157 tagged adversarial-review, measured the same way as everything else here.
Browse within: ai-code-review 141midstream 69upstream 51agent-orchestration 20ai-development 20boilerplate 20codex-cli 19architecture 18community 14downstream 10auto-fix 8claude-code-skills 8entry 8routing 8
Skill Claude CodeCodex
Multi-angle code review that adapts to what is being reviewed — a mid-flight worktree increment, a full PR before production, a merge-window integration sweep, or a security-only pass. Findings are scored, adversarially refuted, widened to the same defect elsewhere in the codebase, and reported to the native review…
Skill Claude CodeCodex
Full product development pipeline: expert role debates, single-blind review, document generation, and human decision logging. Orchestrates 4 modular skills into a complete idea-to-development flow. Use when starting a new product from scratch. Triggers on "product workflow", "new product", "full pipeline", "idea to…
shawnclybor/clybor-claude-tooling
Skill Claude CodeCodex
Governs driving Excel Online (Business) through a Microsoft Copilot Studio agent against SharePoint-hosted .xlsx. Triggers — "Copilot Studio", "Excel Online (Business)", "add a row", "update a row", "delete a row", "connector 502 / BadGateway", "Office Script", "pin the File input", "spreadsheet agent", "SharePoint…
shawnclybor/clybor-claude-tooling
Skill Claude CodeCodex
A framing diagnostic for "why did this happen?" moments during agent and tool work. Use when the user says "why did this fail", "why did the agent do that", "why is this output wrong", "why isn't this working", or otherwise asks for an explanation of agent/tool behavior. Reads like an incident report — frame the…
shawnclybor/clybor-claude-tooling
Skill Claude CodeCodex
Audit and rewrite content to remove AI writing patterns ("AI-isms") from deliverables, emails, and any written output. Use this skill whenever generating deliverable content (Phase 1 curation in any client deliverable skill), drafting client emails longer than 3 sentences, writing proposals or SOWs, creating reports…
tetckx/deep-structural-analysis-skill
Skill Claude CodeCodex
Multi-perspective structural analysis for complex social, economic, philosophical, and systemic questions — produces stratified, fact-bound, confidence-calibrated conclusions via multi-lens analysis + structural tools + adversarial prior checks. Invoke when the user asks for deep analysis, multi-angle exploration…
yinguangyao/evidence-first-skill
Skill Claude CodeCodex
A work method for non-trivial tasks that produce conclusions or deliverables, such as research, analysis, troubleshooting, plans, documents, or code. It emphasizes checking evidence, especially when sources conflict or facts and numbers matter.
razaumair2203-ux/codex-adversarial-review-lite
Skill Claude CodeCodex
Codex Adversarial Review - Lite: user-invoked audit workflow for Claude Code users who want Codex CLI to independently review AI-generated code, plans, test expectations, and scope before fixes are applied. Cross-platform (Windows, macOS, Linux, WSL). Use only when the user explicitly invokes audit or selftest.
Skill Claude CodeCodex
Monitor deployments with read-only evidence gathering, anomaly detection, cadence summaries, and local alerts. Use when watching a deploy, validating staging or production after release, comparing Datadog/database/runtime evidence, investigating new errors or skipped work, or linking post-deploy anomalies back to…
Skill Claude CodeCodex
Empirically test whether a skill actually improves model output — before trusting it. Runs a controlled experiment: planted-flaw fixture, no-skill control arm, skill arm(s), optional cross-model arms via installed CLIs, blind judging with shuffled labels, and a pressure test for verdict stability. Produces…
Skill Claude CodeCodex
Adversarial collaborator who pushes back like a senior engineer - the default adversarial reviewer. Surfaces hidden assumptions, grounds every challenge in evidence, presents real counterpoints with proven alternatives, drives toward synthesis, and records settled claims as verdict nodes in docs/verdicts/ so an…
Skill Claude CodeCodex
Review changes to the Agent Skills import/export bridge for path safety, round-trip fidelity, and validation correctness.
Skill Claude CodeCodex
Detects per-caller special-cases (bandaids) bolted onto shared infrastructure/common functions, and when two or more same-kind special-cases exist proposes generalizing the lower-level mechanism instead.
Skill Claude CodeCodex
Detect breaking API contract changes, DTO modifications without compatibility handling, and missing tests for changed API boundaries.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: