| 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.
npx skills add https://github.com/langfuse/langfuse --skill agent-setup-maintenance
Use this skill when changing the shared agent setup for the repository.
../../README.md for the shared config and shim model.../../AGENTS.md for repo-level expectations.../skill-creator/SKILL.md, then apply the
repo-specific checks in this skill.
../../../scripts/agents/sync-agent-shims.mjsbefore changing generated outputs or provider discovery behavior.
../../../scripts/postinstall.shand ../../../package.json when changing install-time
sync behavior.
.agents/, not generated provider outputs.AGENTS.md and CLAUDE.md as discovery symlinks; do not turnthem back into manually maintained copies.
.claude/, .cursor/, .codex/,.vscode/, and .mcp.json as generated discovery surfaces unless the tool
requires a truly tool-specific feature.
AGENTS.md concise. Move detailed or conditional workflows intoshared skills or package AGENTS.md files.
repo convention, recurring pitfall, reusable workflow, or verification
pattern, update the smallest relevant AGENTS.md or shared skill.
SKILL.md as the entrypoint; donot add skill-by-skill links to root AGENTS.md.
README.md andcontributor-facing docs in the same PR.
pnpm install runs in environments that may not contain the full repo sourcetree.
postinstallbefore scripts/ and .agents/ are available in the image.
cleanly when the required repo-owned files are not present.
Run after changing shared agent setup:
pnpm run agents:syncpnpm run agents:checkRun additional verification when relevant:
pnpm run postinstall when install-time behavior changesa fixed discovery path or feature that cannot be expressed through the shared
setup model.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.
Convert abstract edge concepts into strategy draft variants and optional exportable ticket YAMLs for edge-candidate-agent export/validation.
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
Analyze the protocol layer between agent harness and LLM model. Use when (1) understanding message wire formats and API contracts, (2) examining tool call encoding/decoding mechanisms, (3) evaluating streaming protocols and partial response handling, (4) identifying agentic chat primitives (system prompts, scratchpads, interrupts), (5) comparing multi-provider abstraction strategies, or (6) understanding how frameworks translate between native LLM APIs and internal representations.
Translate SKILL.md and README.md files into multiple languages for sharing skills internationally
>- Summarizes Google Cloud Data Lineage graphs to help users debug data quality issues and understand data provenance for BQ/GCS. Use when summarizing upstream and downstream data flows, and presenting complex lineage data as an intuitive Markdown report. Don't use for generic BigQuery queries, editing lineage relationships, or downstream deprecation. Don't use for downstream blast-radius impact analysis (use datalineage-bigquery-asset-impact-analysis skill instead).
Audit experiment integrity before claiming results. Uses fresh-agent GPT-5.6-Sol review (same-family provisional in the base Codex mirror) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says \"审计实验\", \"check experiment integrity\", \"audit results\", \"实验诚实度\", or after experiments complete before writing claims.
Take langfuse/agent-setup-maintenance from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npm.
Without those the skill loads but fails at the first command.