librechat-core — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited librechat-core (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Claude Code skills for LibreChat configuration, deployment, and administration.
This marketplace provides guided workflows that Claude Code can activate when you're working with LibreChat — writing YAML configs, setting up agents, diagnosing errors, managing authentication, and more.
Disclaimer: These skills were built using Claude Code with the skill-creator plugin and Serena MCP server. They have been tested against a single LibreChat v0.8.3 instance running locally. While all 12 skills pass testing, edge cases or version-specific issues may exist. Bug reports and contributions are welcome.
Add the marketplace to Claude Code:
/plugin marketplace add https://github.com/bethanychamberlain/claude-skills-librechatThen install a plugin:
/plugin install librechat-core| Plugin | Skills | Description |
|---|---|---|
librechat-core | config, agents, troubleshooting | YAML configuration, agent setup, debugging |
librechat-data | rag, tools | Document retrieval (RAG), agent tools and capabilities |
librechat-mcp | mcp | Model Context Protocol server integration |
librechat-ops | deployment, infrastructure, monitoring, upgrades | Docker/cloud deployment, databases, logging, version management |
librechat-security | auth, access-control | OAuth2/SAML/LDAP authentication, user restrictions and permissions |
5 plugins, 12 skills, 97 reference files, 11 templates, 2 helper scripts.
Once installed, skills activate naturally during conversation. Examples:
→ activates the config skill
→ activates the troubleshooting skill
→ activates the rag skill
→ activates the auth skill
→ activates the access-control skill
You don't need to name skills explicitly — describe what you're trying to do and Claude Code will use the right skill.
For the best results, fill in librechat-context-template.md and paste its contents at the start of your session (or save it as LIBRECHAT_CONTEXT.md in your project). This tells Claude which version you're running, how it's deployed, what providers are configured, and any constraints it should know about.
See CONTRIBUTING.md for how to add skills, fix docs, or propose a new plugin.
This project was inspired by and built on the framework established by alirezarezvani/claude-skills.
MIT — see LICENSE.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.