DevNullLtd/Yuzu / .claude/skills/adversarial-review
adversarial-review
VerifiedRun an adversarial two-phase code review of a change with TWO independent reviewers — Claude and Codex — who review alone, then cross-examine each other's findings, then Claude synthesizes a single weighted verdict. Use when the user says "/adversarial-review", "adversarial review", "review this with Codex", "get Codex to review", "two-reviewer review", "cross-examine this PR", or wants a second independent model to grade a change before merge.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.9 KB |
| review-prompt.md | markdown | 7.6 KB |
| run-codex-reviewer.shexecutable | script | 5.0 KB |
| run-kimi-reviewer.shexecutable | script | 14.2 KB |
| run-kimi-sandbox-hook.shexecutable | script | 1.0 KB |
| run-kimi-sandboxed-shell.shexecutable | script | 1.9 KB |
run-kimi-sandboxed-shell.sh
View on GitHub#!/usr/bin/env bash
# Exact-command collector allowed by Kimi's restricted permission profile.
# It accepts no model-controlled command text and emits bounded empirical context.
set -euo pipefail
[[ $# -eq 0 ]] || { echo "error: sandbox dispatcher accepts no arguments" >&2; exit 2; }
: "${YUZU_KIMI_SANDBOX_REPO:?set YUZU_KIMI_SANDBOX_REPO}"
: "${YUZU_KIMI_SANDBOX_REVIEW_DIR:?set YUZU_KIMI_SANDBOX_REVIEW_DIR}"
: "${YUZU_KIMI_SANDBOX_IMAGE:?set YUZU_KIMI_SANDBOX_IMAGE to an immutable image digest}"
case "$YUZU_KIMI_SANDBOX_IMAGE" in
*@sha256:*) ;;
*) echo "error: sandbox image must be pinned by digest" >&2; exit 2 ;;
esac
command -v docker >/dev/null 2>&1 || {
echo "error: docker is required for Kimi sandboxed shell mode" >&2; exit 2; }
REPO="$(cd "$YUZU_KIMI_SANDBOX_REPO" && pwd)"
REVIEW_DIR="$(cd "$YUZU_KIMI_SANDBOX_REVIEW_DIR" && pwd)"
DOCKER_ARGS=(
run --rm --pull never
--network none
--read-only
--cap-drop ALL
--security-opt no-new-privileges
--pids-limit 256
--memory "${YUZU_KIMI_SANDBOX_MEMORY:-4g}"
--cpus "${YUZU_KIMI_SANDBOX_CPUS:-4}"
--user "$(id -u):$(id -g)"
--env HOME=/tmp/kimi-home
--env "YUZU_REVIEW_OUTPUT=$REVIEW_DIR/KIMI_SANDBOX_OUTPUT.md"
--tmpfs "/tmp:rw,nosuid,nodev,noexec,size=1g"
--volume "$REPO:$REPO:ro"
--volume "$REVIEW_DIR:$REVIEW_DIR:rw"
--workdir "$REPO"
)
if [[ -n "${YUZU_KIMI_SANDBOX_GIT_DIR:-}" ]]; then
GIT_DIR="$(cd "$YUZU_KIMI_SANDBOX_GIT_DIR" && pwd)"
DOCKER_ARGS+=(--volume "$GIT_DIR:$GIT_DIR:ro")
fi
if [[ -n "${YUZU_KIMI_SANDBOX_PLATFORM:-}" ]]; then
DOCKER_ARGS+=(--platform "$YUZU_KIMI_SANDBOX_PLATFORM")
fi
exec docker "${DOCKER_ARGS[@]}" "$YUZU_KIMI_SANDBOX_IMAGE" /bin/bash -lc \
'if command -v git >/dev/null 2>&1; then
{ git status --short; git diff --stat; git log -5 --oneline --decorate; }
else
echo "sandbox image has no git; orchestrator dynamic evidence remains authoritative"
fi > "$YUZU_REVIEW_OUTPUT" 2>&1'
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |