Loading...
Loading...
Found 575 Skills
You must use this when seeking cross-domain analogies, applying first-principles reasoning, or overcoming creative bottlenecks.
TypeORM for TypeScript/JavaScript. Covers entities, repositories, and relations. Use with SQL databases. USE WHEN: user mentions "typeorm", "@Entity", "Repository", "DataSource", "QueryBuilder", "typeorm migration", asks about "decorators for database", "active record pattern", "entity relationships", "typeorm relations" DO NOT USE FOR: Prisma projects - use `prisma` skill; Drizzle - use `drizzle` skill; SQLAlchemy (Python) - use `sqlalchemy` skill; raw SQL - use `database-query` MCP; NoSQL - use `mongodb` skill; Sequelize - not supported
Orchestrates comprehensive cognitive thinking patterns for complex problem-solving. Analyzes tasks to select optimal pattern(s) from foundational, reasoning, creative, metacognitive, specialized, and neurodivergent categories. Chains multiple patterns when needed and validates outputs before responding.
Install AI UI components from the Elements registry. Use when user needs chat interfaces, agentic UIs (tool calls, reasoning, plans), multi-agent dashboards, or AI devtools. Triggers on "AI component", "chat UI", "agent UI", "tool call component", "streaming text", "agentic", "multi-agent", "AI SDK", "chat input", "message bubble", "thinking indicator".
Autonomous co-pilot — agent formulates goal from natural language, enables lock mode with SessionCopilot reasoning, works until goal is achieved.
Perses plugin scaffolding and creation: select plugin type (Panel, Datasource, Query, Variable, Explore), generate with percli plugin generate, implement CUE schema and React component, test with percli plugin start, build archive with percli plugin build. Use for "create perses plugin", "new panel plugin", "new datasource plugin", "perses plugin scaffold". Do NOT use for dashboard creation (use perses-dashboard-create).
[QwenCloud] Understand images and videos with Qwen vision models. TRIGGER when: user wants to analyze, describe, or extract information from images or videos, OCR text extraction, chart/table reading, visual reasoning, multi-image comparison, screenshot understanding, video comprehension, or explicitly invokes this skill by name (e.g. use qwencloud-vision). DO NOT TRIGGER when: user wants to generate/create images (use qwencloud-image-generation), generate videos (use qwencloud-video-generation), text-only tasks without visual input, or non-Qwen vision tasks.
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, designing systems, or making architectural decisions. Enters plan mode, reads all available docs, explores the codebase deeply, then interviews the user relentlessly with ultrathink-level reasoning on every decision until a shared understanding is reached. Produces a validated design spec before any implementation begins. Triggers on feature requests, design discussions, refactors, new projects, component creation, system changes, and any task requiring design decisions.
Apply a latticework of mental models from multiple disciplines to improve decision quality. Use this skill when the user needs to think more clearly, avoid cognitive blind spots, apply cross-disciplinary reasoning, or evaluate a complex decision from multiple angles — even if they say 'how should I think about this', 'what am I missing', 'give me a different perspective', or 'what frameworks apply here'.
Concurrency debugging skill for diagnosing data races and deadlocks. Use when reading TSan race reports, debugging deadlocks with GDB thread inspection, analyzing lock-order graphs with Helgrind, identifying std::atomic misuse patterns, or reasoning about happens-before in C++ and Rust. Activates on queries about data races, TSan reports, deadlocks, Helgrind, lock ordering, thread sanitizer output, or atomic ordering issues.
A method for iteratively improving text instructions for agents (skills / slash commands / task prompts / CLAUDE.md sections / code generation prompts) by having unbiased executors run them, then evaluating from both perspectives (executor self-report + instruction-side metrics). Repeat until improvement plateaus. Use immediately after creating or significantly revising a prompt or skill, or when you suspect the reason an agent isn't behaving as expected is due to ambiguity in the instructions.
Adversarial stress-test of a /think intelligence brief. Reads the think output markdown, then deploys 5-7 of the same analytical frameworks — but each one is hunting exclusively for reasons the recommendation is wrong, the conviction is unearned, and the idea will fail. Every framework becomes a prosecutor, not a judge. Surfaces the strongest kill shots, identifies which parts of the original brief are load-bearing but unverified, and produces a Red Team Report with a survival verdict. Use when the user says "red-team this", "attack this", "poke holes", "steel-man the opposition", "why is this a bad idea", "/red-team", or presents a /think brief they want stress-tested.