production-python-ai
100 / 100 · Low risk
Fine to try.
Production-grade Python and AI engineering standards. Use for ANY Python work — FastAPI services, LangChain/LangGraph agents, RAG pipelines, LLM API integrations, document processing, or data scripts — whether writing new code, reviewing, refactoring, or debugging. Enforces typed Pydantic boundaries, structured errors and logging, LLM call timeouts/retries/output validation, secret management, async correctness, and tested code.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Other copies in this repository
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'production-python-ai' ] || [ -L ~/.agents/skills/'production-python-ai' ]; then echo 'A skill folder named production-python-ai already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/skillmds/skillmd' "$d" && git -C "$d" checkout --quiet '4467dd0debe8f189ba78142ee57ec42aea84e623' -- 'plugins/secure-code-review-pipeline/skills/ai-engineering-standards' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/secure-code-review-pipeline/skills/ai-engineering-standards' ~/.agents/skills/'production-python-ai' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'production-python-ai' ~/.claude/skills/'production-python-ai' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/skillmds/skillmd/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-09 | 4467dd0 | 100 |
| 2026-11-07 | 1b0ba86 | 100 |