Build, debug, refactor, or review Astro applications that integrate SolidJS, including islands, client directives, state ownership, prop serialization, SSR and hydration, routing,…
Transmutación alquímica de código en cuatro etapas — nigredo (descomposición), albedo (purificación), citrinitas (iluminación), rubedo (síntesis) — con puntos de control de…
Standard 5-phase workflow for most development tasks - bugs, small features, refactors (30-60 min)
Review code for quality, security, and maintainability following best practices. Use when reviewing pull requests, examining code changes, auditing code quality, or when the user…
El ADN de Aura: las filosofías centrales de Producto/UX e Ingeniería que rigen todo Fluxo AI. Cárgalo y aplícalo de forma persistente antes de diseñar flujos, escribir o…
Use when starting an issue, bugfix, feature, or refactor that should be driven by multiple coordinated subagents: explore → plan → code → review, with the main agent acting as…
Automate detection and removal of duplicate files/functions in TypeScript, JavaScript, and Python projects.
Variable and function naming discipline: domain vocabulary over generic words, verb semantics, scope-proportional length, and the specific naming anti-patterns Claude defaults to.
Testability discipline for application code. Identifies when logic should be extracted into pure helpers, when routes/pages/components are carrying too much domain work, and when…
Use whenever Thien asks Codex to improve, update, refactor, clarify, or redesign an automation. Runs a Claude/Cursor/Claude/Cursor critique loop before Codex saves and syncs the…
Expert automation workflow refactoring tool for Power Automate, n8n, Make, Zapier and other platforms.
Common mistake — doing unrequested work (refactoring, adding extra features, cleaning up style) when the user asked for a specific, targeted change.
Reviews diffs and PRs for correctness, security, and team standards, with confidence-scored findings in severity buckets (Critical / Suggestions / Nice to have).
How to respond to code review feedback: verify before implementing, clarify unclear items, and push back with technical reasoning when needed.
Reviews axum web framework code for routing patterns, extractor usage, middleware, state management, and error handling.
When the user needs to perform the same operation across multiple files, components, or entities. Use when the user says "do this to all," "batch," "bulk update," "across all…
Cascade the same edit pattern across N files safely. Use when applying the same refactor to multiple files (e.g.
Design and refactor beam tracking ML/RL pipelines (CSI teacher vs RSRP student), enforce shape contracts, and produce inference-safe models.
Use when considering, evaluating, or performing a refactor, restructure, cross-file rename, or cleanup
Implement testable production behavior through a red-green-refactor cycle. Use for bug fixes, features, and behavior-changing refactors, whether or not they belong to a formal…
リファクタリング（構造変更）と機能変更（behavior change）が同一 diff に混在していないかを識別し、structural change に対する external behavior preservation の証拠（テスト・型・静的解析）が揃っているかを diff-time で確認する。証拠不足のときは Characterization…
Provides language-specific best practices, code quality standards, and framework detection for refactoring workflows
Analyze the impact of code changes by mapping call graphs and identifying all direct and indirect dependencies.
Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories.
為單一 BMAD story 依序跑三階段（bmad-create-story → bmad-dev-story → bmad-code-review），每階段委派給一個全新 context 的 subagent 執行，主線只做協調、階段之間停下等使用者確認。code-review 會審查＋收官（回填發現、依結果切狀態），但不自動修 code；被審出的…
Refactoring (Martin Fowler) — Full rules — comprehensive mandatory coding standards. Use when asked to apply Refactoring principles or review code against Refactoring standards.
Refactoring (Martin Fowler) — Condensed rules — key principles distilled. Use when asked to apply Refactoring principles or review code against Refactoring standards.
Refactoring (Martin Fowler) — Minimal rules — essential one-liners only. Use when asked to apply Refactoring principles or review code against Refactoring standards.
Refactoring Guru (Refactoring.Guru) — Full rules — comprehensive mandatory coding standards. Use when asked to apply Refactoring Guru principles or review code against Refactoring…
Refactoring Guru (Refactoring.Guru) — Condensed rules — key principles distilled. Use when asked to apply Refactoring Guru principles or review code against Refactoring Guru…
Refactoring Guru (Refactoring.Guru) — Minimal rules — essential one-liners only. Use when asked to apply Refactoring Guru principles or review code against Refactoring Guru…
Refactoring techniques (behavior-preserving structural change, code smells) to consult when refactoring code. Reference material, not a review.
TDD template for bookie subagent tasks. Covers pure-validator TDD, fixture patterns, table-driven cases, and the red-green-refactor loop specific to ledger write validation.
Use this for safe code modernization, structural cleanup, legacy refactors, and revamps that should still respect the current codebase structure and avoid unnecessary churn.
Skeptical expert code review that maps changes to repo structure and infrastructure, applies strict engineering standards, and prefers minimal fixes.
Invoked automatically when creating git branches to suggest proper names. Covers prefixes: feature/, bugfix/, hotfix/, release/, docs/, test/, chore/, refactor/.
Apply the same change across multiple repos simultaneously using parallel agent teams. Creates worktrees, applies changes, runs tests, commits, and creates PRs.
Reviews BubbleTea TUI code for proper Elm architecture, model/update/view patterns, and Lipgloss styling. Use when reviewing terminal UI code using charmbracelet/bubbletea.
Discover edge cases and test coverage gaps through systematic analysis. Use when analysing test coverage, finding bugs, hunting for edge cases, or when code-reviewer identifies…
Author, validate, test, and troubleshoot Copilot Studio agents through YAML-driven commands instead of clicking through the product UI.
Build or refactor an AppKit app feature on top of SwiftASB using explicit application, window, document, thread, and turn ownership with main-actor UI updates and clear runtime…
Engineering excellence for builders. Use when: writing code, making technical decisions, refactoring, reviewing, completing implementation work.
빌드 오류 자동 수정 워크플로우. 컴파일 에러, 타입 에러, 누락된 import, 빌드 설정 문제를 진단하고 수정합니다. Use when build fails and quick targeted fixes are needed without broader refactoring.
Fix broken builds, type errors, or test failures with the smallest safe diff — no opportunistic refactors, no cleanup, no unrelated changes.
Build or refactor a Swift package API on top of SwiftASB without leaking raw app-server wire models, while keeping live Codex probes opt-in, isolated, timeout-bounded, and…
Build or refactor reusable, data-driven enemy archetype and moveset systems for Three.js action games.
Drive a planned change to 100% coverage across an entire codebase when a prior agent run stopped early.
Review C99 code for compliance with HBF's strict coding standards including compiler warnings, Linux kernel style, and licensing constraints.
Use when diagnosing, preventing, or refactoring the 'You have uncommitted work pending' CalloutException caused by mixing DML and callouts in the same Apex transaction.
Authors, validates, improves, scaffolds, and refactors Canopy skills using a structured control-flow notation (IF, ELSE_IF, ELSE, SWITCH, CASE, DEFAULT, FOR_EACH, BREAK, END, ASK,…
Use when this tick or session hit real, disproportionately costly friction with the harness (a pitfall it could have warned about, a slow gate, missing operational knowledge) or…
Review control flow quality using 87-item checklist. Use when code has deep nesting (3+ levels), complex conditionals, loop design questions, high cyclomatic complexity (McCabe…
Guide safe refactoring with research-backed discipline and small-change rigor. Produce refactoring approach, step sequence, and risk assessment.
Use when active development or explicit refactoring has concrete code-structure risk: a source file is accumulating independently changing responsibilities, a…
Enforces quality verification gates with four-step validation (tests pass, build succeeds, checklist complete, no blockers) before task completion, PR creation, or status updates.
Systematic debugging with defense-in-depth approach (symptoms → immediate cause → root cause → systemic issues → prevention).
Audit source and tests for ADR-030 anti-patterns, determinism failures, API-boundary violations, and test-helper leakage with Option A/B/C handling from the Test Quality Method.
Refresh stale learning and pattern docs under docs/solutions/ by reviewing them against the current codebase, then updating, consolidating, or deleting drifted ones.
Create an isolated git worktree for parallel feature work or PR review. Use when starting work that should not disturb the current checkout, or when `ce-work` or `ce-code-review`…
Turn a feature or product idea into an approved design spec before any implementation. Use only when the user explicitly asks to brainstorm, explore, or co-design an idea; never…