メニュー
Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from distinct critical lenses. Triggers: "adversarial review".
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/pedronauck/skills --skill adversarial-reviewコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Cross-LLM peer review of an implemented change (the diff) via `compozy exec`: an independent reviewer runtime pressure-tests the diff and writes one scoped Markdown findings artifact for user-directed remediation. Project-agnostic — any repo or language; auto-discovers project rule files and the verify command. Use after an implementation pass (feature, bug fix, refactor) when the user explicitly asks for an external review of the diff before commit or PR. Do not use for spec/TechSpec review — use spec-peer-review.
Implements concurrent Go patterns using goroutines and channels, designs and builds microservices with gRPC or REST, optimizes Go application performance with pprof, and enforces idiomatic Go with generics, interfaces, and robust error handling. Use when building Go applications requiring concurrent programming, microservices architecture, or high-performance systems. Invoke for goroutines, channels, Go generics, gRPC integration, CLI tools, benchmarks, or table-driven testing.
VC outreach and raise execution: investor target lists (partner-level, tiered), warm-intro and cold-email plays that convert to first calls, meeting prep and objection handling, the parallel-process pipeline (batching, momentum, follow-ups), and diligence through close (data room, references, term-sheet-to-wire). Use when a founder needs an investor list, wants intros or cold emails to VCs, is preparing for or debriefing an investor meeting, is managing an active raise pipeline, or is assembling a data room. Don't use for deck authoring (use vc-pitch-deck) or for round sizing, narrative, and term economics (use vc-strategy).
SOC 職業分類に基づく
SKILL.md を表示中
| name | adversarial-review |
| description | Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from distinct critical lenses. Triggers: "adversarial review". |
| schedule | After cook sessions that produce large diffs (200+ lines), implement plan phases, or complete a planning session |
Spawn reviewers on the opposite model to challenge work. Reviewers attack from distinct lenses grounded in brain principles. The deliverable is a synthesized verdict — do NOT make changes.
Hard constraint: Reviewers MUST run via the opposite model's CLI (codex exec or
claude -p). Do NOT use subagents, the Agent tool, or any internal delegation mechanism as
reviewers — those run on your own model, which defeats the purpose.
Read brain/principles.md. Follow every [[wikilink]] and read each linked principle file.
These govern reviewer judgments.
Identify what to review from context (recent diffs, referenced plans, user message).
Determine the intent — what the author is trying to achieve. This is critical: reviewers challenge whether the work achieves the intent well, not whether the intent is correct. State the intent explicitly before proceeding.
Assess change size:
| Size | Threshold | Reviewers |
|---|---|---|
| Small | < 50 lines, 1–2 files | 1 (Skeptic) |
| Medium | 50–200 lines, 3–5 files | 2 (Skeptic + Architect) |
| Large | 200+ lines or 5+ files | 3 (Skeptic + Architect + Minimalist) |
Read references/reviewer-lenses.md for lens definitions.
Create a temp directory for reviewer output:
REVIEW_DIR=$(mktemp -d /tmp/adversarial-review.XXXXXX)
Determine which model you are, then spawn reviewers on the opposite:
If you are Claude → spawn Codex reviewers via codex exec:
codex exec --skip-git-repo-check -o "$REVIEW_DIR/skeptic.md" "prompt" 2>/dev/null
Use --profile edit only if the reviewer needs to run tests. Default to read-only.
Run with run_in_background: true, monitor via TaskOutput with block: true, timeout: 600000.
If you are Codex → spawn Claude reviewers via claude CLI:
claude -p "prompt" > "$REVIEW_DIR/skeptic.md" 2>/dev/null
Run with run_in_background: true.
Name each output file after the lens: skeptic.md, architect.md, minimalist.md.
Each reviewer gets a single prompt containing:
Spawn all reviewers in parallel.
Before reading reviewer output, log which CLI was used and confirm the output files exist:
echo "reviewer_cli=codex|claude"
ls "$REVIEW_DIR"/*.md
If any output file is missing or empty, note the failure in the verdict — do not silently skip a reviewer.
Read each reviewer's output file from $REVIEW_DIR/. Deduplicate overlapping findings.
Produce a single verdict:
## Intent
<what the author is trying to achieve>
## Verdict: PASS | CONTESTED | REJECT
<one-line summary>
## Findings
<numbered list, ordered by severity (high → medium → low)>
For each finding:
- **[severity]** Description with file:line references
- Lens: which reviewer raised it
- Principle: which brain principle it maps to
- Recommendation: concrete action, not vague advice
## What Went Well
<1–3 things the reviewers found no issue with — acknowledge good work>
Verdict logic:
After synthesizing the reviewers, apply your own judgment. Using the stated intent and brain principles as your frame, state which findings you would accept and which you would reject — and why. Reviewers are adversarial by design; not every finding warrants action. Call out false positives, overreach, and findings that mistake style for substance.
Append to the verdict:
## Lead Judgment
<for each finding: accept or reject with a one-line rationale>