Flashlight skill for static security review of SuiteScript 2.x code against OWASP Top 10 (2021) pitfall patterns (OSCP-001 through OSCP-048), extended with Vanguard severity…
Refactoring, migration, cleanup, extraction of responsibilities. Use when user mentions 'refactoring', 'migration', 'nettoyage résidus', 'extraction'.
Run autonomous maintenance tasks (dependency updates, dead code removal, small refactors) in an isolated branch.
Nightly direct-execution skill for reducing code complexity thresholds. Receives pre-computed threshold data, refactors violations, updates thresholds, commits, and creat — from…
Capture and compare per-op activations between two TorchTitan runs to spot numerics divergence (eager vs aot_fx_trace, FSDP vs no-FSDP, before vs after a refactor).
Enhanced Mikado Method for complex architectural refactoring - systematic dependency discovery, tree-based planning, and bottom-up execution
Review Odoo addon code for correctness, security, performance, migrations, tests, and official Odoo coding guidelines.
Run on an existing project to decide KEEP / MERGE / ARCHIVE — never limbo. Forces a call on tools that already exist and may have stopped earning their keep.
Behavior-preserving refactoring specialist - plans and executes safe incremental restructuring with code smell / SATD / hotspot targeting, characterization-test safety nets,…
After a code change, sync the project's ontology vault — read what's already there, identify new capabilities / elements / domains introduced by the change, and write them back…
Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review…
Refactor macOS SwiftUI views and scenes into stable structure. Use when splitting large views, tightening scene state, or narrowing AppKit escapes.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and — from…
Use when completing tasks, implementing major features, or before merging to verify work meets requirements — from phamlongh230-lgtm/yamtam-engine
Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.
Delegate coding tasks to OpenCode CLI agent for feature implementation, refactoring, PR review, and long-running autonomous sessions.
Run OpenCode (MiniMax) and Claude code reviews iteratively until both find no issues. Use after making changes and before committing.
Design and plan fixes/refactoring for an OpenSpec change from confirmed reviewer findings without editing code.
Use before you shorten, compress, or rewrite the BODY of an existing SKILL.md or agent .md — the moment you are about to cut text to reduce length.
Codex deep ops-safety review of a proposed Bash command BEFORE it executes. Invoke MANUALLY (via /ops-preflight) when the ops-risk-triage hook has emitted an `ask` for an…
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Orchestrate a behavior-preserving refactor — confirm tests are green, restructure without changing behavior, keep tests green, review, and gated commit.
Plan and execute large refactors with dependency-aware work packets and parallel analysis.
Keep notebooks synchronized with `.py` or `.md` representations so version control, review, and refactoring can happen outside bulky notebook JSON.
Upgrade Palantir Foundry SDK versions and handle breaking changes. Use when upgrading foundry-platform-sdk, migrating between API versions, or detecting deprecations in Foundry…
Use when fixing widespread errors such as lint, type, test, or repetitive refactor issues that can be partitioned across file groups.
Write C++ code following Sean Parent's "No Raw Loops" philosophy. Emphasizes algorithm-based thinking, composition over iteration, and treating code as mathematical reasoning.
Lisa-native code review of the current git diff. Walks every changed hunk and reports correctness bugs, security issues, and obvious defects as severity-ranked findings with…
AI Assistant untuk optimasi kode otomatis. Bukan hanya scanner pola, tapi asisten pribadi yang belajar dari gaya coding-mu, memberi saran proaktif, auto-refactor, dan meningkat…
Generate a complete feature design specification (design.md, tasks.md) and Gherkin scenarios from natural language requirements.
Rename the current Claude session for peon-ping notifications and terminal tab title. Use when user wants to give this session a custom name like "/peon-ping-rename Auth…
Use when developing or reviewing Python code for a scientific package (e.g., cooltools) that targets collaborative development with multiple contributors.
Persistent planning system with 3 markdown files (PLAN.md, PROGRESS.md, CONTEXT.md). Use when starting large features, multi-session work, or complex refactoring.
Code quality and technical debt management decision framework for systematic refactoring and simplification.
Use ao revisar mudanças recentes Laravel ou Angular do Petrvs-PGD antes de merge, especialmente back-end, com postura Tech Lead, validação obrigatória de Repository Pattern,…
pf-frontend 프로젝트 컨벤션과 React 19 Best Practices 기반 코드 리뷰. "코드 리뷰", "리뷰해줘", "이 코드 괜찮아?" 요청 시 사용.
Phase-level verification gate run at a v3.x phase boundary (the post-phase analog of verify-plan). Spawns three independent full-context lenses in parallel — PM (honesty-auditor)…
Phase agent that triages a Linear ticket — expands acronyms, classifies (feature/bug/docs/refactor/chore), identifies genuine blockers (a semantic second-pass over the backlog —…
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface ass — from…
Executa a Fase 2 do refactor Kryonix — quebrar o monólito de packages usando callPackage, dar casa ao CLI shell, ao kryonix-home (Rust), ao instalador (Rust+Vite) e ao Doctor TUI,…
Reviews Phoenix code for controller patterns, context boundaries, routing, and plugs. Use when reviewing Phoenix apps, checking controllers, routers, or context modules.
Code-craft guardrails that reduce the most common LLM coding mistakes — think before coding, simplicity first, surgical changes, and verifiable success — gated by objective…
Refuses to start coding if the estimated change is larger than a threshold. Forces plan-mode for big tasks so they don't get cowboyed in one turn.
Create an implementation plan for a new feature, refactor, or fix. Guides an interactive design discussion and produces a structured plan document.
Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.
Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.
Apply structured thinking before coding. Use when: starting new features, making architectural decisions, refactoring large components, or evaluating implementation approaches.
Planning philosophy, patterns, and practices for implementation planning. Use when planning features, architectural changes, or refactoring.
Converts a refactor map into a phased plan using parallel-change, branch-by-abstraction, or strangler fig patterns.
Use when a Shiny application or R package currently runs only on Windows and you need to enable deployment on Linux or macOS.
Review PooCommerce code changes for coding standards compliance. Use when reviewing code locally, performing automated PR reviews, or checking code quality.
Confidence-based code review that filters issues to 80+ threshold, eliminating false positives and noise.
Multi-agent orchestration system using Claude Code's native background agents (2.0.64+) for true parallel collaboration.
Angular 20 conventions for the Alexis Trejo portfolio—standalone components, zoneless SSR, routing, services, file layout, naming, and data patterns.
Use when a Godot/.NET task needs a Layer 4 overlay completion review after a large refactor, multi-file implementation, or new feature, and the agent must assess layer boundaries,…
Spin up a PR code review sub-agent. Ranks bugs critical/high/medium/low, eliminates false positives, writes consolidated report, applies KISS/DRY fixes (main logic only, skip…
GitHub PRのレビューコメントを自動検出し、コード修正を適用する。インラインスレッド・レビュー本文・Issueコメントに対応し、CodeRabbit・Copilot等のbotコメントも処理する。PRレビュー後の修正作業を自動化したい場合に使用する。Do NOT use for レビュー自体の実施（ai-code-reviewを使用すること）。
Walk a maintainer through deep code review of open pull requests on the configured `
` repo (default: read from `/project.md → upstream_repo`).
Sweep open pull requests on the configured `
` repo (default: read from `/project.md → upstream_repo`), classify each one against the project's quality…
完整 PR 生命週期（通用版，任何專案皆可用）：從建立 PR 到 code-review → parallel review（4 個 pr-review-toolkit subagent） → fix → re-review → CI → merge。無 SDD/spectra 依賴。 SDD 專案（需要 spectra archive + Jira…