Implements minimal code to make failing tests pass (Green phase of Red-Green-Refactor). Use when the user explicitly asks to make tests pass, implement to green, or apply…
Code review practices with technical rigor and verification gates. Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false completion claims in…
Create, update, refactor, explain, or review Semantic Kernel solutions using shared guidance plus language-specific references for .NET and Python.
Directory-aware meta-skill. Maintains the integrity and efficiency of the entire skill society. On activation, runs scripts/crawler.py to map every SKILL.md under the project…
Reviews serde serialization code for derive patterns, enum representations, custom implementations, and common serialization bugs.
Serena MCP for project memory and code navigation. Use when managing Serena memories, navigating symbols, performing intelligent refactoring, or maintaining context/continuity…
Decide when Rails logic stays in the model and when it earns a service object. Use when the user asks about service objects, fat models, "where does this logic go", refactoring a…
Reviews Shopify Liquid themes, cart logic, product templates, and checkout flow implementation for conversion optimization, mobile usability, and performance.
Internal project-context placement and consistency reference used by context refactoring and verification workflows.
Use when designing any implementation task before writing code (feature, bug fix, refactor, config change).
Analyze and simplify existing implementations to reduce complexity, improve maintainability, and enhance scalability.
This entry turns GitHub Next's Code Simplifier workflow into a narrow cleanup agent. The agent inspects code changed in the last day, proposes behavior-preserving simplifications,…
Review changed code for smells (duplication, oversized files, dead code, complexity), propose focused refactors, and verify with tests. No scope creep.
Simplifies, polishes, and declutters code without changing behavior. Use when asked to simplify, clean up, refactor, declutter, remove dead code or AI slop, or improve re — from…
Create or refactor high-quality skills with lean frontmatter, progressive disclosure, and optional bundled helpers. Use when authoring reusable agent workflows.
Extraer y reimportar codigo VBA de archivos Excel .xlsm en Windows usando Python (pywin32/oletools) o VBScript.
Compress verbose SKILL.md files using Chain-of-Density with skill-aware formatting. Use when a skill exceeds 200 lines or needs terse refactoring.
Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement.
Meta-skill for creating, refactoring, vetting, and maintaining Claude Code skills. Treats skills as production software.
Scan Codex session history for skill failures, usage patterns, and coverage gaps. Use when the user wants daily skill-health monitoring or evidence-backed recommendations about…
WHAT: Analyze skill reliability from Codex session evidence. WHEN: Use when skill failures, routing gaps, quality regressions, or keep-improve-merge-retire decisions need evidence.
Internal skill that validates a new or modified AI DevStudio skill against project standards. Checks YAML frontmatter, token optimization section, line limit, and naming…
Use when planning or breaking down any change: a PR, a refactor, a feature, or a delegated unit of work.
Apply multi-file edits: feature additions, component creation, refactors, route setup, and integration tasks.
Trigger: review my code, code review, PR review, review this diff, critique my implementation, is this code good, find problems in my code, senior review, review pull request,…
Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.
SOLID, DRY, KISS, YAGNI — принципы чистого кода с примерами на TypeScript и Python. Use when: code review, refactoring, architecture decisions, new feature design, or when code…
SOLID principles checklist with Java examples. Use when reviewing classes, refactoring code, or when user asks about Single Responsibility, Open/Closed, Liskov, Interface…
Use when the user wants an incremental Sonar refresh after code changes, a pull, or a refactor.
Comprehensive code review workflow coordinating quality, security, performance, and documentation reviewers. 4-hour timeline for thorough multi-agent review.
Recognize when a mission is a bulk edit and drive the occurrence-classification guardrail on the user's behalf.
Use when Claude Code needs to refactor code, tests, docs, specs, or project structure in a SpecDD project while preserving specified behavior, public contracts, scenarios,…
Split a large or mixed Git working tree into multiple focused local commits. Use when changes span unrelated concerns, combine refactors with behavior changes, mix generated files…
Universal SQL code review assistant that performs comprehensive security, maintainability, and code quality analysis across all SQL databases (MySQL, PostgreSQL, SQL Server,…
Reviews SQLAlchemy code for session management, relationships, N+1 queries, and migration patterns. Use when reviewing SQLAlchemy 2.0 code, checking session lifecycle,…
Reviews sqlx database code for compile-time query checking, connection pool management, migration patterns, and PostgreSQL-specific usage.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and — from…
Use when the user explicitly requests a code review, or during subagent-driven development where review is part of the workflow
Extract code into a new function or class. Use when the user says 'extract this' or wants to refactor by pulling out code.
Practical guide for building safe, syntax-aware srgn CLI commands for source-code search and transformation.
Modify features with impact analysis and compatibility checks. Triggers on modify/change/update/refactor intent.
One repeatable pass that keeps fak trustworthy while it iterates fast — the question no other scorecard asks: as we add items quickly, how do we KNOW a regression / tail-wag /…
Staff-engineer-level code review that goes beyond correctness to evaluate architectural alignment, system-level implications, failure modes, performance, scalability, backward…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and — from…
Register a Stage work item before you touch governed files. Use this whenever you start a task, feature, fix, refactor, or doc change in a project that has a `.stage/` harness —…
When the user asks for a code review, shares code for feedback, or says "review this", "check my code", "what's wrong with this".
Stealth Nexus operations skill. Invoke for VPS/proxy chain setup, diagnostics, and ops scripts. Do not invoke for CLI refactoring, LocalAI runtime operations, or PR-only reviews.
DRY, KISS, SRP 원칙에 대해서 코드 리뷰를 수행합니다. 코드 품질 검토, 리팩터링 기회 식별, 중복 코드 감지, 복잡한 로직 단순화에 특화되어 있습니다.
Arbeitsweise und Denkweise für die (Weiter-)Entwicklung der simon42 Dashboard Strategy — Architektur-Leitplanken, Qualitäts-Gates, Kreuzauswirkungs-Check, Umgang mit Community-PRs…
Search code by AST structure using ast-grep. Find semantic patterns like function calls, imports, class definitions instead of text patterns.
Performs a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance.
Find the bugs a diff can actually ship: TypeScript, React, Next.js, OWASP, accessibility, SEO, database, and deploy-risk review.
Claude-directed parallel OpenAI Codex CLI worker fleet for bulk generation. Use when a job is high-volume, well-specified, and splits into independent worker-sized tasks (content…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, designing systems, or making architectural — from…
AI-native software development lifecycle that replaces traditional SDLC. Triggers on "plan and build", "break this into tasks", "build this feature end-to-end", "sprint p — from…
Use when completing tasks, implementing major features, or before merging to verify work meets requirements — from steph-frtech/cdesign-expo
Use when completing tasks, implementing major features, or before merging to verify work meets requirements — from jleechanorg/claude-commands
Forces Claude to match output scope exactly to what was requested. Triggers before adding error handling for impossible edge cases, extracting one-time abstractions into classes,…
Use when editing existing code — making a fix, adding a feature, or changing behavior in a file that already has working code.
Refactor/rename/migration discipline — enumerate all call sites before editing, separate mechanical from judgment edits, keep the build green, verify by absence and presence.