scenario-refine-loop
100 / 100 · Low risk
Fine to try.
Use when a Scenario output must be checked and improved rather than accepted first roll: iterating a generation until it matches the brief, fixing a batch that came back off-brief, retrying failed shots methodically, wiring an automated generate, review, revise loop, or deciding whether to re-prompt, swap references, inpaint, post-process, or change model. Keywords: refine, iterate, critique, review loop, QA, self-correction, verify, acceptance criteria, retry, drift.
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/'scenario-refine-loop' ] || [ -L ~/.agents/skills/'scenario-refine-loop' ]; then echo 'A skill folder named scenario-refine-loop already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/scenario-labs/skills' "$d" && git -C "$d" checkout --quiet 'b96506d77c8595a4fe9c66eddb0bf9b5953a1d45' -- 'skills/scenario-refine-loop' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/scenario-refine-loop' ~/.agents/skills/'scenario-refine-loop' && 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/'scenario-refine-loop' ~/.claude/skills/'scenario-refine-loop' (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/scenario-labs/skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-11 | b96506d | 100 |
| 2026-11-08 | f38c3e8 | 100 |
| 2026-11-07 | a4a8409 | 100 |