Implement one unit of work end-to-end — from a tracker issue OR an ad-hoc description: spec review, TDD (RED→GREEN→REFACTOR), pre-PR self-review, open a PR, then drive the…
Polish the active feature before review — code polish always; UI normalize + ship-quality pass when UI is touched.
Mine your Claude Code sessions and code-review history for the corrections you keep repeating, cluster them, adversarially verify each candidate, and distill the survivors into…
Use when writing or refactoring Go collection/pointer helper code in OpenMeter, especially when choosing between standard library slices/maps helpers and github.com/samber/lo for…
Function-level refactor workflow using call graph tools (Epic 114). Use before changing a symbol's signature, deleting a function, or refactoring callers — maps blast radius via…
Thoughtbox-first Theseus workflow for behavior-preserving refactors. Use this when structure changes but behavior must stay fixed and scope drift needs hard boundaries.
Create, update, review, or refactor VS Code Copilot skills, hooks, and MCP configs. Use when the user wants to build or maintain reusable skills, lifecycle hooks, MCP…
Generate a PR description from the current branch's changes against a GitHub PR, using the gh CLI. Use when writing, drafting, or updating pull request descriptions, PR summaries,…
Break a work-items.md file (produced by /plan-work-items) into independently-grabbable GitHub issues, one per slice, in each slice's target repo.
Perform a standards-based code review on a GitHub Pull Request, then post the findings as inline review comments and mark the PR as 'Requested changes'.
Run comprehensive code quality checks, tests, and fixes autonomously
Functionality Isolation Protocol — analyze dependencies for a file or symbol to understand the blast radius of changes.
Refactoring guidance with design patterns and code improvement strategies.
Parallel 3-reviewer code review: Security, Business-Logic, Architecture.
Scan the codebase for common code smells using threshold-based detection: long methods, god classes, long parameter lists, deep nesting, magic numbers, data clumps, and more.
This skill should be used when the user asks to "refactor context file", "split CLAUDE.md into skills/rules/hooks", "AGENTS.mdを分解", "コンテキストファイルを整理", or wants a single context file…
Executes automated project-wide refactoring with a focus on cross-file optimization. This skill should be used when the user asks for project-wide refactoring, cross-file…
This skill should be used when the user asks to "review ruby code", "audit ruby codebase", "find over-engineering in ruby", "simplify ruby classes", "review lib/", or wants to…
This skill should be used when the user asks to "clean my code", "make it human readable", "make this readable", "rewrite this cleanly", "refactor this", "clean up this function",…
This skill should be used for SB-owned refactoring: evaluate scope, preserve behavior with baseline tests, make structural changes, and prove nothing regressed.
Author a new Claude Code skill the house way, or refactor a fat skill into a lean SKILL.md + references/.
4-phase code review: UNDERSTAND, VERIFY, ASSESS risks, DOCUMENT findings.
Use this skill when the task involves creating, reviewing, or refactoring installable skills, shared skill references, or reusable agent-authoring guidance; when the work depends…
Review 3D Gaussian Splatting implementation code for correctness, performance bugs, and best practices.
[52] EXECUTE. Three-stage refactoring workflow: (1) iterative research of refactor/modularization options, (2) plan + risk/edge-case analysis + Scope150 validation, then implement…
5W1H Decision Framework Tool. Use for: (1) Systematic decision-making before creating todos, (2) Preventing duplicate implementation, (3) Detecting avoidance behavior, (4)…
Author and validate A12 Kernel document models with the dmtool CLI — both a model's structure (fields, groups, type definitions, includes, config) and its validation rules.
Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.
Pre-release ABAP code security and quality peer review across 12 dimensions. Auto-runs abaplint + ATC.
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 a Godot/.NET task needs a Layer 4 overlay review to prevent abstraction decay during feature work, flow extension, or touched-code refactoring, especially around flag…
Detects code smells in PHP codebases. Identifies God Class, Feature Envy, Data Clumps, Long Parameter List, Long Method, Primitive Obsession, Message Chains, Inappropriate…
Map the access surface of a feature a software engineer is about to ship. Use when the engineer names a specific feature or PR and wants a structured read of who can reach what,…
Review JusticeHub code against ACT ecosystem values. Enforces cultural protocols, ALMA principles, and regenerative design.
Use when creating or refactoring Action Mailer emails. Applies Rails 7.1+ conventions, parameterized mailers, preview workflows, background delivery, and email design best…
GitHub Actions workflow authoring conventions for readable, least-privilege workflows — .github/workflows/*.yaml layout, explicit scoped triggers, boolean logic with truthy/falsey…
Use when creating or refactoring Active Job background jobs. Applies Rails 8 conventions, Solid Queue patterns, error handling, retry strategies, and job design best practices.
Code review: IoC, RESTful, Contracts, Security (OWASP), Clean Architecture, SOLID.
Use when a task needs structural/relational code navigation — call graph, references, blast-radius, trace flows, safe refactors — and the GitNexus plugin is enabled.
Use when allocating feature/hotfix/refactor/chore/docs IDs or creating branches — canonical `[NNNN][L]` format that the scripts (next-id.sh, get-branch-metadata.sh, done.sh) expect
RED-GREEN-REFACTOR execution discipline for AI agents. Use when implementing any feature or bugfix that has (or should have) tests — forces a failing test confirmed for the right…
Address code review feedback by walking through comments one at a time with the user. Use when the user has received code review comments — on a GitHub PR, in a document in the…
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human.
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it shoul — from…
Use when adopting a shared module, library, chart, or service, or doing any consolidation, migration, or refactor that supersedes existing code.
Composite skill — safely refactor a module end-to-end with sequencing, parallel implementation, post-refactor cleanup, and rationale capture.
Layered code review pipeline — automated checks first, then AI-assisted review, then human review focused on Ousterhout red flags, AI failure patterns, silent failures, and…
Complete Claude Code productivity system — project setup, prompting patterns, sub-agent orchestration, context management, debugging, refactoring, TDD, and shipping 10X faster.
Enterprise-grade code review agent. Reviews PRs, diffs, or code files for security vulnerabilities, performance issues, error handling gaps, architecture smells, and test…
Use an agent to review a diff productively, with the right scope, framing, and scepticism about its findings. Use when reviewing your own changes before requesting human review.
Run an author agent and a reviewer agent in a loop with a strict finding format, a mandatory verification pass, and a convergence rule that ends it.
Sous-agent spécialisé dans la revue de code automatisée, déclenchable par un agent parent pour analyser du code.
Expert code reviewer specializing in code quality, security vulnerabilities, and best practices across multiple languages.
Create Claude Code slash commands and OpenCode command files that delegate to subagents. Use when creating new commands or refactoring existing ones to follow the delegation…
Refactor Codex configuration files and Agent Skills by splitting concerns, deduplicating instructions, and reorganizing guidance across AGENTS.md, project docs, and skills.
Generate an agent across the host AI tools a project uses. Use when the user wants to create, scaffold, or refactor an agent, subagent or specialized role.
Advanced repository analysis and refactoring guide. Identifies technical debt and architectural anti-patterns using AI reasoning.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Use when implementing, reviewing, refactoring, simplifying, debugging, or planning code changes that need explicit assumptions, minimal scope, surgical edits, and verifiable…