Use when creating, modifying, reviewing, or refactoring Go production code, especially API shape, package boundaries, naming, dependency ownership, error handling, concurrency,…
Use when reviewing GDScript or C# Godot code — checklist of best practices, common anti-patterns, and Godot-specific pitfalls
Use when Godot project has code-created objects, tight coupling via direct references, monolithic scripts over 150 lines, or needs scene-first architecture with signals and…
Capture the current output of untested legacy code as a recorded baseline so a refactor can prove it changed nothing.
Go language server (gopls) providing code intelligence, refactoring, and analysis for .go files. Use when working with Go code that needs autocomplete, go-to-definition, find…
Plan and execute safe refactoring using dependency analysis — find dead code, preview renames, verify no critical paths broken.
Search and rewrite code with GritQL — declarative queries backed by tree-sitter. Use when refactoring across languages or applying AST transformations at scale.
Searches and rewrites codebases using GritQL declarative queries. Use when refactoring across languages, migrating dependencies, enforcing code patterns, or applying complex…
Delegate a coding task to the Grok Build CLI as a background implementer, then review its diff and land it yourself.
Ground every version, stack, and best-practice choice in what is current today, read from the release channel rather than from recall.
Review changed files for bugs, security issues, and code quality; produce REVIEW.md — from alo-exp/silver-bullet
When planning or refactoring an outbound motion, validating account selection before investing pipeline resources, debugging why a sequence is unde...
Use when refactoring unhealthy code and needing Code Health findings to choose small safe steps and verify improvement.
Rename, split, merge, or restructure an existing canonical artifact with cross-reference scrubbing and an explicit rename-map deliverable.
Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable findings first…
Hope-native baseline for implementing, fixing, refactoring, and maintaining code: inspect the repository first, protect user changes, keep scope narrow, and finish with direct…
Use after design or implementation to package handoff notes, refactor UI code, split god components, document tokens, and prepare maintainable frontend deliverables.
Audits a project's agentic harness (CLAUDE.md, AGENTS.md, .claude/rules, .claude/settings.json) and refactors it into a layered, path-scoped configuration that loads only what is…
Build, refactor, and debug Hawk pages, templates, cards, and Hawk-500 code. Use when working with Hawk's page/file/card/load model, Sail/manx UI, `%twin`/`%call`/`%view`/`%lens`…
Use when writing, refactoring, or deciding how to test an HDL module, component, or IP block (ROHD, Chisel, SpinalHDL, Verilog, VHDL) and you need it parameterized, validated, and…
Review PRs, branches, diffs, and workflow artifacts for package-level go/no-go readiness with severity-ranked synthesis.
Reviews HealthKit code for authorization patterns, query usage, background delivery, and data type handling.
Perform a large-scale refactor with staged work and validation; use when changes span many files or modules.
Apply the Honest Code principles when writing, reviewing or refactoring code. Use when writing new code, reviewing a diff, refactoring, or when the user asks to make code…
Use when writing or refactoring code, before creating files - enforces separation of pure business logic (Functional Core) from side effects (Imperative Shell) using FCIS pattern…
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file.
Run a full architectural refactor cycle — explores the codebase for friction, categorizes dependencies, designs competing approaches for structural changes, then fixes everything…
Run Codex's native code-review on the current branch, working tree, or a specific commit. Use when the user invokes /hyperclaude:hyper-code-review, or after producing code changes…
Use when applying Hyperflow's orchestration doctrine in Codex, Antigravity, or another single-agent surface.
Hyperflow execution phase. Use when a task file exists in .hyperflow/tasks/ and the work needs building — verbs like build, implement, add, refactor, "wire up", "run the plan",…
Structured code reviews with severity-ranked findings and deep multi-agent mode. Use when performing a code review, auditing code quality, or critiquing PRs, MRs, or diffs.
Process code review feedback critically: check correctness before acting, push back on incorrect suggestions, no performative agreement.
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…
Refactor IC10 code for clarity and structure. Use when user wants to reorganize code, apply design patterns, improve naming, or make code more maintainable without changing…
Analyze system-wide impact of changes before making them. Use before modifying shared utilities, changing APIs, or refactoring core functionality.
Use when implementation is complete and ready for verification, before marking task done. Absorbs code-reviewer role — no separate code review needed in ECW workflow.
Full-lifecycle project workflow. Takes batched tickets, implements via /implement-batch, runs smoke tests, then executes a comprehensive quality pipeline (refactor, review-arch,…
Execute refactoring tasks from a task file with parallel agent orchestration
Autonomous TDD build agent. Implements a plan using red-green-refactor with BDD scenarios as RED tests.
Дисциплинированная реализация: код, API, schemas, configs, tests, naming, errors, reuse, sync. Используй для: реализация, доработка, рефакторинг, нейминг, реюз, контракты,…
Automatically trigger review agents after task completion. Use when strategic-planner finishes planning tasks (calls plan-consultant) or when main agent completes coding tasks in…
Implement using TDD Red-Green cycle. Focus on Red-Green only; refactoring is separate step.
Update all import statements, module references, string paths, and config references after moving or renaming files and modules.
Incrementally implement feature improvements from docs/improvements.md with tests and atomic commits. Focuses on new functionality rather than refactoring.
Improve existing agent skills based on user feedback and best practices. Use when the user wants to fix, enhance, or refactor an existing skill.
Improve test design and coverage, including TDD/red-green-refactor guidance.
Break multi-file changes into atomic commits ordered by dependency. Use for refactors, breaking API changes, or features touching 3+ files.
Use when IMPLEMENTING refactoring changes. Enforces metrics-driven protocol with before/after measurements.
Use when implementing features or refactoring with TDD - enforces writing ONE test at a time, implementing minimal code to pass, then repeating, preventing batch test writing that…
Write an infrastructure-as-code review checklist and conduct a structured review of Terraform, CloudFormation, Pulumi, or Ansible code.
JpaEntity, Adapter, Repository 클래스를 구현할 때 반드시 사용. 인프라 계층 구현 시 TDD(Red-Green-Refactor) 방식으로 진행. "JpaEntity 구현", "Adapter 구현", "Repository 구현", "영속성 계층" 작업 시 자동 발동.
Use when deciding whether similar code should be deduplicated. Prioritizes shared intent and change reason over textual similarity, avoiding harmful DRY abstractions when code…
Route ambiguous Phoenix/LiveView/Ecto work requests to the correct /phx: workflow. Use when intent is unclear, mixed (bug fix vs. refactor), or scope is ambiguous.
Human-in-the-loop code review with chunk-by-chunk approve/reject/chat loop (git add -p style). Use when reviewing PRs, diffs, patches, or documents interactively.
Guides adding and structuring internal Go packages: when to create a new package, import paths, cmd vs internal boundaries, and domain layout.
Analyze feature requests, refactor plans, or technical decisions to determine investment value and provide recommendations.
IoT quality assurance for the ESP32 pool-controller — static analysis, anti-pattern detection, code review rules, hardening for 24/7 operation, and systematic quality gates.
Guide structured analysis of problems and planning of implementation. Use when starting work on a new feature, encountering a bug, refactoring existing functionality, or any task…
对本次 diff 进行多维 code review 并自动修复，循环迭代直到收敛或达到最大轮次。 适用场景：开发完成一个 feature 或 fix 后，在提交/建 MR 前做质量保障。 触发关键词：「code review」「review 一下代码」「使用 iterative-code-review skill」 「review and fix」「做…
Systematic codebase refactor scan. Use when the user asks to scan/audit a project for refactoring opportunities — file-size violations, long functions, argument-mutation…