@skills · Owner
Agent skills by langfuse
53 skills indexed from github.com/langfuse. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.
- .agents · Collection · 32,652 stars
- .agents · Collection · 32,652 stars
- add-model-price · Skill · 32,652 stars
Use when editing worker/src/constants/default-model-prices.json, packages/shared/src/server/llm/types.ts, pricing tiers, tokenizer IDs, or matchPattern reg
- agent-setup-maintenance · Skill · 32,652 stars
Shared workflow for editing Langfuse's repo-owned agent setup under `.agents/`. Use when changing AGENTS files, shared skills, `.agents/config.json`, gener
- analyze-cloud-costs · Skill · 32,652 stars
Analyze Langfuse Cloud infrastructure cost structure using Metabase cost marts. Use when asked about cloud spend, AWS versus ClickHouse cost splits, cost d
- backend-dev-guidelines · Skill · 32,652 stars
Build or review Langfuse backend code. Use for tRPC routers, public REST APIs, BullMQ processors, services, middleware, Prisma or ClickHouse access, OpenTe
- changelog-writing · Skill · 32,652 stars
Shared workflow for writing Langfuse changelog entries after a feature is complete. Use when a branch is ready for merge and a changelog entry or changelog
- clickhouse-best-practices · Skill · 32,652 stars
MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always rea
- code-review · Skill · 32,652 stars
Review Langfuse code changes for correctness, regressions, and best practices.
- create-repo-agent · Skill · 32,652 stars
Design, implement, review, or harden Langfuse repo-owned autonomous agents. Use for LLM-powered GitHub Actions, scheduled or dispatched agents, agent-creat
- datadog-query-recipes · Skill · 32,652 stars
Research Langfuse production telemetry with reusable Datadog queries. Use for tenant or project activity, API usage, queue behavior, spans, logs, metrics,
- debug-issue-with-datadog · Skill · 32,652 stars
Establish root cause by combining Datadog telemetry with the Langfuse repo. Use when investigating or triaging a user report, Linear or GitHub issue, incid
- frontend-browser-review · Skill · 32,652 stars
Shared workflow for browser-based review of user-visible frontend changes in Langfuse. Use when a change affects UI behavior, layout, styling, navigation,
- frontend-large-feature-architecture · Skill · 32,652 stars
Architect large or state-heavy Langfuse frontend features. Use for virtualized lists, large tables, controllers, Zustand stores, row selection, high-freque
- git-workflow · Skill · 32,652 stars
Langfuse repo Git, GitHub, commit, branch, pull request, issue search, release, and production-promotion workflow. Use when staging, committing, pushing, o
- housekeeping · Skill · 32,652 stars
Triage an engineer's work queue across Linear, Pylon, and GitHub. Use for assigned, urgent, waiting, or stale issues, support follow-ups, and PR reviews.
- incident-alert-tickets · Skill · 32,652 stars
Read and record root causes in the Linear `incident-alert` knowledge base. Use before and after investigating a named Datadog monitor, incident.io alert or
- infra-scaling · Skill · 32,652 stars
Tune and review Langfuse autoscaling for web, web-iso, and web-ingestion. Use for Terraform scale settings, RPM targets, scaling bounds, task counts, cost/
- langfuse · Collection · 32,652 stars
- langfuse-codebase-navigator · Skill · 32,652 stars
Navigate Langfuse repositories, code areas, and agent skills. Use to locate code, choose the right repo or skill, search across the Langfuse organization,
- langfuse-previews · Skill · 32,652 stars
Use Langfuse's disposable per-PR previews at pr-N.preview.langfuse.com (synthetic data only). Use for preview access, failed deployments, test-data seeding
- linear-bug-triage · Skill · 32,652 stars
Use this skill after a bug or regression candidate has measured evidence to document them within linear.
- pnpm-upgrade-package · Skill · 32,652 stars
Upgrade pnpm workspace dependencies to target/latest versions: direct/transitive bumps, release-age checks, temporary overrides, minimumReleaseAgeExclude,
- posthog-instrumentation · Skill · 32,652 stars
Product analytics with posthog. Use when adding a meaningful user action or feature in `web/**`, touching PostHog capture code, changing session replay or
- react-component-cleaner · Skill · 32,652 stars
Use this skill to clean up a React component. Only use this skill when instructed to do so by the user.
- react-component-guidelines · Skill · 32,652 stars
Guidelines for writing React components. Use this when creating a new react component.
- refactor-react-effects · Skill · 32,652 stars
Refactor avoidable React useEffect usage in Langfuse frontend code. Use when adding, reviewing, or removing effects; initializing forms or local UI state f
- security-review · Skill · 32,652 stars
Review Langfuse changes for SSRF, tenant isolation, secret handling, unsafe redirects or uploads, RBAC drift, and client telemetry privacy. Use when a desi
- seed-test-data · Skill · 32,652 stars
Seed reproducible local Langfuse data in ClickHouse and Postgres. Use for complex traces, long sessions, v3/v4 events, bulk list data, or frontend renderin
- sentry-instrumentation · Skill · 32,652 stars
Decide whether and how errors report to Sentry. Use when touching capture or error-handling paths in `web/**`, triaging Sentry noise, or changing Sentry se
- skill-creator · Skill · 32,652 stars
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's cap
- skills · Collection · 32,652 stars
- skills · Collection · 32,652 stars
- storybook · Skill · 32,652 stars
Use when writing or reviewing Storybook stories (`.stories.tsx`) for React components.
- turborepo · Skill · 32,652 stars
Configure and troubleshoot Turborepo monorepos. Use for turbo.json, task pipelines, dependsOn, caching, filters, affected packages, CI optimization, enviro
- vercel-composition-patterns · Skill · 32,652 stars
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing
- vercel-react-best-practices · Skill · 32,652 stars
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next
- web · Collection · 32,652 stars
- weekly-production-review · Skill · 32,652 stars
Prepare Langfuse weekly production reviews covering failures, fixes, open issues, and tracking gaps. Use for "what broke last week," production bugs, Datad
- .cursor · Collection · 235 stars
- langfuse · Skill · 235 stars
Interact with Langfuse and access its documentation: tracing, monitoring, creating datasets, running experiments, and evaluating AI applications. Use when
- skill-creator · Skill · 235 stars
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's ca
- skills · Collection · 235 stars
- skills · Collection · 235 stars
- skills · Collection · 235 stars
- cursor-agents-workflow · Skill
Human handoff, Linear branch names, reviewable (non-draft) PRs, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on th
- grill-me · Skill
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants
- langfuse-onboarding · Skill
Configure an agent for whoever is using it — outside contributor or Langfuse maintainer, which areas they work on, which integrations are connected — and,
- linear-agent-writes · Skill
The org policy for what an agent may write to Linear, and how it must be marked. Read this before creating a ticket, editing a description, or commenting o
- linear-context-handover · Skill
Use Linear as the org's memory: reconstruct a feature's history before touching it, and leave the reasoning behind finished work in the ticket description
- linear-planning · Skill
Plan a feature in Linear as subtickets that map 1:1 to a chained PR stack, with enough context in each ticket that an agent could implement it from the tic
- linear-work-rhythm · Skill
Answer "what should I do today" for a Langfuse maintainer, from the tracker rather than from memory: which projects you lead, which owe an update before th
- pr-stack-workflow · Skill
Split a large change into a chained stack of small, independently reviewable pull requests, and verify each branch on its own. Use when a change is too lar