agent-setup-maintenance

작성자: langfuse

이 스킬은 저장소의 공유 에이전트 설정을 변경할 때 사용하세요.

npx skills add https://github.com/langfuse/langfuse --skill agent-setup-maintenance

Agent Setup Maintenance

Use this skill when changing the shared agent setup for the repository.

Start Here

Workflow

  1. Edit the canonical files under .agents/, not generated provider outputs.
  2. Keep root AGENTS.md as a symlink to .agents/AGENTS.md. Write folder instructions in AGENTS.md directly; do not generate CLAUDE.md companions.
  3. Treat tool-specific directories such as .claude/, .cursor/, .codex/, .vscode/, and .mcp.json as generated discovery surfaces unless the tool requires a truly tool-specific feature.
  4. Keep root AGENTS.md concise. Move detailed or conditional workflows into shared skills or package AGENTS.md files.
  5. Treat developer feedback as a learning loop: when a task reveals a durable repo convention, recurring pitfall, reusable workflow, or verification pattern, update the smallest relevant AGENTS.md or shared skill.
  6. When adding or changing a shared skill, keep SKILL.md as the entrypoint; do not add skill-by-skill links to root AGENTS.md.
  7. When shared setup behavior changes materially, update README.md and contributor-facing docs in the same PR.

Docker / Install-Time Constraint

  • pnpm install runs in environments that may not contain the full repo source tree.
  • In Docker builds, Turbo's pruned install stage can run root postinstall before scripts/ and .agents/ are available in the image.
  • Keep install-time agent setup logic robust in those pruned contexts: skip cleanly when the required repo-owned files are not present.

Required Verification

Run after changing shared agent setup:

  • pnpm run agents:sync
  • pnpm run agents:check
  • node --test scripts/agents/sync-agent-shims.test.mjs when sync behavior changes

Run additional verification when relevant:

  • pnpm run postinstall when install-time behavior changes
  • targeted tests for any scripts you changed

Design Rules

  • Prefer one repo-owned source of truth over duplicated provider-specific files.
  • Keep shared setup tool-neutral where possible.
  • Only keep provider-specific files in source control when the provider requires a fixed discovery path or feature that cannot be expressed through the shared setup model.

langfuse의 다른 스킬

frontend-browser-review
langfuse
이 스킬은 변경 사항이 브라우저에서 사용자가 보거나 수행하는 작업에 영향을 미칠 때 사용하세요.
frontend-large-feature-architecture
langfuse
대규모 Langfuse 프론트엔드 기능, 가상화된 목록, 대형 테이블, 컨트롤러 컴포넌트, 로컬 기능을 구축, 변경 또는 리팩터링할 때 사용합니다.
skill-developer
langfuse
Anthropic 모범 사례에 따라 Claude Code 스킬을 생성하고 관리합니다. 새 스킬을 만들거나, skill-rules.json을 수정하거나, 트리거를 이해할 때 사용합니다…
langfuse-prompt-migration
langfuse
하드코딩된 프롬프트를 Langfuse로 마이그레이션하여 버전 관리와 배포 없는 반복을 가능하게 합니다. 사용자가 프롬프트를 외부화하거나, 프롬프트를 Langfuse로 이동하려는 경우 사용합니다.
incident-alert-tickets
langfuse
Read and, after human approval, update the Linear `incident-alert` knowledge base. Use before and after investigating a named Datadog monitor,…
refactor-react-effects
langfuse
Langfuse 프론트엔드 코드에서 피할 수 있는 React useEffect 사용을 리팩터링합니다. 효과를 추가, 검토 또는 제거할 때; 폼이나 로컬 UI 상태를 초기화할 때 사용합니다…
sentry-instrumentation
langfuse
Decide whether and how errors report to Sentry. Use when touching capture or error-handling paths in `web/**`, triaging Sentry noise, or changing Sentry…
posthog-instrumentation
langfuse
Product analytics with posthog. Use when adding a meaningful user action or feature in `web/**`, touching PostHog capture code, or answering product-usage…