MCP App StoreMCP App Store
from Claude Code Workflows654
A comprehensive framework for technical decision-making, anti-pattern detection, and quality assurance for AI-driven development.
This skill provides a rigorous set of technical decision criteria and a collection of anti-patterns to ensure AI agents produce maintainable, high-quality code. It shifts the agent's focus toward 'Value-First Engineering', prioritizing the lowest-lifecycle-cost solutions that deliver actual user value.
Activate this skill during technical design reviews, when assessing implementation choices, debugging systemic failures, or when auditing code for technical debt and smells. It is specifically useful when the agent needs to decide whether to abstract code (Rule of Three) or implement complex error handling (Fail-Fast principles).
Optimized for Claude Code and other agentic IDEs (Cursor, Codex, Gemini CLI) that support structured procedural instructions.
This skill has not been reviewed by our automated audit pipeline yet.
Language-Agnostic Coding Principles
Opinionated, language-agnostic principles and patterns to improve maintainability, readability, and robustness when implementing features, refactoring, or revie
Language‑Agnostic Coding Principles
Opinionated, language-agnostic principles for writing maintainable, readable, and secure code — use when implementing features, refactoring, or reviewing code q
Evolve — Goal-Driven Improvement Loop
Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr
Code Spec Backfill
Identify missing function-level contracts and backfill docstrings and type annotations; report ambiguous gaps with misuse scenarios. Incremental, state-driven w
Matrix Warnings
Manage file and package warnings (add, remove, list, check) for a Matrix workflow; parse user arguments and call the matrix_warn tool to enforce repository-leve
Minimalist Code Writer
A high-signal coding standard focused on minimizing noise, eliminating redundant comments, and removing narrative output.
HiveMind Architect Strategist
Research-first architecture review and strategic planning skill: scans codebases, finds architectural issues, and synthesizes evidence-based recommendations for
zigts Expert (Zigttp)
Author, verify, and fix zigts (restricted TypeScript) handlers for the zigttp runtime using a compiler-in-the-loop workflow and JSON diagnostics.
Code Evaluation Harness
Spawns an independent evaluator agent to score code outputs on functionality, code quality, originality, and usability/security, producing a structured EVAL_REP
ESLint — JavaScript & TypeScript Linting
Guides configuration and usage of ESLint 9+ (flat config) for JS/TS projects, including React and TypeScript plugin patterns and CI integration.