Langfuse — official skill for LLM observability, evals and prompt management
Docs-first agent workflows for Langfuse: instrumentation, datasets, experiments, evaluations, prompt migration, user feedback, CI/CD gates — via CLI and live docs
- What
- Docs-first agent workflows for Langfuse: instrumentation, datasets, experiments, evaluations, prompt migration, user feedback, CI/CD gates — via CLI and live docs
- Cost
- Free
- Needs
- a Langfuse project with API keys (Langfuse Cloud has a free tier at langfuse.com/cloud, or self-host) — save LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY in the secure vault, never paste them into chat; the langfuse-cli runs via npx (no install required)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — the official @langfuse skill for agents working with Langfuse LLM observability. Its core principles: never implement from memory — always fetch current docs first (Langfuse ships fast), use the `langfuse-cli` for querying and modifying data, pin exact SDK versions in plans, and never guess at UI labels when guiding users through the interface. The skill routes each use case to a dedicated reference: instrumenting applications, building evaluation datasets, migrating prompts from codebases, prompt engineering, setting up evals and LLM-as-a-Judge calibration, error analysis, user-feedback capture, CI/CD experiment gates, and v4 project migration — plus three ways to read the docs live (llms.txt index, per-page markdown fetch, doc/issue search API). It also defines a feedback path so users can report when the skill itself is wrong. MIT-licensed. Honest caveats: you need a Langfuse project and API keys (Langfuse Cloud offers a free tier — save keys in the vault, never paste them into chat; self-hosting is also possible); distinct from the community `bluman1-langfuse` connector already listed — that one is a lean MCP-style connector for browsing traces and scoring, this is the vendor's full engineering playbook; docs-first means real network calls to langfuse.com every run. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: a Langfuse project with API keys (Langfuse Cloud has a free tier at langfuse.com/cloud, or self-host) — save LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY in the secure vault, never paste them into chat; the langfuse-cli runs via npx (no install required) Install "Langfuse — official skill for LLM observability, evals and prompt management" for me. It gives my agent @langfuse's official playbook: docs-first workflows for instrumenting apps, creating datasets, running experiments, evaluating, managing prompts, capturing user feedback, CI/CD experiment gates and v4 migration — via langfuse-cli data access and live documentation (llms.txt, per-page markdown, doc/issue search). MIT-licensed. Note: the community bluman1-langfuse connector (already listed on Skill Harbor) is a leaner alternative for simple trace browsing. Repository: https://github.com/langfuse/skills/blob/main/skills/langfuse/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "langfuse". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. create a Langfuse project and save the API keys in the vault). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.