调试
定位并修复问题，分析错误
code-smell-detector
rysweet
Identifies anti-patterns specific to amplihack philosophy. Use when reviewing code for quality issues or refactoring. Detects: over-abstraction, complex inheritance, large functions (>50 lines), tight coupling, missing all exports. Provides specific fixes and explanations for each smell.
dynamic-debugger
rysweet
Interactive debugging via DAP-MCP for multiple languages with natural language commands
ohos-app-build-debug
openharmonyinsight
"Build, install, launch, and debug HarmonyOS/OpenHarmony applications using DevEco Studio toolchain. Use when Claude needs to: (1) Build OHOS apps with hvigorw, (2) Install HAP files to devices via hdc, (3) Launch or debug OHOS applications, (4) Parse crash stacks with hstack, (5) Take device screenshots, or (6) Detect DevEco Studio environment and SDK tools. Automatically detects DevEco Studio installation and configures JAVA_HOME, PATH, and toolchain."
sher-deploy
sherdotsh
Deploy frontend projects to instant preview URLs using sher. After building a project, run sher link to get a live, shareable URL in seconds.
wix-cli-app-validation
wix
Use when testing app readiness, verifying runtime behavior, or validating before releases and after changes in the code. Triggers include validate, test, verify, check readiness, preview validation, build verification, TypeScript compilation.
convergence-study
HeshamFS
Spatial and temporal convergence analysis with Richardson extrapolation and Grid Convergence Index (GCI) for solution verification
differentiation-schemes
HeshamFS
Select and apply numerical differentiation schemes for PDE/ODE discretization. Use when choosing finite difference/volume/spectral schemes, building stencils, handling boundaries, estimating truncation error, or analyzing dispersion and dissipation.
background-job-processing
aj-geddes
Implement background job processing systems with task queues, workers, scheduling, and retry mechanisms. Use when handling long-running tasks, sending emails, generating reports, and processing large datasets asynchronously.
sdd-explore
Gentleman-Programming
Explore and investigate ideas before committing to a change. Trigger: When the orchestrator launches you to think through a feature, investigate the codebase, or clarify requirements.
debugging-dbt-errors
AltimateAI
Debugs and fixes dbt errors systematically. Use when working with dbt errors for: (1) Task mentions "fix", "error", "broken", "failing", "debug", "wrong", or "not working" (2) Compilation Error, Database Error, or test failures occur (3) Model produces incorrect output or unexpected results (4) Need to troubleshoot why a dbt command failed Reads full error, checks upstream first, runs dbt build (not just compile) to verify fix.
optimizing-query-text
AltimateAI
Optimizes Snowflake SQL query performance from provided query text. Use when optimizing Snowflake SQL for: (1) User provides or pastes a SQL query and asks to optimize, tune, or improve it (2) Task mentions "slow query", "make faster", "improve performance", "optimize SQL", or "query tuning" (3) Reviewing SQL for performance anti-patterns (function on filter column, implicit joins, etc.) (4) User asks why a query is slow or how to speed it up
better-result-adopt
davis7dotsh
Migrate codebase from try/catch or Promise-based error handling to better-result. Use when adopting Result types, converting thrown exceptions to typed errors, or refactoring existing error handling to railway-oriented programming.
backend-implementation-patterns
organvm-iv-taxis
Production-ready backend API implementation patterns including REST, GraphQL, authentication, error handling, and data validation
trace-qa
MooseGoose0701
Analyze and answer questions about agent execution traces. Use this skill when the user asks about a trace, wants to debug a failed agent run, understand what an agent did, analyze token usage or efficiency, or asks "what happened in trace X". Triggers: trace analysis, trace debugging, trace QA, execution review, agent run review.
plain-talk-reportcard
Terryc21
'Codebase analysis with A-F grades explained in plain language for non-technical stakeholders. Self-contained iOS/Swift audit. Triggers: "plain talk report card", "stakeholder report", "non-technical audit".'
Slide Management
rhuss
MANDATORY USE - ALWAYS INVOKE THIS SKILL when the user mentions ANY of these actions: "delete slide", "remove slide", "add slide", "insert slide", "create new slide", "new slide between", "get rid of slide", "fix gaps", "renumber slides", OR when they confirm/answer questions about slide deletion/addition (e.g., "yes delete slide 6", "add a slide after 5"). CRITICAL - NEVER manually edit slides.md or rename slide files yourself - this skill uses the manage-slides.py script which handles automatic renumbering, gap detection/fixing, git-aware operations, and slide number vs position conversion. AUTO-TRIGGER IMMEDIATELY when user wants to modify slide count, order, or numbering. This skill is the ONLY correct way to add/delete slides.
Slide Quality Assessment
rhuss
This skill should be used when the user asks to "analyze slide quality", "review slide", "check slide design", "optimize slide", "improve slide content", "assess slide clarity", or needs evidence-based quality evaluation using the 12-point checklist for presentation slides.
enhanced-commands
Terryc21
Enhanced list of custom Claude commands for iOS and macOS Swift projects with examples and output locations.
form-ux-design
peterbamuhigire
Cross-platform form UX/UI patterns for web (Bootstrap 5/Tabler) and Android (Jetpack Compose). Covers field anatomy, validation, error states, multi-step wizards, accessibility, touch-friendly inputs, and submission workflows. Use when building any form — registration, data entry, settings, checkout, search, filters, or clinical forms. Companion to webapp-gui-design, healthcare-ui-design, pos-sales-ui-design, and jetpack-compose-ui skills.
api-error-handling
peterbamuhigire
"Comprehensive, standardized error response system for PHP REST APIs with SweetAlert2 integration. Use when building REST APIs that need consistent error formatting, specific error message extraction from database exceptions, validation error handling, and seamless frontend integration. Includes PDOException parsing, business rule extraction, and complete SweetAlert2 error display patterns."
pr-review
freenet
Executes comprehensive PR reviews following Freenet standards. Performs four-perspective review covering code-first analysis, testing, skeptical review, and big-picture assessment.
ai-error-handling
peterbamuhigire
Validation and error handling for AI-generated code. Use when verifying AI output, building production code, or ensuring code correctness. Enforces automatic quality checks and validation loops.
ai-error-prevention
peterbamuhigire
Error prevention strategies for AI-assisted development. Use when working with Claude to minimize hallucinations, incomplete solutions, and wasted tokens. Enforces "trust but verify" workflow.
screenshot-cli
Mic92
Take screenshots. Use when needing to see the screen or debug graphical issues.