MCP App StoreMCP App StoreThis skill runs an adversarial, three-agent code review pipeline: a Hunter (maximize recall to find potential bugs), a Skeptic (challenge and attempt to disprove findings with risk-adjusted scoring), and a Referee (independently adjudicate and produce a definitive report). The design enforces strict context boundaries so each phase analyses code independently, reducing confirmation bias and producing high-fidelity bug reports with structured BUG-IDs and severity scoring.
Use for pre-merge security audits, large PR reviews, legacy code audits, or any high-stakes module where false negatives are costly. It supports scanning entire projects, directories, individual files, or branch-diff mode (files changed between branches).
Agents that can spawn isolated subagents, read code, and pass structured data between phases (e.g., orchestration-capable assistants or platforms supporting isolated runtimes).
Three-phase adversarial code review skill (Hunter/Skeptic/Referee) with isolated agent contexts to eliminate sycophancy bias. No bundled scripts — pure prompt orchestration. Well-documented with clear execution protocol, scoring systems, and structured output format. Niche but well-designed for teams doing serious code review.
Clean skill with no security concerns. The isolated-context design pattern is thoughtful and well-articulated. No executable code to test.
Remind — Conversation Recall
Search and recall past Claude Code/agent conversation sessions to find decisions, code snippets, and context for continuation or reference.
Humanize
Revision and editing rules to remove AI-like patterns from prose so output reads more natural and human — applied automatically to any human-facing text before
Runtime Context
Detects which execution environment an agent is running in (Claude Code, Vercel Sandbox, or local dev) and exposes available tools and capabilities for safe, en
CI/CD Pipeline Monitor
Automates the process of waiting for CI/CD pipelines (GitHub Actions, GitLab CI, Vercel) to complete and analyzing results.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
ds-fix — data-science mid-analysis fixer
Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.
TradeOS
Natural-language driven CEX trading and portfolio management for agents: API key vaulting, multi-exchange orders, DCA, arbitrage scanning, alerts and security r
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.
Java 25 & Spring Boot 4 Code Reviewer
Run focused, evidence-based code reviews for Java 25 and Spring Boot 4 projects — migration risks, architecture boundaries, null-safety (JSpecify), security, an
ArcKit — French Public Procurement (fr-marche-public)
Generates French public procurement (Dossier de Consultation des Entreprises) drafts aligned with the Code de la Commande Publique, UGAP frameworks, and DINUM d
ArcKit Architecture Conformance
Run a systematic architecture conformance assessment that compares ADRs and principles against HLD/DLD artifacts to surface drift, violations, and technical deb
