智能助手安装器

howtoletmyagent_installer

by bullkis1

Install companion OpenClaw skills from howtoletmyagent.xyz article URLs or skill manifests.

4.4k其他未扫描2026年4月20日

安装

claude skill add --url https://github.com/openclaw/skills

文档

Howtoletmyagent Installer

Use this skill when the user wants to install or learn a companion skill from a Howtoletmyagent article.

Accepted inputs:

Required workflow:

  1. Verify that the source URL belongs to https://howtoletmyagent.xyz or another explicitly approved preview host.
  2. Resolve the manifest URL:
    • article URL -> /api/skills/<slug>
    • manifest URL -> use it directly
  3. Fetch the manifest JSON.
  4. Explain what will be installed and ask for approval before writing files or running install commands.
  5. If the manifest says the source is clawhub, prefer the provided install command.
  6. If a ClawHub install is unavailable or fails, create a local workspace skill folder and write the manifest files exactly as provided.
  7. After install, tell the user to start a new session with /new or restart the gateway so OpenClaw reloads the skill.

Safety rules:

  • Only trust manifests from https://howtoletmyagent.xyz unless the user explicitly approves another domain.
  • Never execute arbitrary code from the manifest. This manifest is for skill files, not shell scripts.
  • Show the target install path before writing files.
  • If a manifest looks malformed or unsafe, stop and explain the issue instead of guessing.

Implementation notes:

  • Prefer using browser or web-fetch tools to read the manifest.
  • If a CLI install is approved, use the exact command supplied by the manifest.
  • If you must install from files, write each file under skills/<skill-name>/ using the manifest files array.

Success condition:

  • The requested companion skill is installed.
  • The user gets the exact prompt they can use next to trigger it.

相关 Skills

Claude API

by anthropic

热门

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.

其他
安全124.4k

并行代理

by axelhu

热门

Use when facing 2 or more independent tasks that can be worked on without shared state - dispatches parallel subagents using sessions_spawn for concurrent investigation and execution, adapted for OpenClaw

其他
未扫描4.4k

高光制作器

by bwbernardweston18

热门

>

其他
未扫描4.4k

评论