← All skills

agentsop-regression-gate

100 / 100 · Low risk

Fine to try.

By agentsope/SkillAlchemy (GitHub) · coding · 469 stars · scanned at commit 955562e

Build a held-out eval set, run it on every prompt/model change, and block regressions in CI. An LM change is a code change — gate it with a test suite (eval set + metric + threshold). Cross-framework SOP not surfaced by any single base skill.

Works with any agent that supports SKILL.md skills.

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.

Install

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

if [ -e ~/.agents/skills/'agentsop-regression-gate' ] || [ -L ~/.agents/skills/'agentsop-regression-gate' ]; then echo 'A skill folder named agentsop-regression-gate already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/agentsope/SkillAlchemy' "$d" && git -C "$d" checkout --quiet '955562e4416c483da946e9c95a1c3974ac52df3c' -- 'skills/agentsop-regression-gate' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/agentsop-regression-gate' ~/.agents/skills/'agentsop-regression-gate' && 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/'agentsop-regression-gate' ~/.claude/skills/'agentsop-regression-gate' (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 agentsope/SkillAlchemy shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/agentsope/SkillAlchemy.svg)](https://zalavijaysinh.github.io/skilltrust/repos/agentsope/SkillAlchemy/)

Score history