e2e-driven-iteration
100 / 100 · Low risk
Fine to try.
Use at the start of every inner-loop iteration where the goal is to fix a bug / close a failing test / reach a green E2E. Forbids editing code without first running the E2E to capture a fresh loss signal, and forbids declaring "done" without the E2E passing. Makes the cycle "E2E → loss → 5-why-by-layer → fix → E2E" the only admissible rhythm.
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/'e2e-driven-iteration' ] || [ -L ~/.agents/skills/'e2e-driven-iteration' ]; then echo 'A skill folder named e2e-driven-iteration already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/CorvinLabs/CorvinOS' "$d" && git -C "$d" checkout --quiet '3f28cfd9b82326ff325e645ff041589c3220d813' -- 'corvin_operator/bundle/skills/ldd/e2e-driven-iteration' && mkdir -p ~/.agents/skills && cp -R "$d"/'corvin_operator/bundle/skills/ldd/e2e-driven-iteration' ~/.agents/skills/'e2e-driven-iteration' && 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/'e2e-driven-iteration' ~/.claude/skills/'e2e-driven-iteration' (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/CorvinLabs/CorvinOS/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-12 | 3f28cfd | 100 |
| 2026-11-08 | 2a40b4e | 100 |