Restructure code with behavioral parity proven through unmodified pre-existing tests, then refactor. No behavior change.
Review a PR against the top 20 Tier 2 LLM-enforceable best practices from 35 seminal software engineering books (Code Complete, Clean Code, A Philosophy of Software Design,…
Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.
Chat with deepseek-v4-flash, a 284B MoE model (13B active per token) with a 1M-token context window, tuned for coding and agentic workflows.
Detect DRY violations and recommend refactoring strategies. Args: [branch |
]
Detect duplicate MoonBit code using AST-based similarity analysis. Use when working with .mbt files and looking for code duplication, refactoring opportunities, or enforcing code…
Use when writing, reviewing, or refactoring code, or scaffolding a new project. Language-agnostic principles (types encode invariants, parse don't validate, errors as values, no…
Review a diff for reuse, composition, codebase consistency, and slop - the 'does this fit the codebase' lens rather than 'is it correct'.
Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a chan — from…
Iterative auto-fix code review — runs `/optimus:code-review` in a fresh subagent context per iteration, applies fixes, runs tests, bisects failures, and continues until…
Use this skill when conducting or improving code reviews. Provides structured review processes, conventional comments patterns, language-specific checklists, and feedback…
Use when reviewing code changes for quality, security, performance, or maintainability issues and identifying simplification opportunities in a single token-efficient pass
Breaker（Claude）× Judge（Codex）の二者構造で、反例生成とテスト実行により「本当の欠陥」のみを抽出する敵対的コードレビュー。重要変更・最終ゲート・見逃したくない場面に使う。対象が PR なら確認ゲート経由で PR にレビューを投稿する。通常のレビューは /code-reviewer を使うこと。
Author, update, and validate prompts (skills, agents, subagents, workflows, commands, rules, templates, or just any generic prompt).
Use when docs/solutions/ learnings may be stale — after refactors, migrations, or dependency upgrades, when a retrieved learning feels outdated or contradicts a recently solved…
Prove a change achieved its intended outcome: a mechanical build+test+lint prerequisite (delegated to /toolchain:check and /toolchain:lint, STOPs if broken), then outcome…
Read-only GitHub activity card for a named contributor on . Fetches PR authorship, code-review activity, issues, and PR/issue comments over a configurable window.
Use when: designing, reviewing, or refactoring C++ error handling policy, exceptions vs std::expected vs error codes, exception safety guarantees (basic, strong, nothrow), RAII…
Create a ralph (a deterministic execution plan with steps) for a coding task. Use when the user wants to plan and break down a feature, bug fix, or refactor into executable steps…
Epic 主入口。用于大需求或系统级能力的端到端拆解与长程执行：planning、review、子 feature design（批量）、goal 包。不要用于单个功能(cs-feat)、bug 修复(cs-issue)、行为等价重构(cs-refactor)、对外文档(cs-docs)。
Feature 主入口。用于新功能或功能改造，先按风险自动选择 Quick、Standard 或 Goal lane，再恢复并推进对应流程。不要用于单纯 bug 修复(cs-issue)、行为等价重构(cs-refactor)、对外文档(cs-docs)、大需求拆解(cs-epic)。
Delegate a single write task to Cursor Composer via cursor-companion.sh inside an isolated worktree, then Lead-review the diff and cherry-pick.
Record a technical-debt item (DEBT-NNN) — registration only by default, or register + auto-generate a fix TASK with --task.
Systematic codebase quality scan for identifying duplication, redundancy, and improvement opportunities.
Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a chan — from…
Perform holistic review of completed refactoring, validate improvements, and create follow-up tasks if needed
Reviews a Pull Request or validates local changes before opening a PR, following the eventaservo architecture and Rails patterns. Analyzes committed, staged, and unstaged changes.
Snapshot a Figma frame's metadata, tokens, design-context, and screenshot to local files under `.ai-docs/figma//` so downstream agents (design-builder, design-grader, spec…
Systematically fix all failing tests after business logic changes or refactoring
Revisa código frontend de customização Fluig (widgets com SuperWidget, Custom Elements, FreeMarker e CSS) e produz um relatório de achados classificados por severidade, cada um…
Use when assessing overall project quality, onboarding onto a new codebase, or before major refactoring to establish a baseline.
Write less code and say less about it. Applies YAGNI and stdlib/native-first so the agent writes the minimum code that needs to exist, and responds tersely — stripping filler,…
Identify high-priority refactoring targets using hotspot scoring. Ranks modules by issue severity and coupling count.
Keep a software system cheaply changeable over its whole life — the phase that is 60–80% of total cost and most under-resourced — across: classifying and funding it, making…
Lightweight implementation orchestrator for low-complexity work — fixes, refactors, doc changes, or single-AC features that do not warrant a phase plan or factory decomposition.
Use when the sensei tutor selects or applies a pedagogical framework. Routes to 10 frameworks: 5w2h (default — structured analysis), pear-loop (Plan-Explore-Analyze-Rewrite),…
Facilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises after architectural work (new files, schema changes, refactors).
Run a standalone code review on lilnas changes — correctness, testing, maintainability, project standards — plus conditional reviewers (kieran- typescript, julik-frontend-races,…
Narrow bare `rescue _ ->` / `rescue e ->` so UndefinedFunctionError, KeyError, and typos propagate instead of being swallowed.
Applies the Refactoring Priority Premise (RPP) levels L1-L6 for systematic code refactoring. Use when improving code quality through structured refactoring passes.
Orchestrates a same-series Odoo git rebase - replaying a feature or fix branch onto an updated base of the SAME Odoo major version - forwarding INTENT, not diff text.
Triage code-review findings (manual or AI), fix the ones you choose one at a time with tests, defer/log the rest, then validate — and if the work is on a PR, commit and push so…
Full pull-request review — fetch the PR, run the project's validation, review the diff with fresh eyes (dispatching the code-reviewer agent), categorize issues by severity, post…
Use when starting a new feature, refactor, or multi-step task - before writing any code. Use especially when scope is unclear or multiple files are involved.
Use when the user wants a new feature or capability built and it is not a one-to-two-step change - "I want to add X", "let's build a way to Y", "can we add", "new feature: Z", a…
Plan a feature, refactor or migration as a reviewable, versioned artifact the user annotates line by line before any code is written, instead of a plan that scrolls away in chat.
Run a full pull request review and post review comments directly to the current branch's GitHub PR. Requires the gh CLI to be installed and a PR to already exist for the current…
Create a clean PR branch by filtering out .design/ and .planning/ commits. Code-review-ready branch for the design implementation work.
Use when: deciding whether a pull request, diff, or change set is too large or mixed to review in one pass, splitting an oversized PR into reviewable slices, separating refactor…
Synthesize a recurring code-review rule into a custom lint rule — gated by an independent soundness test that abstains rather than ship a checker it can't prove sound
Identify opportunities to introduce a refactor that would make a feature easy to implement.
Generate synthetic code context for LLM coding tasks. Automatically use this before making code changes, fixing bugs, refactoring, or answering questions about the codebase.
Review my code, code review, is this ready to ship, check for bugs, security audit, review this PR, pre-merge check, is this safe to deploy, check code quality.
Detect duplicate Rust code using AST-based similarity analysis. Use when working with .rs files and looking for code duplication or refactoring opportunities.
Safety analysis before refactoring -- dependency graph, test coverage, public API exposure, blast radius verdict.
Create a detailed refactor plan with tiny commits via user interview, then file as a GitHub issue RFC.
Use when: planning or executing a behavior-preserving refactor: characterization coverage before touching code, small reversible steps with a green check after each, strict…
Atomic rename of Python symbols (functions, classes, methods) or modules using the structural index. Finds all static callers, import sites, __all__ re-exports, and Sphinx…
Use when: sharpening a software requirement or a requirement set so it is buildable and decidable rather than merely well-formed - replacing vague quality words and quantifiers…
Triage reviewer comments on a GitHub PR with receiving-code-review discipline — verify each against the codebase, then accept/push-back/clarify, and optionally reply in-thread.