MCP App StoreMCP App Store
from specialist-agent12
Performs adversarial stress-testing of code to find edge cases, race conditions, security holes, and logical flaws before deployment.
The Grill skill systematically attacks target code to reveal vulnerabilities, edge-cases, race conditions, and logical bugs that normal reviews often miss. It defines a structured workflow: target analysis, categorized attack vectors (input, state, boundary, logic, error paths), reproducible proofs, severity ratings, and hardening recommendations.
Use before deploying critical code (authentication, payments, data handling), after complex changes, or when auditing fixes. Not intended for generic code quality reviews — it's adversarial and focused on breaking behavior.
Designed for code-review and security-focused agents (Claude Code, Cursor, Codex, advanced LLM-based security scanners).
Grill is an adversarial code review skill that guides an agent through systematic stress-testing across 5 attack categories (input, state, boundary, logic, error path). No scripts included — purely instructional via SKILL.md. The skill is well-structured with clear steps, detailed attack tables, and a resilience scoring formula. Security posture is strong: read-only by design, restricted tool access, no network calls or credentials.
Clean instructional skill with no scripts. The adversarial review methodology is thorough and well-documented. The allowed-tools field correctly restricts to Read, Bash, Glob, Grep. Minor architectural concern: single monolithic SKILL.md could benefit from splitting attack tables into references/. The bash access is broader than needed but the skill explicitly mandates read-only operation.
Test-Driven Development (TDD)
Run disciplined TDD cycles: write a failing test, implement the minimal fix, then refactor — for features and bugfixes where correctness matters.
/verify — Verification Before Completion
Run fresh verification commands (tests, build, lint, types) and require full output evidence before claiming work is complete or merging changes.
/learn — Interactive Learning Mode
Teaching-first implementation assistant: explains why decisions are made, walks through architecture, and produces incremental code with pedagogy for onboarding
Adaptive Planning (/plan)
Generate an implementation plan matched to task complexity — from quick mini-plans to full design documents — before writing code or making large changes.
Systematic Debug (/debug)
A four-phase, evidence-first debugging methodology agent skill: gather evidence, analyze patterns, formulate hypotheses, and implement & prove fixes.
Smart Commit (conventional commit generator)
Generate and apply conventional commit messages with automatic type & scope detection plus pre-commit validation for secrets and debug artifacts.
Conversion Rate Optimization (CRO)
Audit landing pages and user flows to find conversion friction and deliver prioritized, testable A/B recommendations.
Migration: Migrate Module
Automates a multi-phase migration of an Angular module to a target architecture with approval gates and validation after each phase.
Next.js: Migration — Migrate Component
Convert a Next.js Pages Router component/page to the App Router pattern, updating routing, data fetching, and component boundaries for Next.js App Router.
Review Review
Use when code changes need review before merge - validates architecture, types, security, and test coverage.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
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
Speak Security Basics
Security best practices for integrating Speak: API key management, audio data privacy, student data protection, and COPPA/FERPA compliance for production deploy
Apollo Security Basics
Practical security best-practices for integrating with the Apollo.io API: safe key storage, PII redaction, minimal permissions, rotation, and automated audit ch