPAIR_PATH or ANCHOR_WALLET (fallback ~/.config/solana/id.json).
  • Solana RPC source: SOLANA_RPC_URL or ANCHOR_PROVIDER_URL (fallback http://127.0.0.1:8899).
  • Backend endpoint source: EASYCLAW_API_BASE_URL / EASYCLAW_WS_URL (or alias vars in backend-common.js).
  • Optional API credential: EASYCLAW_API_TOKEN (required for protected backend controls).
  • Local process usage: onboarding probes solana config get and can spawn child Node.js processes for autotrade execution.
  • Local file writes:
    • onboarding persists selected wallet envs into easyclaw-skill/.env
    • strategy onboarding writes files into easyclaw-skill/state/strategies/

Command Interface

Use {baseDir}/scripts/dex-agent.sh:

# toolchain + environment diagnostics
{baseDir}/scripts/dex-agent.sh doctor

# install local skill dependencies
{baseDir}/scripts/dex-agent.sh install

# wallet, USDC, margin, and open orders
{baseDir}/scripts/dex-agent.sh balance
{baseDir}/scripts/dex-agent.sh balance --json

# submit order tx
{baseDir}/scripts/dex-agent.sh order --market-id 1 --side buy --type market --margin 1000000
{baseDir}/scripts/dex-agent.sh order --market-id 2 --side sell --type limit --margin 2000000 --price 3000000000

# backend REST queries
{baseDir}/scripts/dex-agent.sh backend positions --mine --limit 20
{baseDir}/scripts/dex-agent.sh backend position-history --mine --limit 20
{baseDir}/scripts/dex-agent.sh backend chart-candles --market BTCUSDT --timeframe 1m --limit 120
{baseDir}/scripts/dex-agent.sh backend orderbook-heatmap --exchange binance --symbol BTCUSDT --limit 30
{baseDir}/scripts/dex-agent.sh backend portfolio --period 7d
{baseDir}/scripts/dex-agent.sh backend strategy-templates
{baseDir}/scripts/dex-agent.sh backend agent-risk --agent-id agent-001

# realtime WS monitor
{baseDir}/scripts/dex-agent.sh watch --channels "agent.signals,portfolio.updates,market.price.BTCUSDT"

# realtime signal -> auto order execution
{baseDir}/scripts/dex-agent.sh autotrade --market-id 1 --margin 1000000 --min-confidence 0.75

# guided onboarding + strategy capture + autotrade start
{baseDir}/scripts/dex-agent.sh onboard --market-id 1 --margin 1000000

Files

  • scripts/balance.js: user balance and order summary
  • scripts/order-execute.js: user order submission helper
  • scripts/backend.js: backend REST API query helper
  • scripts/ws-watch.js: backend websocket channel subscriber
  • scripts/realtime-agent.js: signal-driven auto-order loop
  • scripts/onboard.js: interactive onboarding flow (wallet selection, registration wait, strategy capture, autotrade kickoff)
  • scripts/backend-common.js: backend endpoint/auth helpers
  • scripts/common.js: PDA, signer, tx, and decode utilities
  • package.json: local runtime dependencies
  • .env.example: required environment keys

Setup

  1. Copy .env.example to .env.
  2. Fill signer and RPC values.
  3. Run dex-agent.sh install.
  4. Run dex-agent.sh balance first to validate access.
  5. Run dex-agent.sh backend doctor and dex-agent.sh watch --channel system.status.
  6. Run dex-agent.sh onboard --market-id \x3Cid> --margin \x3Cu64> for guided onboarding.

For env definitions and option details, read references/dex-env.md.

Safety

  • Keep KEYPAIR_PATH and private keys local.
  • Use devnet/localnet unless explicitly instructed otherwise.
  • Confirm ORDER_ENGINE_PROGRAM_ID and MARKET_REGISTRY_PROGRAM_ID before placing orders.
安全使用建议
This skill appears to do what it says: interact with EasyClaw and submit Solana orders. Before installing: 1) Do NOT point KEYPAIR_PATH at a mainnet/private wallet you cannot afford to risk; prefer a devnet/localnet keypair or a throwaway wallet for testing. 2) Review and confirm EASYCLAW_API_BASE_URL / EASYCLAW_WS_URL and ORDER_ENGINE_PROGRAM_ID / MARKET_REGISTRY_PROGRAM_ID are correct and expected for the network you intend to use. 3) Note that onboarding will read your local keypair file, run `solana config get`, and write the selection into easyclaw-skill/.env; strategy prompts are written to state/strategies/. 4) The skill can autonomously execute orders (autotrade/realtime) — test with --dry-run and small amounts first and consider running in an isolated environment. 5) If you need stronger protection, avoid exposing your primary keypair file and consider using a signing mechanism (hardware or remote signer) instead of a plain filesystem keypair. 6) If you have low trust in the source, review the scripts (already included) and run dex-agent.sh doctor and dex-agent.sh balance on devnet before enabling autonomous operations.
功能分析
Type: OpenClaw Skill Name: easyclaw Version: 0.0.2 The skill is classified as suspicious due to its inherent high-risk capabilities, including reading and using Solana private keys (`KEYPAIR_PATH` in `scripts/common.js`), signing and sending financial transactions on-chain (`scripts/order-execute.js`), making external API calls to configurable endpoints (`scripts/backend-common.js`), and spawning child processes (`scripts/onboard.js`, `scripts/realtime-agent.js`). While these actions align with the stated purpose of a DEX trading agent, they represent significant attack surfaces. There is no clear evidence of intentional malicious behavior such as unauthorized data exfiltration or backdoor installation within the provided code, nor are there prompt injection attempts against the OpenClaw agent in `SKILL.md` or `agents/openai.yaml`. However, the broad permissions and sensitive operations, particularly the handling of private keys and execution of child processes based on user-controlled inputs, elevate the risk beyond benign, classifying it as suspicious due to the potential for exploitation if inputs or environment variables are compromised.
能力评估
✓ Purpose & Capability
Name/description match what the files implement: Node scripts to query EasyClaw backend, subscribe to websocket channels, and submit Solana DEX orders. Required binaries (node, npm), Solana RPC env vars, program IDs, and a KEYPAIR_PATH or ANCHOR_WALLET are expected for signing transactions and interacting with on-chain programs. Some env var names are duplicated/aliased (EASYCLAW_API_TOKEN / API_AUTH_TOKEN / API_TOKEN) but this is a convenience, not an incoherence.
ℹ Instruction Scope
SKILL.md and the scripts instruct the agent to read local wallet keypair files, run `solana config get`, persist selected wallet settings into easyclaw-skill/.env, write strategy files to easyclaw-skill/state/strategies/, spawn child Node.js processes, subscribe to backend websockets, and can run an autotrade loop that will place real orders. All of those behaviors are within the described purpose, but they include local file reads/writes and autonomous order submission (sensitive actions) and so should be explicitly acknowledged before use.
✓ Install Mechanism
No remote arbitrary download/install is embedded in the skill. The provided dex-agent.sh runs `npm install` (standard) and package.json lists typical npm packages (@solana/web3.js, dotenv, ws). npm install will fetch packages from the public registry (normal risk for Node projects). There are no obscure download URLs or extract steps in the manifest.
ℹ Credentials
The skill requires direct access to a local Solana keypair file (KEYPAIR_PATH / ANCHOR_WALLET and ~/.config/solana/id.json) and backend API tokens (EASYCLAW_API_TOKEN / aliases). These are necessary to sign transactions and call protected backend endpoints, so the requested credentials are proportional to the trading purpose — but they are highly sensitive. The skill will write the chosen wallet path into a local .env and persist strategy files, increasing persistence of that information on disk.
ℹ Persistence & Privilege
always is false and the skill is user-invocable; model invocation is enabled (default). The skill persists a .env file and strategy files under its folder and spawns child processes to execute orders. While it does not request system-wide privileges or modify other skills, its ability to autonomously place orders (realtime autotrade) combined with wallet access is a significant operational privilege — use caution and prefer devnet/localnet or dry-run when testing.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install easyclaw
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /easyclaw 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.0.2
Version 0.1.0 of easyclaw-skill - Added `.env.example` file providing sample environment variable keys for required configuration. - Updated skill metadata with version, homepage, and detailed environment/bin/config requirements. - Expanded documentation to clarify wallet, RPC, and backend credential sources, as well as local file-write behavior. - No changes to command interface or user workflows. - Setup and safety instructions remain unchanged.
v0.0.1
Initial release of easyclaw-skill – a self-contained user DEX toolkit for EasyClaw. - Enables order submission, balance and open-order checks, and backend queries via local scripts. - Provides realtime websocket monitoring and signal-driven auto order execution. - Supports guided onboarding and strategy capture. - All commands accessible through a single `dex-agent.sh` interface. - Designed for user workflows only; does not include admin or keeper operations. - Includes scripts for balance, order, backend API, websocket, and onboarding functions with local environment safety guidelines.
元数据
Slug easyclaw
版本 0.0.2
许可证 —
累计安装 2
当前安装数 2
历史版本数 2
常见问题

easyclaw 是什么？

Run user-facing EasyClaw DEX actions from a self-contained skill folder. Use when an agent needs to submit user orders or check wallet/margin/order balances... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 514 次。

如何安装 easyclaw？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install easyclaw」即可一键安装，无需额外配置。

easyclaw 是免费的吗？

是的，easyclaw 完全免费（开源免费），可自由下载、安装和使用。

easyclaw 支持哪些平台？

easyclaw 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 easyclaw？

由 ColdBell（@ice-coldbell）开发并维护，当前版本 v0.0.2。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论