staging-evaluate
100 / 100 · Low risk
Fine to try.
Turn a captured staging bundle (output/staging/<date>/) into a verified, ranked dogfooding backlog: features/fix-*.md specs + _IDEAS/backlog.md entries + FILED GitHub issues. Use when the user mentions evaluating a staging bundle, grooming staging findings, Mode D, verify-before-groom, turning a walkthrough/CLI-run capture into fix specs, replicating a customer report, or filing issues from a captured run. Also triggers on "staging-evaluate", "evaluate the bundle", "groom the findings", "Mode D…
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/'staging-evaluate' ] || [ -L ~/.agents/skills/'staging-evaluate' ]; then echo 'A skill folder named staging-evaluate already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/orionfold/relay' "$d" && git -C "$d" checkout --quiet 'b80e0240f42f84cd950fe8361a11a10699aa7984' -- '.agents/skills/staging-evaluate' && mkdir -p ~/.agents/skills && cp -R "$d"/'.agents/skills/staging-evaluate' ~/.agents/skills/'staging-evaluate' && 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/'staging-evaluate' ~/.claude/skills/'staging-evaluate' (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/orionfold/relay/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-08 | b80e024 | 100 |