调试
定位并修复问题，分析错误
Review Response Writer
rshankras
yourapp.com/help
git-best-practices
NeverSight
Git workflow patterns for commits, branching, PRs, and history management across heterogeneous repositories. Use when creating commits, managing branches, opening pull requests, or rewriting history. Do not use for non-git implementation tasks or repo-specific release policy decisions without repository documentation.
yellow-best-practices
NeverSight
Yellow Network and Nitrolite (ERC-7824) development best practices for building state channel applications. Use when building apps with Yellow SDK, implementing state channels, connecting to ClearNodes, managing off-chain transactions, or working with application sessions.
Error Handling Base
Dicklesworthstone
Foundation for error handling patterns. This is a base skill designed to be extended by language-specific error handling skills.
Complete Rust Development
Dicklesworthstone
A comprehensive skill for Rust development that combines error handling, testing, and logging patterns. Demonstrates the 'includes' composition feature by merging content from multiple standalone skills.
flutter-fix-layout-issues
flutter
Fixes Flutter layout errors (overflows, unbounded constraints) using Dart and Flutter MCP tools. Use when addressing "RenderFlex overflowed", "Vertical viewport was given unbounded height", or similar layout issues.
vrm-springbone-physics
Project-N-E-K-O
Debugging and fixing VRM SpringBone physics issues in three-vrm, including hair/clothing physics that flies upward, sticks out horizontally, or behaves unnaturally.
📝 任务完成后归档
Project-N-E-K-O
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。
Vanilla JS UI Race Conditions (VRM vs Live2D)
Project-N-E-K-O
Dealing with delayed DOM generation, lazy loading, and optimistic state synchronization in vanilla JavaScript without a reactive framework.
vrm-mtoon-outline
Project-N-E-K-O
Adjusting VRM MToon material outline thickness in three-vrm. Covers outline width modes, property access, and how to fix outlines that appear too thick when models are scaled.
i18n
Project-N-E-K-O
"i18n (internationalization) toolkit for projects using i18next. Provides three main functions: (1) i18n-check - Detect hardcoded Chinese text in HTML/JS files, (2) i18n-fix - Replace hardcoded text with i18n markers, (3) i18n-sync - Align translation keys across multiple languages (zh-CN, en, ja, ko, zh-TW). Use when working on internationalization tasks, detecting untranslated strings, or syncing locale files."
sapui5-linter
secondsky
Use this skill when working with the UI5 Linter (@ui5/linter) for static code analysis of SAPUI5/OpenUI5 applications and libraries. This skill should be used when: (1) Setting up UI5 Linter in a project for the first time, (2) Configuring linting rules and ignore patterns for UI5 codebases, (3) Running the linter to detect deprecated APIs, global variable usage, CSP violations, or manifest issues, (4) Using autofix to automatically correct deprecated API usage, global references, event handlers, and manifest properties, (5) Troubleshooting linting errors or warnings in UI5 code, (6) Integrating UI5 Linter into CI/CD pipelines or pre-commit hooks, (7) Preparing UI5 projects for migration to UI5 2.x by identifying compatibility issues, (8) Understanding and resolving specific linting rules like no-deprecated-api, no-globals, async-component-flags, or manifest validation rules. The skill covers all 19 linting rules, comprehensive autofix capabilities and limitations, CLI options, configuration patterns, performance optimization, and integration with development workflows. Keywords: SAPUI5, OpenUI5, UI5 Linter, @ui5/linter, static analysis, deprecated APIs, global variables, CSP, manifest.json, ui5.yaml, ESLint, pre-commit hooks, GitHub Actions, CI/CD, Node.js, TypeScript, XML, JSON, HTML, YAML, OData v2/v4, async, event handlers, jQuery, autofix, performance optimization, 19 linting rules, no-deprecated-api, no-globals, no-async-component-flags, manifest-v2, UI5 2.x migration
api-logging-guidelines
inkeep
"Best practices and guidelines for using logger in API routes. Defines appropriate logging levels, what to log, and when to avoid logging. Use when implementing or reviewing API route logging, debugging strategies, or optimizing log output."
planning-with-files
OthmanAdi
Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring >5 tool calls. Supports automatic session recovery after /clear.
planning-with-files
OthmanAdi
Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring >5 tool calls. Supports automatic session recovery after /clear.
pi-planning-with-files
OthmanAdi
Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring >5 tool calls. Supports automatic session recovery after /clear.
cli-developer
Jeffallan
Use when building CLI tools, implementing argument parsing, or adding interactive prompts. Invoke for CLI design, argument parsing, interactive prompts, progress indicators, shell completions.
debugging-wizard
Jeffallan
Use when investigating errors, analyzing stack traces, or finding root causes of unexpected behavior. Invoke for error investigation, troubleshooting, log analysis, root cause analysis.
diagnosing-bugs
mattpocock
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
moai-lang-r
modu-ai
R 4.4+ development specialist covering tidyverse, ggplot2, Shiny, and data science patterns. Use when developing data analysis pipelines, visualizations, or Shiny applications.
moai
modu-ai
MoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (plan, run, sync, fix, loop, project, feedback) to specialized agents. Use for any development task from planning to deployment.
moai-workflow-loop
modu-ai
Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.
moai-lang-rust
modu-ai
Rust 1.92+ development specialist covering Axum, Tokio, SQLx, and memory-safe systems programming. Use when building high-performance, memory-safe applications or WebAssembly.
moai-lang-elixir
modu-ai
Elixir 1.17+ development specialist covering Phoenix 1.7, LiveView, Ecto, and OTP patterns. Use when developing real-time applications, distributed systems, or Phoenix projects.