← All skills

inference-optimization-safety-precheck

95 / 100 · Low risk

Fine to try.

By cemini23/Cybersecurity-wiki (GitHub) · other · 12 stars · scanned at commit 5ea7630

K405 checklist before adding an inference optimisation. A draft model enters the token path and the TCB. Re-run the safety eval, not just the quality eval.

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'inference-optimization-safety-precheck' ] || [ -L ~/.agents/skills/'inference-optimization-safety-precheck' ]; then echo 'A skill folder named inference-optimization-safety-precheck already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/cemini23/Cybersecurity-wiki' "$d" && git -C "$d" checkout --quiet '5ea7630c92d7788635bddb1c35b4f0d45e9d7e71' -- '.cursor/skills/inference-optimization-safety-precheck' && mkdir -p ~/.agents/skills && cp -R "$d"/'.cursor/skills/inference-optimization-safety-precheck' ~/.agents/skills/'inference-optimization-safety-precheck' && 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/'inference-optimization-safety-precheck' ~/.claude/skills/'inference-optimization-safety-precheck' (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

The badge for cemini23/Cybersecurity-wiki shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/cemini23/Cybersecurity-wiki.svg)](https://zalavijaysinh.github.io/skilltrust/repos/cemini23/Cybersecurity-wiki/)

Score history