By jukben
Adversarial reasoning and decision stress-testing. Pressure-test arguments, run pre-mortems, play devil's advocate, and generate structured Decision Records.
A Claude Code plugin marketplace with curated skills by jukben.
Add the marketplace to Claude Code:
/plugin marketplace add jukben/claude-skills
Then install individual plugins:
/plugin install adversarial-review@jukben-skills
/plugin install pr-pipeline@jukben-skills
Adversarial reasoning and decision stress-testing. Pressure-test arguments, run pre-mortems, play devil's advocate, and generate structured Decision Records.
Usage: /adversarial-review:adversarial-review or triggered automatically when you mention decision records, ADRs, devil's advocate, pre-mortems, etc.
Features:
PR lifecycle from branch to merge. Two skills that work together:
/pr-pipeline:pr — Detects branch state, runs self-review (/simplify + parallel code review & test agents), publishes as draft PR, and hands off to babysit/pr-pipeline:babysit-pr — Monitors CI, fixes failures, rebases, resolves review threads (human vs bot), enables automerge, loops until mergedFeatures:
/simplify + 2 parallel agents (code review, test & CI)/loopMIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub jukben/claude-skills --plugin adversarial-reviewPR lifecycle skills: self-review with parallel agents, publish as draft PR, and babysit through merge with CI monitoring and review thread resolution
Symmetric two-AI peer review using OpenAI Codex CLI. Both AIs review independently in a blind pass, then debate per-issue with terminal states until convergence. Catches significantly more issues than single-pass validation.
Multi-agent adversarial review panel — 4-6 AI reviewers debate your code/plans, then a judge delivers a structured verdict with epistemic labels. Bundles plan-review-integrator for applying review findings back into implementation plans.
Automatic code review, adversarial review, and rescue via Codex.
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Analytical thinking tools - dialectic analysis, bias elimination, codex consultation
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.