← All skills
judge
79 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.
By Borda/AI-Rig (GitHub) · coding · 31 stars · scanned at commit 2af2f1f
Research-supervisor review of program.md — validates experimental methodology (hypothesis clarity, measurement validity, control adequacy, scope, strategy fit), emits APPROVED / NEEDS-REVISION / BLOCKED verdict before expensive run loop.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. It runs automatically when the plugin is installed. Expected for a coding skill.
Found in 35 places.
Show 17 more
- plugins/cc_research/skills/judge/SKILL.md, line 86
export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}" - plugins/cc_research/skills/judge/SKILL.md, line 147
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name research) || exit $?; export PLUGIN_ROOT - plugins/cc_research/skills/judge/SKILL.md, line 213
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name research) || exit $?; export PLUGIN_ROOT - plugins/cc_research/skills/judge/SKILL.md, line 245
_PROGRAM_TIMEOUT='<resolved metric_timeout_sec>' - plugins/cc_research/skills/judge/SKILL.md, line 258
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name research) || exit $?; export PLUGIN_ROOT - plugins/cc_research/skills/judge/SKILL.md, line 269
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name research) || exit $?; export PLUGIN_ROOT - plugins/cc_research/skills/judge/SKILL.md, line 282
case '${metric_cmd}' in '${'*|'') echo "! BLOCKED — metric_cmd not substituted"; exit 1;; esac - plugins/cc_research/skills/judge/SKILL.md, line 289
case '${guard_cmd}' in '${'*|'') echo "! BLOCKED — guard_cmd not substituted"; exit 1;; esac - plugins/cc_research/skills/judge/SKILL.md, line 298
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name research) || exit $?; export PLUGIN_ROOT - plugins/cc_research/skills/judge/SKILL.md, line 315
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name research) || exit $?; export PLUGIN_ROOT - plugins/cc_research/skills/judge/SKILL.md, line 329
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name research) || exit $?; export PLUGIN_ROOT - plugins/cc_research/skills/judge/SKILL.md, line 399
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name research) || exit $?; export PLUGIN_ROOT - plugins/cc_research/skills/judge/SKILL.md, line 515
rm -f .temp/state/skill-contract.md # clear contract — judge verdict complete (compaction-contract.md §Lifecycle) # timeout: 5000 - plugins/cc_research/CHANGELOG.md, line 103
- The same hook reads each command as the shell's own words before judging it: quotes, backslash escapes, `$'…'` strings and line continuations are resolved and - plugins/cc_research/CHANGELOG.md, line 107
- fortify's `bash -c "$METRIC_CMD"` and `"$GUARD_CMD"` blocks and sweep's heredoc-data block now prompt each run instead of being auto-allowed. - plugins/cc_research/CHANGELOG.md, line 183
- `blueprint-manifest.json` is regenerated with the allowlist gate: 685 of the 707 entries the previous gate admitted stay auto-allowed, including the `fortify` - plugins/cc_research/hooks/hooks.json, line 8
"command": "for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v \"$n\" >/dev/null 2>&1 && exec \"$n\" \"${CLAUDE_PLUGIN_ROOT}/hooks/audit-cl
and 15 more places
Changes files outside its own folder
This is disclosed by the author in the skill's SKILL.md or README.
Found in 1 place.
Connects to the internet
This is disclosed by the author in the skill's SKILL.md or README. It runs automatically when the plugin is installed.
Found in 2 places.
Can call paid AI services billed to you
The author does not mention this. It runs automatically when the plugin is installed.
Found in 2 places.
Safer alternatives
Low-risk skills in the same category (coding) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'judge' ] || [ -L ~/.agents/skills/'judge' ]; then echo 'A skill folder named judge already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Borda/AI-Rig' "$d" && git -C "$d" checkout --quiet '2af2f1f55a9eaf520f795f3557e739f9bd78d078' -- 'plugins/cc_research/skills/judge' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/cc_research/skills/judge' ~/.agents/skills/'judge' && rm -rf "$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/'judge' ~/.claude/skills/'judge' (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 Borda/AI-Rig shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/Borda/AI-Rig/)
Score history
| Date | Version | Score |
|---|
| 2026-11-13 | 2af2f1f | 79 |
| 2026-11-09 | 1f354b2 | 82 |
| 2026-11-07 | 82bd7e4 | 82 |