Loading...
Loading...
Found 913 Skills
Context-gathering for finding files to read. Maps codebase structure, returns overview + prioritized file list with line ranges. Thoroughness: quick for lookups, medium for bugs/features, thorough for multi-area, very-thorough for architecture audits. Triggers: explore, find files, where is, how does X work.
Stop your AI from making things up. Use when your AI hallucinates, fabricates facts, isn't grounded in real data, doesn't cite sources, makes unsupported claims, or you need to verify AI responses against source material. Covers citation enforcement, faithfulness verification, grounding via retrieval, and confidence thresholds.
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.
This skill should be used when reviewing pull requests, performing comprehensive code review, analyzing code changes before merge, or when the user asks for thorough/ultra-critical code review. Performs EXTREMELY CRITICAL 6-pass analysis identifying runtime failures, code consistency issues, architectural problems, environment compatibility risks, and verification strategies. Posts structured review as GitHub PR comment. Use when user asks to "review PR", "review this code", "review changes", "check this PR", "analyze PR", "post review", or for Phase 3 of devflow. Supports parallel review mode with multiplier (code-review-3, code-review 6X) for consensus-based reviews. This is an ultra-critical reviewer that does not let things slip and desires only perfection.
This skill should be used when the user asks to "send a payment", "check balance", "list transactions", "create a quote", "manage customers", "create external account", "what currencies does Grid support", "how do I use the Grid API", "send money to [country]", "pay [UMA address]", "send to CLABE", "send to PIX", "send to IBAN", "send to UPI", "fund sandbox account", "test a payment", "on-ramp", "off-ramp", "convert crypto to fiat", "convert fiat to crypto", "look up UMA", "real-time quote", "JIT funding", or any payment operations using the Grid API CLI.
Apple HIG guidance for input methods and interaction patterns: gestures, Apple Pencil, keyboards, game controllers, pointers, Digital Crown, eye tracking, focus system, remotes, spatial interactions, gyroscope, accelerometer, and nearby interactions. Use when asked about: "gesture design", "Apple Pencil", "keyboard shortcuts", "game controller", "pointer support", "mouse support", "trackpad", "Digital Crown", "eye tracking", "visionOS input", "focus system", "remote control", "gyroscope", "spatial interaction". Also use when the user says "what gestures should I support," "how do I add keyboard shortcuts," "how does input work on Apple TV," "should I support Apple Pencil," or asks about input device handling. Cross-references: hig-components-status, hig-components-system, hig-technologies for VoiceOver and Siri.
Analyzes changes since last release and updates CHANGELOG.md ONLY. Does NOT trigger releases.
Delegate tasks to the cost-effective opencode/glm-5 model. Use when you need inexpensive task execution, simple research, or delegating work that doesn't require the most powerful models.
Systematic codebase investigation to extract architectural patterns and implementation details from an existing project, with findings persisted for long-term reuse. Use when the user wants to explore an open-source or existing codebase to understand how it works and inform the development of a new project. Triggers include: "explore this codebase", "investigate this repo", "how does X implement Y", "I want to build X, study how Y does it", "deep dive into this project", "understand how this works".
Uniwind — Tailwind CSS v4 styling for React Native. Use when adding, building, or styling components in a React Native project that uses Tailwind with className. Triggers on: className on React Native components, Tailwind classes in RN code, global.css with @import 'uniwind', withUniwindConfig, metro.config.js with Uniwind, withUniwind for third-party components, useResolveClassNames, useCSSVariable, useUniwind, dark:/light: theming, platform selectors (ios:/android:/native:/web:/tv:), data-[prop=value] selectors, responsive breakpoints (sm:/md:/lg:), tailwind-variants, tv() component variants, ScopedTheme, Uniwind.setTheme, Uniwind.updateCSSVariables, Uniwind.updateInsets, @layer theme, @variant, @theme directive, @theme static, @utility, CSS variables in React Native, accent- prefix pattern, colorClassName, tintColorClassName, contentContainerClassName, Uniwind Pro (animations, transitions, shadow tree, native insets), safe area utilities (p-safe/pt-safe/-safe-or-/-safe-offset-), gradients in RN, custom CSS classes, hairlineWidth(), fontScale(), pixelRatio(), light-dark(), OKLCH colors, cn utility, tailwind-merge, HeroUI Native, react-native-reusables, Gluestack. Also triggers on: "styles not applying", "className not working", "audit Uniwind setup", "check my config", "add a component", "style a component". Does NOT handle NativeWind-to-Uniwind migration — use the migrate-nativewind-to-uniwind skill for that.
Use when the user wants to validate that implemented code matches its specifications, generate integration tests from feature files, or check if code still satisfies existing scenarios. Trigger after implementation completes a feature. Also use when the user asks "does the code do what we specified?" or "generate tests from the feature files".
OpenHarmony Distributed Soft Bus Code Security Review Expert - Comprehensive inspection of C/C++ code against secure coding standards and logging specifications. Covers over 40 security rules, including key areas such as pointer safety, memory management, lock management, and sensitive information protection. Provides cross-file call analysis and control flow analysis, generating detailed code review reports. Only triggered when user input contains "软总线安全卫士" (Soft Bus Security Guard). ⚠️ Important: This skill is a read-only review tool and does not modify source files.