review

57 / 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

Multi-agent code review of GitHub Pull Requests (Python source, documentation (Markdown/RST), and CI/CD config PRs) covering architecture, tests, performance, docs, lint, security, and API design. TRIGGER when: user provides a GitHub PR number (e.g. 42, #42) and asks to review/audit/check it, or provides a saved review-report path with --reply to draft a contributor-facing comment; phrases: 'review PR 123', 'audit this pull request', 'look at PR #42', 'draft a reply for this review report'. SKI…

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 31 places.

plugins/cc_oss/skills/review/SKILL.md, line 121PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name oss) || exit $?; export PLUGIN_ROOT
plugins/cc_oss/skills/review/SKILL.md, line 133PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name oss) || exit $?; export PLUGIN_ROOT
plugins/cc_oss/skills/review/SKILL.md, line 149PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name oss) || exit $?; export PLUGIN_ROOT

Show 17 more

plugins/cc_oss/skills/review/SKILL.md, line 165export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
plugins/cc_oss/skills/review/SKILL.md, line 180PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name oss) || exit $?; export PLUGIN_ROOT
plugins/cc_oss/skills/review/SKILL.md, line 197PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name oss) || exit $?; export PLUGIN_ROOT
plugins/cc_oss/skills/review/SKILL.md, line 212PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name oss) || exit $?; export PLUGIN_ROOT
plugins/cc_oss/CHANGELOG.md, line 180- The same hook reads each command as the shell's own words before judging it: quotes, backslash escapes, `$'…'` strings and line continuations are resolved and
plugins/cc_oss/bin/resolve_test_plan.py, line 86proc = subprocess.run( # noqa: S603 - argv list, no shell
plugins/cc_oss/bin/resolve_test_plan.py, line 89except (OSError, subprocess.SubprocessError):
plugins/cc_oss/blueprint-manifest.json, line 5408"template": "PLUGIN_ROOT=$(python \"${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py\" --plugin-name oss) || exit $?; export PLUGIN_ROOT\nexport CSID=\"${CLAUDE
plugins/cc_oss/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\" \"${CLAUDE_PLUGIN_ROOT}/hooks/audit-cl
plugins/cc_oss/hooks/hooks.json, line 17"command": "for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v \"$n\" >/dev/null 2>&1 && exec \"$n\" \"${CLAUDE_PLUGIN_ROOT}/hooks/enforce-
plugins/cc_oss/hooks/hooks.json, line 26"command": "for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v \"$n\" >/dev/null 2>&1 && exec \"$n\" \"${CLAUDE_PLUGIN_ROOT}/hooks/enforce-
plugins/cc_oss/hooks/hooks.json, line 37"command": "for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v \"$n\" >/dev/null 2>&1 && exec \"$n\" \"${CLAUDE_PLUGIN_ROOT}/hooks/audit-cl
plugins/cc_oss/hooks/hooks.json, line 48"command": "for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v \"$n\" >/dev/null 2>&1 && exec \"$n\" \"${CLAUDE_PLUGIN_ROOT}/hooks/enforce-
plugins/cc_oss/hooks/hooks.json, line 57"command": "for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v \"$n\" >/dev/null 2>&1 && exec \"$n\" \"${CLAUDE_PLUGIN_ROOT}/hooks/enforce-
plugins/cc_oss/hooks/hooks.json, line 66"command": "for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v \"$n\" >/dev/null 2>&1 && exec \"$n\" \"${CLAUDE_PLUGIN_ROOT}/hooks/enforce-
plugins/cc_oss/hooks/hooks.json, line 75"command": "for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v \"$n\" >/dev/null 2>&1 && exec \"$n\" \"${CLAUDE_PLUGIN_ROOT}/hooks/agent-ro
plugins/cc_oss/hooks/hooks.json, line 85"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/allow-di

and 11 more places

Downloads and installs other software

The author does not mention this.

Found in 6 places.

plugins/cc_oss/skills/review/templates/agent-prompts.md, line 9**Missing-package evidence gap — close it, never just document it (every agent):** claim needs a run, run blocked because a Python package is absent or installe
plugins/cc_oss/skills/review/templates/agent-prompts.md, line 183. **Support check (wheel-only, default index)** — `uv pip install --dry-run --only-binary :all: --no-config --no-cache --default-index https://pypi.org/simple
plugins/cc_oss/skills/review/templates/agent-prompts.md, line 194. **Fetch (no code runs)** — every overlay-set name passed step 2, then `uv pip install --only-binary :all: --no-deps --no-config --no-cache --default-index ht

Show 3 more

plugins/cc_oss/skills/review/templates/agent-prompts.md, line 26No `uv` but `<env-python> -m pip` works: step 2 routing check first (its `pip config list` covers every pip config scope + `PIP_*` env), then support check + fe
plugins/cc_oss/bin/resolve_test_plan.py, line 311The full-suite command comes from contributor docs, which are untrusted: a line such as ``pytest; curl x | sh``
plugins/cc_oss/bin/resolve_test_plan.py, line 326>>> safe_command("pytest; curl x | sh") is None

Sends data to these websites: x

The author does not mention this. It runs automatically when the plugin is installed.

Found in 3 places.

plugins/cc_oss/bin/resolve_test_plan.py, line 328>>> safe_command("curl -o pytest http://x") is None
plugins/cc_oss/hooks/agent-router.js, line 216const req = https.request(
plugins/cc_oss/hooks/agent-router.js, line 296const req = https.request({ hostname: "api.anthropic.com", headers, ...options }, (res) => {

Changes files outside its own folder

The author does not mention this.

Found in 1 place.

plugins/cc_oss/blueprint-manifest.json, line 4143"template": "PLUGIN_ROOT=$(python \"${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py\" --plugin-name oss) || exit $?; export PLUGIN_ROOT\n[ -f ~/.claude/setting

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.

plugins/cc_oss/hooks/agent-router.js, line 218hostname: "api.openai.com",
plugins/cc_oss/hooks/agent-router.js, line 296const req = https.request({ hostname: "api.anthropic.com", headers, ...options }, (res) => {

Safer alternatives

Low-risk skills in the same category (coding) that look related. Check that one does what you need.

Other copies in this repository

Borda/AI-Rig has 3 more folders with a skill named review. This page shows the lowest-scoring copy.

plugins/cc_develop/skills/review 82/100 · Low risk
plugins/bridge_cc-codex/claude-skills/review 97/100 · Low risk
plugins/bridge_cc-codex/codex-skills/review 100/100 · Low risk

Install

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

if [ -e ~/.agents/skills/'review' ] || [ -L ~/.agents/skills/'review' ]; then echo 'A skill folder named review 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 "$d" checkout --quiet '2af2f1f55a9eaf520f795f3557e739f9bd78d078' -- 'plugins/cc_oss/skills/review' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/cc_oss/skills/review' ~/.agents/skills/'review' && 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/'review' ~/.claude/skills/'review' (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.

SkillTrust badge for Borda/AI-Rig

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/Borda/AI-Rig.svg)](https://zalavijaysinh.github.io/skilltrust/repos/Borda/AI-Rig/)

Score history

Date	Version	Score
2026-11-13	`2af2f1f`	57
2026-11-09	`1f354b2`	69
2026-11-07	`82bd7e4`	69