发现 research debugging 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Audits feature completeness by scanning codebases and comparing against PRD requirements. Identifies gaps between backend implementation and user-facing accessibility. Generates remediation tasks and integrates...
Extended investigation for technology evaluation, competitive analysis, architectural exploration, and best practices research. Unlike spike (time-boxed hours), deep-research supports multi-day comprehensive in...
Analyzes completed agent sessions to identify what went well, what went wrong, and patterns to improve. Reads from .claude/ folder (session logs, progress.md, git history) and produces actionable insights. Use...
Time-boxed technical investigation with structured output. Use for feasibility studies, architecture exploration, integration assessment, performance analysis, or risk evaluation. Creates spike tasks in ohno, e...
Performance analysis, optimization techniques, and performance testing for web applications. Covers profiling, bottleneck identification, frontend optimization (bundle size, rendering, Core Web Vitals), backend...
Review UI code for Web Interface Guidelines compliance - accessibility, forms, animation, performance
Run a single-session performance audit on the codebase
Analyzes web and mobile applications for WCAG 2.2 AA accessibility compliance. Audits code (HTML, React, React Native, SwiftUI), interprets automated tool output, and processes manual tester findings. Produces...
Atlas skill for code-first browser automation and web verification. USE WHEN browser, screenshot, navigate, web testing, verify UI, VERIFY phase. Replaces Playwright MCP with 99% token savings.
Perform automated code reviews with best practices, security checks, and refactoring suggestions. Use when reviewing code, checking for vulnerabilities, or analyzing code quality.
Analyze a traceback or error log, identify root cause, and implement the minimal fix with a short summary. Use when a traceback is provided.
Debug CoGames mission or variant regressions by comparing branch vs main. Use when behavior changes or a `cogames play` command regresses.
Code quality verification skill for reviewer agents. Provides checklists for logic clarity, error handling, maintainability, and performance. Use during VERIFICATION phase to assess implementation quality.
Deep reasoning protocol for exhaustive, multi-dimensional analysis and production-ready code generation. Suspends brevity for maximum depth and irrefutable logic.
Search codebase for a pattern and open top hits.
Shellcode 分析专用工具，支持反汇编、系统调用识别、字符串提取、网络指标检测等功能。
Evaluate and implement visualization algorithms for ocean/foam rendering. Use when discussing rendering techniques, contour algorithms, performance optimization for graphics, or evaluating algorithm tradeoffs....
Visual regression for canvas-rendered matrix progressions. Tests filmstrip strips that show how 2D data evolves visually over time. Auto-apply when editing *Progressions.ts strip definitions or stories with fil...
Apply performance optimization patterns for game loop, rendering, and state updates. Use when discussing frame rate, optimization, profiling, or when editing core game loop code. Auto-apply when user mentions "...
Expert SRE investigator for incidents and debugging. Uses hypothesis-driven methodology and systematic triage. Can query Axiom observability when available. Use for incident response, root cause analysis, produ...
Debug code, analyze errors, interpret stack traces, find root causes, and suggest fixes. Use when troubleshooting bugs, analyzing crashes, or investigating unexpected behavior.
Visual inspection and code review for Web Interface Guidelines compliance. Triggers on "review my UI", "check accessibility", "audit design", "review UX", "fix the layout", "find design problems". Supports both...
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Process code review findings interactively - fix or skip issues from monty-code-review output. Presents issues in severity order, applies fixes, runs quality checks, and updates review documents with status mar...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。