Agent Skills by SNT Go
Showing 67 vetted skills indexed across 2 GitHub repositories.
multi-agent-autonomous-loop-pattern
Orchestrate five parallel agents with ScheduleWakeup and atomic git commit safeguards.
multi-llm-routing-pattern
Route LLM requests across multiple backends via an OpenAI-compatible gateway.
gem-llm-gateway-debug
Diagnose GEM-LLM Gateway authentication, rate limiting, and proxy routing failures.
api-contract-testing-pattern
Validate FastAPI routes, response schemas, and status codes against a committed OpenAPI snapshot.
deployment-checklist
Enforce production deployment readiness with a 56-item checklist across seven areas.
book-builder
Convert Markdown design documents into bilingual MD, DOCX, and PDF books.
observability-bundle
Integrate metrics, logs, traces, and error tracking for FastAPI services.
gem-llm-troubleshooting
Map GIL-LLM production symptoms to 13 known failure cases and apply fixes.
gem-llm-admin-cli
Manage GEM-LLM user accounts and API key issuance via CLI.
cloudflare-tunnel-ssh-access-pattern
Route external SSH to Kubernetes pods through Cloudflare Tunnel and cloudflared access ssh.
coverage-instrumentation-pattern
Fix Python 3.12+ coverage by switching pytest to the sysmon backend.
developer-onboarding-doc-pattern
Generate a 4-tier onboarding documentation bundle with a 5-minute quickstart and verification command.
env-isolation-pattern
Isolate production environment variables from pytest and alembic subprocesses.
fastapi-gateway-pattern
Implement a FastAPI OpenAI-compatible gateway with authentication, quotas, and SSE proxying.
api-key-lifecycle-pattern
Implement API key issuance, verification, and revocation with salted hashing.
pytest-fastapi-pattern
Configure deterministic FastAPI pytest integration tests with httpx ASGITransport and respx mocking.
subagent-prompt-engineering-pattern
Enforce a strict subagent prompt template for parallel Claude Code Agent dispatches.
gem-llm-cloudflare-tunnel
Restore external GEM-LLM access via Cloudflare Tunnel with llm.pamout.com routing.
gem-llm-deploy-vllm
Manages lifecycle of GEM-LLM vLLM servers including health checks via /v1/models endpoints.
prometheus-fastapi-metrics
Add Prometheus custom metrics to FastAPI applications with a /metrics endpoint.
sqlite-wal-safe-ops
Backs up SQLite WAL-format databases by checkpointing cache and copying all three files with verification.
gem-llm-supervisor
Start, stop, restart, and health-check vLLM instances with Gateway and Admin UI.
gem-llm-load-test
Generate concurrent load tests for GEM-LLM and collect latency and throughput metrics.
korean-tech-blog-authoring
Produce Korean technical blog posts with consistent tone and preserved English identifiers.