github.com/langfuse/langfuse
| Skill | Added | Review |
|---|---|---|
add-model-price .agents/skills/add-model-price/SKILL.md Use when editing worker/src/constants/default-model-prices.json, packages/shared/src/server/llm/types.ts, pricing tiers, tokenizer IDs, or matchPattern regexes for OpenAI, Anthropic, Bedrock, Vertex, Azure, or Gemini model pricing. | 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
add-to-dependabot-csv .agents/skills/add-to-dependabot-csv/SKILL.md Append GitHub Dependabot or Snyk/code-scanning alerts to an existing vulnerability CSV after verifying their API metadata. Use for "add to Dependabot CSV" or "dismissed it, add it to the list". | 68 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 47a7034 | |
agent-setup-maintenance .agents/skills/agent-setup-maintenance/SKILL.md Shared workflow for editing Langfuse's repo-owned agent setup under `.agents/`. Use when changing AGENTS files, shared skills, `.agents/config.json`, generated shim behavior, provider discovery paths, or install-time agent sync. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
analyze-cloud-costs .agents/skills/analyze-cloud-costs/SKILL.md Analyze Langfuse Cloud infrastructure cost structure using Metabase cost marts. Use when asked about cloud spend, AWS versus ClickHouse cost splits, cost drivers by provider/service/usage type/account, daily cost per tracing event, infra cost dashboards, or cost regressions visible in Metabase. | 73 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
backend-dev-guidelines .agents/skills/backend-dev-guidelines/SKILL.md Build or review Langfuse backend code. Use for tRPC routers, public REST APIs, BullMQ processors, services, middleware, Prisma or ClickHouse access, OpenTelemetry, Zod, environment configuration, or backend tests. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
changelog-writing .agents/skills/changelog-writing/SKILL.md 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 draft is needed. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
clickhouse-best-practices .agents/skills/clickhouse-best-practices/SKILL.md MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses. | 55 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
code-review .agents/skills/code-review/SKILL.md Review Langfuse code changes for correctness, regressions, and best practices. | 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
create-repo-agent .agents/skills/create-repo-agent/SKILL.md Design, implement, review, or harden Langfuse repo-owned autonomous agents. Use for LLM-powered GitHub Actions, scheduled or dispatched agents, agent-created PRs, prompts, allowlists, tokens, untrusted content, or self-updating instructions. | 73 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 47a7034 | |
cursor-agents-workflow .agents/skills/cursor-agents-workflow/SKILL.md Human handoff, Linear branch names, reviewable (non-draft) PRs, the `cursor` GitHub label, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on the GitHub PR, and review-doubt notes for Cursor agents. Use when a Cursor Cloud or Cursor desktop agent implements a Linear issue, opens a GitHub PR, asks a human to test, posts screenshots or videos, or handles Claude, Greptile, or Codex code-review comments. | 74 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 47a7034 | |
datadog-query-recipes .agents/skills/datadog-query-recipes/SKILL.md Research Langfuse production telemetry with reusable Datadog queries. Use for tenant or project activity, API usage, queue behavior, spans, logs, metrics, or ad hoc measurements across production regions; pair with debug-issue-with-datadog for root-cause analysis. | 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
debug-issue-with-datadog .agents/skills/debug-issue-with-datadog/SKILL.md Establish root cause by combining Datadog telemetry with the Langfuse repo. Use when investigating or triaging a user report, Linear or GitHub issue, incident, or pasted production error. | 66 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 47a7034 | |
frontend-browser-review .agents/skills/frontend-browser-review/SKILL.md Shared workflow for browser-based review of user-visible frontend changes in Langfuse. Use when a change affects UI behavior, layout, styling, navigation, or browser-visible regressions and should be checked with available browser automation before signoff. | 64 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 47a7034 | |
frontend-large-feature-architecture .agents/skills/frontend-large-feature-architecture/SKILL.md Architect large or state-heavy Langfuse frontend features. Use for virtualized lists, large tables, controllers, Zustand stores, row selection, high-frequency state, rendering performance, or before adding useEffect, useMemo, useCallback, or form defaults derived from loaded data. | 66 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
git-workflow .agents/skills/git-workflow/SKILL.md Langfuse repo Git, GitHub, commit, branch, pull request, issue search, release, and production-promotion workflow. Use when staging, committing, pushing, opening PRs, choosing a Linear git branch name, handling Claude, Greptile, or Codex review comments, searching GitHub issues, or changing release/promotion behavior. | 64 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 47a7034 | |
grill-me .agents/skills/grill-me/SKILL.md Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me". | 67 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
housekeeping .agents/skills/housekeeping/SKILL.md 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. | 66 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 47a7034 | |
illustrations .agents/skills/illustrations/SKILL.md Draw, compose or change a Langfuse illustration, either an empty-state drawing (`EmptyState.Illustration`, `SpotIllustration`) or a product scene (`LangfuseIllustration`), in the house isometric style with its motion, accessibility and performance contract. Use when adding a drawing for a new area or moment, building a scene from engine parts, retiming how one moves, or reviewing one. | 75 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
incident-alert-tickets .agents/skills/incident-alert-tickets/SKILL.md 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 incident, or on-call page to find or record root causes. | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 | |
infra-scaling .agents/skills/infra-scaling/SKILL.md Tune and review Langfuse autoscaling for web, web-iso, and web-ingestion. Use for Terraform scale settings, RPM targets, scaling bounds, task counts, cost/performance tradeoffs, or Datadog evidence in the infrastructure repo. | 65 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 47a7034 |