Essential LibreChat admin skills: YAML config, agents, troubleshooting
Use when creating LibreChat agents, writing agent system prompts, configuring agent capabilities (file search, code interpreter, tools, artifacts), managing agent sharing/permissions, or debugging agent behavior. Also use for agent-based access control patterns.
Use when configuring LibreChat, editing librechat.yaml, adding endpoints, setting up model providers, configuring modelSpecs, or adjusting interface settings. Also use when asked about LibreChat configuration options, YAML structure, or endpoint setup.
Use when LibreChat has errors, containers won't start, API calls fail, file uploads break, models return errors, or something isn't working as expected. Also use for checking service health, reading logs, and diagnosing performance issues.
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-librechat
Then 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:
"Help me add a custom endpoint for Mistral to my librechat.yaml" → activates the config skill
"I'm getting a 400 error when uploading files to an agent" → activates the troubleshooting skill
"Set up an agent with RAG for student document queries" → activates the rag skill
"Configure SAML authentication with our identity provider" → activates the auth skill
"Lock down the interface so students can only use shared agents" → 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.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub bethanychamberlain/claude-skills-librechat --plugin librechat-coreLibreChat access control, authentication, and user management
LibreChat MCP server configuration and integration
LibreChat deployment, monitoring, infrastructure, and upgrades
LibreChat RAG, file handling, and tool configuration
Flagship+ skill pack for OpenRouter - 30 skills for multi-model routing, fallbacks, and LLM gateway mastery
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
Intelligent OpenClaw (formerly ClawdBot) installation, configuration, and management assistant. Guides users through fresh installs, 23+ channel configurations (Slack, WhatsApp, Telegram, Discord, BlueBubbles, Signal, Google Chat, Teams, Matrix, Feishu/Lark, LINE, and more), troubleshooting, security hardening, tools profiles, SecretRef secrets management, PDF tool, Docker/K8s health probes, and multi-provider model setup. If you can use Claude Code, you can use OpenClaw.
TrueFoundry AI Gateway plugin — onboarding, model routing, MCP servers, prompts, Skills Registry workflows, observability, guardrails, and codebase migration. Works across Claude Code, Codex, and Cursor.
LiveKit Agents SDK skills for building voice AI agents with CLI-based workflow, supporting both Cloud and self-hosted deployments.
Spawn any third-party LLM provider with an Anthropic-compatible API (e.g. DeepSeek, GLM, Kimi, Qwen, MiniMax) as real Claude Code agent-team teammates or one-shot subagents — driven exactly like native teammates. Your main session's own auth is untouched (OAuth subscription or API key, either works); provider workers bill the provider API key via apiKeyHelper (the key never enters env/argv/history). Requires the `cc-fleet` binary on PATH, installed separately.