← 返回 Skills 市场
434
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install aelf-skills
功能描述
Discovery, download, and configuration hub for the entire aelf agent skill ecosystem. Use when the user wants to: (1) explore or list available aelf skills,...
使用说明 (SKILL.md)
aelf Skills Hub
One-stop meta-skill for discovering, downloading, configuring, and routing all aelf ecosystem skills.
Available Skills
Read skills-catalog.json for the full machine-readable registry. Current skills:
| ID | Domain |
|---|---|
portkey-ca-agent-skills |
CA wallet: registration, auth, guardian, transfer |
portkey-eoa-agent-skills |
EOA wallet: create, import, assets, transfer |
aelf-node-skill |
Node: chain status, block, tx, contract view/send |
aelfscan-skill |
Explorer: address, token, NFT, statistics analytics |
awaken-agent-skills |
DEX: quote, swap, liquidity, K-line |
eforest-agent-skills |
NFT marketplace: symbol, collection, listing, trade |
tomorrowdao-agent-skills |
Governance: DAO, proposals, BP election, resources |
Workflow
1. Route user intent
Read docs/SKILL_ROUTING_MATRIX.md to map intent → skill.
Key rules:
- Wallet: default EOA; switch to CA on guardian/register/recover/CA-hash signals.
- Chain data:
aelf-node-skillfor raw node interaction;aelfscan-skillfor aggregated analytics. - DEX/NFT: domain skill handles logic; wallet skill provides signing identity.
- Ambiguous: return Recommended / Alternative / Reason.
2. Bootstrap the skill
./bootstrap.sh --only \x3Cskill-id>
Options: --source auto|npm|github|local, --skip-install, --skip-health, --dest \x3Cdir>.
3. Configure for client
After bootstrap, run setup inside the downloaded skill directory:
cd downloaded-skills/\x3Cskill-id>
bun run setup openclaw # for OpenClaw
bun run setup cursor # for Cursor
bun run setup claude # for Claude Desktop
4. Health check
bun run health:check -- --skills-root ./downloaded-skills
Recovery
| Problem | Action |
|---|---|
| Dependency download failed | ./bootstrap.sh --source github --only \x3Cskill-id> |
| skill-id not found | bun run catalog:generate, then retry |
| Health check failed | Follow health:check output, add missing artifacts |
References
- Catalog field semantics: docs/CATALOG_SCHEMA.md
- Intent routing matrix: docs/SKILL_ROUTING_MATRIX.md
- E2E scenarios with recovery: docs/AI_E2E_SCENARIOS.md
- Security audit:
bun run security:audit
安全使用建议
This package is coherent for its stated purpose, but it is a bootstrapper that downloads and installs third-party skill packages and will run their install/setup scripts. Before installing or running it: 1) review skills-catalog.json and the repository URLs for the skills you'll bootstrap; prefer known GitHub repos; 2) run bootstrap in a contained environment (container, VM, or a machine without sensitive credentials) or use --skip-install and inspect code first; 3) consider using --source=github or --source=local to avoid unexpected npm package variants; 4) be aware that 'bun install' and package setup scripts inherit your environment — avoid running on hosts with high-value secrets; 5) if you need higher assurance, inspect individual skill packages (or run security:audit) before allowing automated bootstrap/installation.
功能分析
Type: OpenClaw Skill
Name: aelf-skills
Version: 0.1.0
This skill bundle is designed as a 'hub' to discover, download, and configure other agent skills. Its core functionality involves executing external commands like `npm pack`, `git clone`, and `bun install` based on entries in `skills-catalog.json`. While this is the stated purpose, it introduces significant supply chain vulnerabilities: if `skills-catalog.json` is compromised or if the AI agent is prompted to use a malicious skill ID, arbitrary code could be downloaded and executed from untrusted npm packages or GitHub repositories. Furthermore, `SKILL.md` and `docs/AI_E2E_SCENARIOS.md` contain explicit instructions for the AI agent to execute shell commands (e.g., `./bootstrap.sh --only <skill-id>`, `cd downloaded-skills/<skill-id>; bun run setup openclaw`) with user-controlled input (`<skill-id>`). This creates a prompt injection risk against the AI agent, as an unsanitized `skill-id` could lead to arbitrary command execution by the agent. There is no evidence of intentional malicious behavior (e.g., data exfiltration, backdoors) in the provided code, but the inherent high-risk capabilities and potential for exploitation classify it as suspicious.
能力评估
Purpose & Capability
Name/description match the code and SKILL.md: this package is a catalog/bootstrapping hub. The scripts build a skills catalog, clone/npm-pack skill packages, and run setup/health commands. Required tools (git, npm, bun, tar) are appropriate for those tasks and no unrelated credentials or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to run bootstrap.sh, bun run setup, and health checks. Those steps read skills-catalog.json/workspace.json and then download and operate on third-party skill repos. This stays within the hub's purpose, but the runtime behavior grants the agent the ability to fetch and operate on external code (including running each skill's setup/install scripts).
Install Mechanism
Bootstrap code downloads via npm (npm pack -> tar extract) and via git clone (GitHub). It extracts tarballs to disk and runs 'bun install' inside downloaded skill directories. These are standard mechanisms for a bootstrapper but are a supply-chain risk: tar extraction and executing package install/setup scripts means arbitrary code from npm/github will be written and executed locally.
Credentials
The package declares no required environment variables or credentials. Some utilities (expandPathWithEnv) will expand ${VARS} found in workspace paths and will error if missing; runCommand inherits process.env when spawning installs, so local environment variables could be visible to child processes. No unrelated secret variables are explicitly requested by the skill.
Persistence & Privilege
The skill is not forced-always, is user-invocable, and does not claim to modify other skills' config. It writes downloaded skill files to a destination directory (downloaded-skills), which is expected behavior for a bootstrap tool.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install aelf-skills - 安装完成后，直接呼叫该 Skill 的名称或使用
/aelf-skills触发 - 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
v0.1.0
- Initial release of aelf-skills-hub, a meta-skill for discovery, installation, configuration, and routing of all aelf ecosystem skills.
- Provides a unified catalog for domains including wallets (CA/EOA), DEX, NFT marketplace, explorer, and governance.
- Outlines intent-based skill routing, skill bootstrapping, configuration for various clients, and health-check workflows.
- Includes troubleshooting steps and references for catalog schema, intent routing, and security audit.
元数据
常见问题
@blockchain-forever/aelf-skills 是什么？
Discovery, download, and configuration hub for the entire aelf agent skill ecosystem. Use when the user wants to: (1) explore or list available aelf skills,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 434 次。
如何安装 @blockchain-forever/aelf-skills？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install aelf-skills」即可一键安装，无需额外配置。
@blockchain-forever/aelf-skills 是免费的吗？
是的，@blockchain-forever/aelf-skills 完全免费（开源免费），可自由下载、安装和使用。
@blockchain-forever/aelf-skills 支持哪些平台？
@blockchain-forever/aelf-skills 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 @blockchain-forever/aelf-skills？
由 hzz780（@hzz780）开发并维护，当前版本 v0.1.0。
推荐 Skills