searching-mlflow-docs — Claude Code skill: what it does and install
Fetches official MLflow GenAI documentation and verbatim code snippets directly through the llms.txt index.
npx skills add mlflow/skills --skill searching-mlflow-docs -a claude-codeWhat searching-mlflow-docs does
The skill fetches official MLflow guides for generative AI workflows. It reads the llms.txt index first to locate the target page. After identifying the file, it pulls raw Markdown rather than rendered HTML. Code blocks are returned verbatim without summarization.
Web search is forbidden to prevent scraping outdated third-party tutorials. Requests always target the latest branch. This prevents accidental reliance on deprecated syntax.
The underlying index covers only GenAI and LLM tooling like LangChain, LangGraph, and OpenAI. If you need classic ML experiment tracking, documentation paths differ and this skill will miss them.
What it helps with
- retrieve official MLflow code examples without summarization
- find current MLflow integration guides for LangChain and LangGraph
- inspect MLflow tracing APIs for LLM applications
- prevent outdated syntax from generic web search results
Example prompts for the agent
- Find MLflow documentation for LangChain integration.
- Show the MLflow tracing API for OpenAI.
- How do I use MLflow with LangGraph?
How to install searching-mlflow-docs
1Skills CLI (Vercel)
npx skills add mlflow/skills --skill searching-mlflow-docs -a claude-code2Manually: put the files in place
~/.claude/skills/searching-mlflow-docs/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/searching-mlflow-docs/
1Skills CLI (Vercel)
npx skills add mlflow/skills --skill searching-mlflow-docs -a codex2Manually: put the files in place
.agents/skills/searching-mlflow-docs/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add mlflow/skills --skill searching-mlflow-docs -a cursor2Manually: put the files in place
.cursor/skills/searching-mlflow-docs/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install mlflow/skills searching-mlflow-docs2Manually: put the files in place
.github/skills/searching-mlflow-docs/SKILL.md1Skills CLI (Vercel)
npx skills add mlflow/skills --skill searching-mlflow-docs -a gemini-cli2Platform CLI
gemini skills install https://github.com/mlflow/skills --path searching-mlflow-docsManually: put the files in place
.devin/skills/searching-mlflow-docs/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add mlflow/skills --skill searching-mlflow-docs -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about searching-mlflow-docs
How to install searching-mlflow-docs in Claude Code?
Run npx skills add mlflow/skills --skill searching-mlflow-docs -a claude-code. The command registers the skill for your Claude Code environment.
What does searching-mlflow-docs do?
It queries the official llms.txt index to pinpoint relevant documentation pages and retrieves raw Markdown code examples.
Does searching-mlflow-docs cover classic ML tracking?
The llms.txt index focuses specifically on LLM and GenAI topics. Paths for classic experiment tracking features may differ.
Source text
SKILL.md · Apache-2.0
--- name: searching-mlflow-docs description: Searches and retrieves MLflow documentation from the official docs site. Use when the user asks about MLflow features, APIs, integrations (LangGraph, LangChain, OpenAI, etc.), tracing, tracking, or requests to look up MLflow documentation. Triggers on "how do I use MLflow with X", "find MLflow docs for Y", "MLflow API for Z". --- # MLflow Documentation Search ## Workflow 1. Fetch `https://mlflow.org/docs/latest/llms.txt` to find relevant page paths 2. Fetch the `.md` file at the identified path 3. Present results with verbatim code examples ## Step 1: Fetch llms.txt Index ``` WebFetch( url: "https://mlflow.org/docs/latest/llms.txt", prompt: "Find links or references to [TOPIC]. List all relevant URLs." ) ``` ## Step 2: Fetch Target Documentation Use the path from Step 1, always with `.md` extension: ``` WebFetch( url: "https://mlflow.org/docs/latest/[path].md", prompt: "Return all code blocks verbatim. Do not summarize." ) ``` ## Anti-Patterns **Do not use `.html` files** — Fetch `.md` source files only. **Do not use WebSearch** — Always start from llms.txt; web search returns outdated or third-party content. **Do not use vague prompts** — "Extract complete documentation" allows summarization. Use "Return all code blocks verbatim. Do not summarize." **Do not use versioned paths** — Always use `/docs/latest/`, never `/docs/3.8/` or other versions unless the user explicitly requests a specific version. **Do not guess URLs** — Always verify paths exist in llms.txt before fetching. Never construct documentation paths from assumptions. **Do not follow external links** — Stay within mlflow.org/docs. Do not follow links to GitHub, PyPI, or third-party sites. **Do not mix sources** — Use only MLflow docs. Do not combine with LangChain docs, OpenAI docs, or other external documentation. **Do not use llms.txt for non-GenAI topics** — The llms.txt index covers LLM/GenAI documentation only. For classic ML tracking features, paths may differ.
© mlflow · Apache-2.0 · mlflow/skills
