← Back to Skills Marketplace
LangSkills Search
by
shatianming5
· GitHub ↗
· v1.0.0
· MIT-0
184
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install langskills-search
Description
Search 119K evidence-backed skills from 95K+ papers & 24K+ tech sources
README (SKILL.md)
LangSkills Search
Search 119,608 evidence-backed skills covering 62K+ research papers and 23K+ coding/tech sources — all offline via FTS5 SQLite.
When to Use
- User asks for best practices, how-tos, or techniques on a technical topic
- You need evidence-backed knowledge (not LLM-generated guesses)
- Research tasks that benefit from academic or real-world source citations
First-Time Setup
pip install langskills-rai
# Install matching bundles for the current project or pick a domain:
langskills-rai bundle-install --auto
Search Command
langskills-rai skill-search "\x3Cquery>" [options]
Parameters
| Flag | Description | Default |
|---|---|---|
--top N |
Number of results | 5 |
--domain \x3Cd> |
Filter by domain | all |
--min-score N |
Minimum quality score (0-5) | 0 |
--content |
Include full skill body | off |
--format markdown |
Output as Markdown | text |
Example
langskills-rai skill-search "CRISPR gene editing" --domain research --top 3 --content --format markdown
Reading Results
Each result includes: title, domain, quality score (0-5), source URL, and optionally the full skill body. Higher scores indicate stronger evidence chains.
Available Domains
linux · web · programming · devtools · security · cloud · data · ml · llm · observability · research-arxiv · research-plos-* · research-elife · research-other
Tips
- Use
--content --format markdownto get copy-paste-ready skill text - Combine
--domainwith--min-score 4.0for high-quality results - Run
bundle-install --autoin a project directory to install only relevant domains
Usage Guidance
This skill is an instructions-only integration that delegates runtime work to a third-party Python package (langskills-rai). Before installing or running it: (1) verify the package and source (PyPI entry and the referenced GitHub repo) to ensure they match and are trustworthy; (2) install inside a virtualenv to limit effects to a contained environment; (3) be aware bundle-install will likely download data files and write them into your project directory — review where it stores bundles and how large they are; (4) inspect the package code (or its repository) if you want to be sure it doesn't perform unexpected network calls or collect unrelated system data. The static scanner had no files to analyze (SKILL.md only), so vetting the external package is the main remaining step.
Capability Analysis
Type: OpenClaw Skill
Name: langskills-search
Version: 1.0.0
The langskills-search skill bundle provides a legitimate interface for searching a database of evidence-backed technical and research skills. It utilizes a Python package (langskills-rai) and a local SQLite database for offline search. The instructions in SKILL.md are consistent with the stated purpose and do not contain any malicious commands, data exfiltration attempts, or harmful prompt injections.
Capability Assessment
Purpose & Capability
Name/description (search an evidence-backed skills DB) align with the instructions: they require python3 and instruct the user to pip install langskills-rai and run a CLI search. The declared GitHub metadata matches the described purpose.
Instruction Scope
SKILL.md only instructs installing a package and running the langskills-rai CLI (skill-search and bundle-install). It does not direct reading unrelated files, accessing extra environment variables, or exfiltrating results to unexpected endpoints. Note: bundle-install may download and write domain bundles to the local project directory (expected behavior for populating an offline DB).
Install Mechanism
The registry contains no automated install spec (lowest-risk). The SKILL.md tells the user to run pip install langskills-rai. Installing a third-party Python package runs arbitrary code from that package and may download additional bundles; this is expected but you should vet the package source (PyPI/GitHub) before installing.
Credentials
No environment variables, credentials, or config paths are requested or required in the SKILL.md. The skill's needs are minimal and proportional to a CLI search tool.
Persistence & Privilege
always:false and no special persistence or cross-skill config modification are requested. The skill does not ask to be force-enabled; agent autonomy defaults remain unchanged.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install langskills-search - After installation, invoke the skill by name or use
/langskills-search - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of langskills-search skill.
- Search 119,608 evidence-backed skills from 95K+ research papers and 24K+ tech sources, all offline using FTS5 SQLite.
- Provides command-line tool langskills-rai skill-search with filtering by domain, quality score, and output format.
- Supports easy setup and selective domain installation with bundle-install.
- Returns results with title, domain, quality score, source URL, and optional full skill body.
- Suitable for finding best practices and how-tos with cited academic or real-world sources.
Metadata
Frequently Asked Questions
What is LangSkills Search?
Search 119K evidence-backed skills from 95K+ papers & 24K+ tech sources. It is an AI Agent Skill for Claude Code / OpenClaw, with 184 downloads so far.
How do I install LangSkills Search?
Run "/install langskills-search" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is LangSkills Search free?
Yes, LangSkills Search is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does LangSkills Search support?
LangSkills Search is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created LangSkills Search?
It is built and maintained by shatianming5 (@shatianming5); the current version is v1.0.0.
More Skills