← Back to Skills Marketplace
234
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install agentscout
Description
Discover trending AI Agent projects on GitHub, auto-generate Xiaohongshu (Little Red Book) publish-ready content including tutorials, copywriting, and cover...
README (SKILL.md)
AgentScout — GitHub Agent Project Discovery & Content Generation
You are AgentScout, a skill that discovers interesting AI Agent open-source projects on GitHub and automatically generates publish-ready content for Xiaohongshu (Little Red Book / 小红书).
When to activate
Activate when the user asks to:
- Find or discover AI/Agent projects on GitHub
- Generate Xiaohongshu / 小红书 content for a GitHub project
- Score or rank open-source projects
- Create social media content from a GitHub repo
What you do
Run the AgentScout pipeline from {baseDir}:
cd {baseDir} && python3 -m src.pipeline
The pipeline will:
- Search GitHub for trending AI Agent projects (keyword search + org monitoring)
- Score each project with LLM on 4 dimensions: novelty, practicality, content fit, ease of use
- Present Top 3 ranked projects for user selection
- Analyze the selected project in depth (README, code, architecture)
- Generate Xiaohongshu copywriting with smart hashtags
- Create 6-9 cover images (HTML template cards + AI-generated concept art)
Output is saved to {baseDir}/output/{date}_{project_name}/ containing:
analysis.md— structured tutorialpost.md— ready-to-publish Xiaohongshu post with tagsimages/— cover, code cards, step cards, architecture, summary cardmetadata.json— project metadata and scores
Setup
Before first use, ensure dependencies are installed:
cd {baseDir} && pip install -r requirements.txt
And configure .env with at minimum:
GITHUB_TOKEN— GitHub Personal Access TokenLLM_API_KEY— Any OpenAI-compatible LLM API key
Usage Guidance
Things to consider before installing or running AgentScout:
- Expect that README content and code snippets will be sent to the configured LLM endpoint (LLM_BASE_URL). Do not point LLM_BASE_URL to an untrusted service if repository content is sensitive.
- Use least-privilege GitHub tokens (avoid full org/admin scopes). Prefer tokens limited to public repo access if you only need public repos.
- The tool writes outputs to output/ and a local SQLite DB at data/agentscout.db in the repo root; run in a sandbox or isolated directory if you want to limit persistence.
- Optional IMAGE_API_KEY defaults to a third-party endpoint (siliconflow). If you supply an image key, confirm the provider and its privacy policy.
- The README requests pip install -r requirements.txt; review requirements and consider installing in a virtualenv/container. Playwright (optional) will download browser binaries when installed.
- If you are concerned about leaking proprietary code, either restrict the search scope to public repositories, run the code with a dummy/limited LLM endpoint, or audit/modify src/utils/llm_client.py to confirm exactly what gets sent.
- Overall the skill appears internally coherent for its stated purpose; proceed if you are comfortable with the data-sharing implications and have limited token scope and an isolated runtime environment.
Capability Analysis
Type: OpenClaw Skill
Name: agentscout
Version: 1.0.0
The AgentScout skill is designed to discover GitHub projects and generate social media content, but it contains high-risk behaviors and security flaws. Specifically, `src/visual/composer.py` initializes the Jinja2 environment with `autoescape=False`, which renders untrusted data (GitHub project names and descriptions) into HTML templates without sanitization. This creates a significant XSS/RCE vulnerability within the headless browser environment used by `html2image` and `playwright` (in `src/visual/screenshot.py`). While these capabilities are plausibly needed for the stated purpose, the lack of input sanitization for external data fetched from GitHub makes the bundle risky.
Capability Assessment
Purpose & Capability
Name/description match the implementation: the package contains GitHub searchers, a scorer, analyzers, content generators, and image/card generators. Required binaries (python3) and env vars (GITHUB_TOKEN, LLM_API_KEY) are appropriate and necessary for searching GitHub and calling an LLM. Optional IMAGE_API_KEY aligns with AI image generation.
Instruction Scope
The runtime instructions (and code) explicitly fetch README, file trees, and key source files (up to several files and snippets) and pass those to the configured LLM for scoring and tutorial generation. This behavior is consistent with the purpose but means repository contents (including possibly sensitive code) will be transmitted to the LLM endpoint you configure.
Install Mechanism
No formal install spec is provided; the README and SKILL.md ask you to pip install -r requirements.txt. The requirements are from standard PyPI packages (PyGithub, openai, playwright, etc.). Playwright install (optional) will download browser binaries, which is typical but worth noting.
Credentials
Only GITHUB_TOKEN and LLM_API_KEY are required; both are proportional to the functionality. IMAGE_API_KEY is optional. There are no unrelated secrets or extraneous credential requests in requires.env. You should still scope tokens minimally (e.g., public_repo or least privilege) and avoid using org-wide or highly privileged tokens.
Persistence & Privilege
Skill is not always-enabled and does not request elevated platform privileges. It writes an SQLite DB under the project data/ path and writes outputs under output/, which is reasonable for local use. It does not modify other skills or system-wide agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agentscout - After installation, invoke the skill by name or use
/agentscout - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is AgentScout?
Discover trending AI Agent projects on GitHub, auto-generate Xiaohongshu (Little Red Book) publish-ready content including tutorials, copywriting, and cover... It is an AI Agent Skill for Claude Code / OpenClaw, with 234 downloads so far.
How do I install AgentScout?
Run "/install agentscout" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is AgentScout free?
Yes, AgentScout is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does AgentScout support?
AgentScout is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created AgentScout?
It is built and maintained by auxito (@auxito); the current version is v1.0.0.
More Skills