코딩 규칙, 프레임워크, 리팩터링, 코드 리뷰 (1.7만건)
Conducts a multi-axis code review (correctness, readability, architecture, security, performance) before merging. Use before merging any change, after finishing a feature or bug fix, when reviewing code another agent or person wrote, or when asked to review a diff or pull request.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when working code feels heavier than it needs to be — deeply nested logic, long functions, unclear names, duplication after a merge, or a review that flagged complexity. Reduces complexity while preserving behavior exactly. Not for code you do not yet understand, or code you are about to rewrite.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generate personalized status briefings on demand. Pulls from your configured data sources (GitHub, email, Teams, Slack, and more), synthesizes across them, and drafts updates in your own communication style for any audience you define
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Interactive onboarding that learns your communication style, audiences, and data sources to configure personalized status briefings. Paste in examples of updates you already write, answer a few questions, and roundup calibrates itself to your workflow. Use the first time Roundup is used, or to recalibrate its style and sources.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reviews and refactors code according to the project's own instruction and guideline files, keeping behavior intact. Use when the user asks for a cleanup pass that must follow repository conventions (for example .github/instructions) rather than generic best practices.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Refactor given method `${input:methodName}` to reduce its cognitive complexity to `${input:complexityThreshold}` or below, by extracting helper methods. Use when a method exceeds a cognitive-complexity threshold flagged by a linter or review.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Deep, evidence-first review of GitHub bugs and PRs: reads the code before forming opinions, finds root causes, decides whether an issue is stale, duplicate, or real, and proposes the best fix. Use when an issue or PR needs real investigation rather than a summary.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review. Use when AI-generated text with factual claims must be checked before it is published or relied on.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Profiles macOS and iOS apps with Instruments and xctrace: choosing templates such as Time Profiler, launching binaries with arguments, recording traces, and exporting results. Use when a Mac or iOS app needs CPU, memory, or responsiveness profiling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reverse-engineers and debugs macOS and iOS binaries with Hopper Disassembler and LLDB: ObjC/Swift symbols, dyld loading, framework internals, and crash investigation from disassembly. Use when private API behavior or a runtime crash needs to be understood at the binary level.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or eslint-disable suppressions, skipped or deleted tests, assertions stripped out, unimplemented stubs, thresholds edited down. Use when no quality bar is written down, when the user says "set up constraints" or "define our standards", when the user wants dimensions they care about — accessibility, web performance, coverage — set up as enforced constraints, when an agent keeps silencing checks or skipping tests to get to green, when you need a coverage or performance threshold and don't know what number to pick, or when an agent writes more code than anyone will read.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when performance budgets or SLAs exist, users or monitoring report slowness, Core Web Vitals fall below thresholds, a change may have caused a regression, or a feature handles large datasets or high traffic. Measure-first workflow: profile, fix the proven bottleneck, re-measure. Not for speculative optimization.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when writing, reviewing, or refactoring production code where reliability, portability, maintainability, explicit contracts, resource safety, and cross-language coding standards matter across Python, TS/JS, C, C++, Rust, or Go.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when refining a vague idea through divergent expansion, convergent focus, and assumption stress-testing before planning or implementation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when writing, editing, or reviewing code, READMEs, docs, commits, changelogs, or any repo content. Pre-2020 human style — terse, opinionated, restrained, with project voice. Blocks the LLM tics (emoji headers, "leverage", "robust", "seamless", "delve", defensive bloat, type-hint overkill, marketing prose, "Whether you're X or Y", verbose error messages) catalogued from cpython, requests, flask, git, ripgrep, express, kubernetes, serde, and the Go stdlib. Triggers on "anti-ai", "human-style", "no slop", "write it like a human", or any time code/docs should look hand-written.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when starting a coding session, setting up a project for AI-assisted development, switching between parts of a codebase, or when agent output quality degrades — hallucinated APIs, wrong patterns, ignored project conventions. Structures what the agent loads and when.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.