性能

cuda-kernels

huggingface

"Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations."

reflexion:reflect

NeoLabHQ

Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification

moai-workflow-thinking

modu-ai

Sequential Thinking MCP and UltraThink mode for deep analysis, complex problem decomposition, and structured reasoning workflows. Use when performing multi-step analysis, architecture decisions, technology selection trade-offs, breaking change assessment, or when --ultrathink flag is specified. Do NOT use for simple decisions or straightforward implementation tasks.

hot-paths

ag-grid

'AG Charts runtime hot paths: which files run per datum, per frame or per interaction, the invariants each tier must hold, and how to evidence a performance claim. Use when reviewing a change that touches series, scene, data-model, scale, interaction or DOM code, when asked whether a diff will cost performance, or when deciding which benchmark to run.'

investment-suitability

JoelLewis

"Investment suitability obligations: FINRA Rules 2111/2090, reasonable-basis/customer-specific/quantitative suitability, product-specific concerns, household considerations."

trade-execution

JoelLewis

"Trade execution and best execution: venue selection, smart order routing, execution algorithms, transaction cost analysis (TCA), market microstructure, and best execution obligations."

gips-compliance

JoelLewis

"GIPS compliance: composite construction, performance presentation, verification, error correction, pooled funds, wrap/SMA programs, and advertising guidelines under the CFA Institute Global Investment Performance Standards."

working-memory-protocol

Bitterbot-AI

Use when deciding what to record with working_memory_note, when the user says "remember this" or corrects you, or when a Crystal Pointer matches the topic. Not for answering from memory (use memory_search).

engineering-culture

RefoundAI

Help users build strong engineering culture. Use when someone is improving developer experience, fostering technical excellence, designing engineering practices, or scaling an engineering organization.

conducting-user-interviews

RefoundAI

Help users run better customer and user interviews. Use when someone is preparing for user research, planning discovery interviews, writing interview questions, analyzing interview findings, or trying to understand customer needs.

having-difficult-conversations

RefoundAI

Help users navigate tough feedback, performance conversations, and conflict. Use when someone needs to give hard feedback, have a performance conversation, fire someone, address conflict with a colleague, or deliver disappointing news like a denied promotion.

building-sales-team

RefoundAI

Help users build and scale their sales organization. Use when someone is hiring their first salespeople, deciding when to bring on sales leadership, structuring sales compensation, or transitioning from founder-led sales.

building-a-promotion-case

RefoundAI

Help users get promoted at work. Use when someone is preparing for a promotion conversation, building their case for advancement, trying to understand what's blocking their promotion, or figuring out how to get to the next level in their career.

evaluating-trade-offs

RefoundAI

Help users make better decisions between competing options. Use when someone is weighing pros and cons, comparing alternatives, struggling with a difficult choice, deciding between speed and quality, or asking "should we do X or Y?"

code-review-large

breaking-brake

In-depth code review for large PRs (>500 lines). Full analysis including architecture, performance, security, and maintainability.

research

QuixiAI

How to research topics using web tools

humanizer

QuixiAI

Detect and remove AI writing patterns to produce natural, human-sounding prose

meeting-prep

QuixiAI

Prepare briefings for upcoming calendar events with attendee context and relevant memories

daily-briefing

QuixiAI

Compile a comprehensive daily briefing from calendar, contacts, goals, and recent activity

Marketing Campaign Analysis

https-deeplearning-ai

agent-creator

hotovo

Create and configure AiderDesk agent profiles by defining tool groups, approval rules, subagent settings, and provider/model selection. Use when setting up a new agent, creating a profile, or configuring agent tools and permissions.

reference-core

angular

Explains the mental model and architecture of the code under packages/core. You MUST use this skill any time you plan to work with code in packages/core

analyzing-marketing-campaign

https-deeplearning-ai

Analyze weekly marketing campaign performance data across channels. Use when analyzing multi-channel digital marketing data to calculate funnel metrics (CTR, CVR) and compare to benchmarks, compute cost and revenue efficiency metrics (ROAS, CPA, Net Profit), or get budget reallocation recommendations based on performance rules.

gtd-coach

iamzifei

Personal GTD (Getting Things Done) coach that helps users achieve their annual goals. Use when users mention goals, plans, daily tasks, productivity, time management, task tracking, reviews, or need help breaking down objectives into actionable steps. Automatically remembers user's goals and progress across conversations. Supports multiple languages.