Loading...
Loading...
Found 1,342 Skills
Prompt Optimizer. Refine draft-level prompts into high-quality ones, generating four strategic variants (A/B/C/D) for users to choose from. Applicable to all scenarios requiring prompt optimization—when users say 'help me optimize this prompt', 'how to write this prompt better', 'the AI didn't understand me, help me clarify this requirement', 'improve the prompt', 'polish the prompt', or mention 'prompt engineering'. Also suitable when users feel their instructions are too vague and need the AI to understand more accurately. It should be invoked whenever users express the intention of 'making instructions clearer/more effective', regardless of whether they use the word 'prompt'.
Helps AI coding assistants write modern Jetpack Compose: correct state, side effects, performance-aware modifiers, Navigation 3, Paging 3 in Compose, coroutines on lifecycle, animations, UI tests, focus/keyboard navigation, Compose Multiplatform boundaries, idiomatic Kotlin, and well-shaped composable APIs. Targets the mistakes LLMs actually make in Compose code. Use when reading, writing, or reviewing Compose projects.
Diagnoses Workload Identity Federation for GKE authentication failures for Pods (403 "iam.serviceAccounts.getAccessToken" / permission denied, "could not find default credentials", or GKE metadata server unreachable) by verifying cluster and node-pool Workload Identity configuration, the Kubernetes ServiceAccount (KSA) to IAM binding (direct principal binding and legacy Google ServiceAccount impersonation), target-resource IAM roles, and gke-metadata-server health. Use when a Pod cannot authenticate to Google Cloud APIs even though Workload Identity is expected to be in effect. Don't use for in-cluster Kubernetes RBAC errors (API-server authorization), general workload crashes (use gke-workload-troubleshooting), or Workload Identity setup and hardening (use gke-workload-security).
The repo front-door for a Flutter/Dart app — the cross-cutting house rules (feature-first layered MVVM, immutable state with a single write path, Riverpod 3.x for state + DI, typed Result/Failure errors, dumb widgets, injected side effects, complexity limits) plus a routing table that sends each task to its deep-dive skill and a recommended feature build order. Use at the start of any Flutter/Dart work, before writing or reviewing a feature, when deciding which layer or package code belongs in, when unsure which skill governs a task (architecture, state, widgets, persistence, testing, i18n, design), or when onboarding to the conventions.
WeWrite Data Review Module: Pulls reading/sharing/like data from WeChat Official Account articles, backfills historical records, and provides adjustment suggestions for topic selection, titles, and frameworks. Trigger keywords: check article data, how's the article data, effect review, check performance, how's the view count. Requires Official Account/WeWrite context; should not be triggered by generic "data analysis".
Compose look-and-feel traps: theme and colour tokens, artwork palettes, gradients and scrims, shimmer, glass and particle effects, animation, image loading, charts and stats displays (percent changes, shares, buckets). Use when a visual bands, pops, freezes or misleads.
Expose a Factorial Code process to Factorial as a Factorial Action — the `factorial` block in a process's metadata.json (master switch, awaitResult, requiredPolicies, and the uiTrigger / form / agentTool / backend entry points), the Factorial One tool contract (description, effect, whenToUse, whenNotToUse, preconditions, doesNotDo, degradation, simulatesFor), the reserved lifecycle slugs, the parameters schema as the contract with Factorial, and how the legacy `form` / `uiTrigger` blocks are kept mirrored. Use when configuring how Factorial reaches a process, writing an agent tool contract, or filling the "Trigger from Factorial" section of a process.
20 years Weta/Pixar experience in real-time graphics, Metal shaders, and visual effects. Expert in MSL shaders, PBR rendering, tile-based deferred rendering (TBDR), and GPU debugging. Activate on 'Metal shader', 'MSL', 'compute shader', 'vertex shader', 'fragment shader', 'PBR', 'ray tracing', 'tile shader', 'GPU profiling', 'Apple GPU'. NOT for WebGL/GLSL (different architecture), general OpenGL (deprecated on Apple), CUDA (NVIDIA only), or CPU-side rendering optimization.
Systematic code refactoring following Martin Fowler's catalog. Methodologies: characterization tests, Red-Green-Refactor, incremental transformation. Capabilities: SOLID compliance, DRY cleanup, code smell detection, complexity reduction, legacy modernization, design patterns, functional programming patterns. Actions: refactor, extract, inline, rename, move, simplify code. Keywords: refactor, SOLID, DRY, code smell, complexity, extract method, inline, rename, move, clean code, technical debt, legacy code, design pattern, characterization test, Red-Green-Refactor, functional programming, higher-order function, immutability, pure function, composition, currying, side effects. Use when: improving code quality, reducing technical debt, applying SOLID principles, fixing DRY violations, removing code smells, modernizing legacy code, applying design patterns.
Extract and structure fuzzy product ideas into validated problem statements, target users, and jobs-to-be-done. Use when a user has a raw idea, concept, or solution in mind but hasn't clearly articulated the problem, target user, or assumptions. This skill helps users communicate context to coding agents more effectively, reducing iteration cycles and "that's not what I meant" moments.
Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight. Use when the user mentions adding animation, transitions, micro-interactions, motion design, hover effects, or making the UI feel more alive.
MUST be used whenever reviewing a Dune app for bugs, missing error states, unhandled promise rejections, or incorrect edge-case behaviour. Do NOT skip — run every step when the user asks for a correctness review, bug check, error handling audit, or robustness review. Triggers: correctness, error handling, bug, edge case, crash, unhandled, null, undefined, empty state, loading state, error boundary, try catch, async error, useEffect cleanup, type guard, runtime error, robustness.