发现 Skills

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Develops with Turso's distributed SQLite (libSQL) platform. Use when working with the @libsql/client driver — leverage edge replicas for low-latency reads, route writes to the primary, and use parameterized queries plus a versioned migration tool (drizzle-kit, atlas) for schema changes.

Generate Flutter applications using Clean Architecture with a feature-first structure, Riverpod state management, Dio + Retrofit for networking, and fpdart error handling. Use this skill when creating Flutter apps, implementing features with clean architecture patterns, setting up Riverpod providers, handling data with the Either type for functional error handling, making HTTP requests with type-safe API clients, or structuring projects with domain/data/presentation layers. Triggers include "Flutter app", "clean architecture", "Riverpod", "feature-first", "state management", "API client", "Retrofit", "Dio", "REST API", or requests to build Flutter features with separation of concerns.

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.

Complete AI agent operating system setup with Kanban task management. Use when setting up multi-agent coordination, task tracking, or configuring an agent team. Includes theme selection (DBZ, One Piece, Marvel, etc.), workflow enforcement (all tasks through board), browser setup, GitHub integration, and memory enhancement (Supermemory, QMD).

Control Athom Homey smart home devices via local (LAN/VPN) or cloud APIs. List/control devices, trigger flows, query zones. Works with Homey Pro, Cloud, and Bridge.

Reviews or implements Clean Architecture / Hexagonal Architecture (Ports & Adapters) and DDD tactical patterns for Java projects. Use when user asks to "apply clean architecture", "implement hexagonal architecture", "add ports and adapters", "apply DDD", "refactor to clean arch", "review architecture", or "add value objects".

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

Distributed traces, spans, service dependencies, and request flow analysis. Use when investigating span-level details, failures, performance bottlenecks, or trace correlation. Trigger: "trace analysis", "slow requests", "failed spans", "service dependencies", "distributed trace", "span details", "HTTP status codes in traces", "database query spans", "messaging spans", "gRPC calls", "Lambda cold starts", "trace ID lookup", "exception analysis", "correlate logs and traces", "request attributes". Do NOT use for explaining existing queries, product documentation or configuration questions, service-level RED metrics (use dt-obs-services), log searching (use dt-obs-logs), or problem analysis (use dt-obs-problems).

Interface and type-surface design work. Use when assignments define or change API contracts, type signatures, or behavioral guarantees.

ALWAYS use this skill when the user asks to manage Claude Code configuration, including MCP servers, permissions, hooks, skills, slash commands, or application preferences. Provides guidance for ~/.claude/settings.json (user config), .mcp.json (MCP servers), CLAUDE.md (memory), and custom commands/skills. Triggers include "configure Claude", "add MCP", "setup hooks", "permissions", "settings", "CLAUDE.md", "slash commands", "skills", or any config management request.

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this". (gstack)

../../../skills/claude/model-router/SKILL.md

../gstack/qa/SKILL.md

This skill should be used when handling a sqlglot version bump, updating sqlglot compatibility, working on a renovate/sqlglot branch, fixing sqlglot-related test failures, or migrating functions from invoke_anonymous_function to sqlglot expression classes.

Post QA handoff comment to ADO with QA page URLs, prerequisites, and wiki link. Reuses test page from /aem-doc-gen if available, otherwise creates its own on QA AEM. Use after /aem-doc-gen and /dx-doc-gen.

Run any question, decision, or artifact through a council of 3 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Adapted from Karpathy's LLM Council. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'council the plan', 'council the implementation'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff. DO trigger when the user presents a genuine decision with stakes, multiple options, or an artifact they want pressure-tested from multiple angles.

Assign or remove Discord roles based on emoji reactions to a designated message in a specific channel. Supports both standard and custom emojis via a mapping object and includes optional user feedback.

Create a FastAPI endpoint to handle video file uploads, save them asynchronously in chunks, run YOLOv8 object tracking, and return processed detection results with bounding boxes and confidence scores.

Use for anything YouTube: search by name or phrase, transcripts (single video, playlist, channel), audio extraction (WAV / MP3 / any ffmpeg format), clip trimming, channel listing, and LLM summarisation. Handles the "I only have an artist / topic name, find and download" flow by chaining `search` → `audio`. Fully integrated as `af youtube <subcommand>` — no external wrapper needed. Chains cleanly into `note-taker`, `knowledge-base`, and `test-taker`.

Provides principles and techniques for fixing bugs, ensuring that fixes are correct, clean, and maintainable. Use this when debugging, repairing issues, reviewing bug fixes, or when you need guidance on proper bug resolution.

End-to-end Stake game development workflow for math, RGS contract, frontend playback, and compliance gating. Use when building or updating Stake games, defining game modes and RTP targets, validating generated books/index metadata, validating event streams, integrating frontend event playback, implementing RGS communication and replay mode, or preparing publication checks including social-language and jurisdiction requirements.

Converts demo UIs into believable, end-to-end product workflows. Use when building, reviewing, or finishing apps, dashboards, CRUD flows, forms, onboarding, checkout, settings, auth-like surfaces, data tools, AI tools, integrations, or any UI that must behave like a real app instead of a static template. Composes after no-slop/perfect-design to make the interface operational, truthful, stateful, validated, persistent, and verifiable.