Loading...
Loading...
Found 4,085 Skills
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
GPU kernel profiling workflow across supported kernel implementation languages. Provides commands for all 4 profiling modes (annotation, event, ncu, nsys), metric interpretation tables, bottleneck identification rules, and the output contract for returning compact results to the orchestrator. Use when: (1) profiling a kernel version, (2) interpreting profiling artifacts/reports, (3) comparing kernel versions, (4) identifying bottlenecks and optimization opportunities, (5) documenting performance in the development log.
Audit all installed agent skills across global and project scopes to find and remove duplicate skills. Use when asked to audit my skills, deduplicate skills, clean up skills, or find duplicate skill installations. Don't use for creating or improving a single skill, running skill evals, or packaging/publishing skills.
Plan how to slice a non-trivial coding task across parallel subagents. Returns a dispatch plan (file assignments, dependencies, output-format contracts) — the main Agent then executes it with the Agent tool + `isolation: "worktree"`. Invoke only when work justifies multi-agent overhead: (a) greenfield 0→1 across multiple independent modules, (b) change touches ≥3 modules, or (c) ≥5 files each with >50 lines of diff. Small changes write inline.
Operate, troubleshoot, and explain ERDA CI/CD workflows through erda-cli. Use when users need help running pipelines, checking status, reading logs, reviewing build history, or diagnosing delivery failures across the build and deploy path.
Sticky and fixed positioning keeps critical UI persistent as the user scrolls — headers at the top, toolbars at the bottom on mobile. Use deliberately: too many fixed layers create visual noise and reduce content area. Use when designing navigation headers, bottom toolbars, floating action buttons, or table column headers.
Disney's 12 animation principles, cinematic storytelling techniques, and comic book conventions apply to web UI — used subtly, they make interfaces feel alive, intentional, and emotionally resonant. Use when designing transitions, micro-interactions, onboarding flows, scroll animations, or any motion in the UI.
NestJS reference skill: modules, controllers, providers, DTOs with class-validator, TypeORM/Prisma, guards, interceptors, pipes, queues (BullMQ), WebSockets, microservices, testing, OpenAPI, and CLI scaffolding. Use when the task touches NestJS application code and should follow the project's module-based architecture.
Upgrade any Pulumi provider to a newer version and reconcile the resulting diff. Use when users want to upgrade or update a provider (including editing package.json, requirements.txt, pyproject.toml, go.mod, or Pulumi.yaml to bump a provider SDK), check for breaking changes before or during an upgrade, fix resources that broke after a provider upgrade, or resolve unexpected replacements, creates, or deletes in a post-upgrade preview. Applies to all providers (aws, azure-native, gcp, kubernetes, aws-native, cloudflare, datadog, etc.) — not just Tier 1. Do NOT use for querying which stacks use what package versions; use skill `package-usage` for cross-stack audits. Do NOT use for general infrastructure tasks.
Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized, or asks "does this follow clean architecture?", "why does everything depend on everything?", "are our layers correct?", "where should this code live?". Also triggers for onboarding requests: "explain this codebase to a new developer" or "give me a codebase tour" (use onboarding mode). Also triggers when user mentions: dependency inversion / hexagonal architecture / bounded contexts / circular imports / tangled dependencies / module coupling / package structure / spaghetti code / directory layout. Use this skill proactively when project structure, module boundaries, or architectural decisions are discussed — even without the word "audit". Do NOT trigger for: PR-level code review (use brooks-review) or line-level refactoring questions — this skill analyzes structural/module-level concerns, not individual functions.
Detects framework-specific anti-patterns, convention violations, and idiom misuse across PHP/Laravel, React/Next.js, and Python/Django/FastAPI codebases. Loads framework-specific reference guides and checks against framework conventions. Generates severity-scored findings with copy-pasteable fix prompts. Trigger phrases: "framework review", "framework check", "laravel best practices", "react best practices", "framework audit", "framework-specific review".
Steedos Server real-time WebSocket system using Socket.IO. Covers the AppGateway (@WebSocketGateway), connection authentication via cookies, room-based event routing (tenant-scoped rooms), subscribe/unsubscribe events, metadata change notifications, record change events, notification broadcasting, and Moleculer event integration for cross-service real-time communication.