Results for “attention-mechanics”

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Expert in creating opening lines, thumbnails, and hooks that stop the scroll. Covers curiosity gaps, pattern interrupts, emotional triggers, and platform-specific hooks. Knows how to earn attention in the first 3 seconds without resorting to clickbait. Use when "hook, opening line, scroll stopper, headline, first line, attention grab, thumbnail, clickable, " mentioned.

Creates digital banners for social, display, hero, and email formats, applying behavioral science principles to maximize attention and conversion.

Econometrics skill for panel data models. Activates when the user asks about: "panel data", "fixed effects", "random effects", "Hausman test", "within estimator", "between estimator", "two-way fixed effects", "clustered standard errors panel", "FE model", "RE model", "pooled OLS", "unobserved heterogeneity", "panel regression", "first difference estimator", "entity fixed effects", "time fixed effects", "面板数据", "固定效应", "随机效应", "豪斯曼检验", "双向固定效应", "面板回归", "个体效应", "时间效应", "一阶差分"

Diverga Memory System v7.0 - Context-persistent research support with checkpoint auto-trigger and cross-session continuity. Triggers: memory, remember, context, recall, checkpoint, decision, persist, 기억, 맥락, 세션, 체크포인트

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Econometrics skill for panel data models. Activates when the user asks about: "panel data", "fixed effects", "random effects", "Hausman test", "within estimator", "between estimator", "two-way fixed effects", "clustered standard errors panel", "FE model", "RE model", "pooled OLS", "unobserved heterogeneity", "panel regression", "first difference estimator", "entity fixed effects", "time fixed effects", "面板数据", "固定效应", "随机效应", "豪斯曼检验", "双向固定效应", "面板回归", "个体效应", "时间效应", "一阶差分"

Diagnose and fix retention problems using the Fogg Behavior Model (B=MAP), covering motivation, ability, prompts, and tiny habits.

Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task. Use when developing students' thinking-about-thinking during independent work.

Animation theory covering the 12 principles of animation and timing guidance. Use when designing motion, choosing easing approaches, or improving animation quality.

Routes requests into the correct obsidian-mind mode: install, daily session loop, capture, review, maintenance, multi-agent wiring, or semantic search, using a ready-made Obsidian vault template for persistent agent memory.

Modify a classroom task with language scaffolds that preserve cognitive demand for EAL learners. Use when adapting existing tasks for students at different English proficiency levels.

Build and query AI-powered knowledge bases from claude-mem observations, enabling focused conversational sessions on specific topics.

Designs persistent memory architectures for AI agents, covering cross-session knowledge retention, entity tracking, temporal validity, graph/vector retrieval, and memory consolidation.

Watches conversations continuously and compresses them into prioritized notes, consolidating and recovering missed sessions with multiple redundancy layers.

Guides daily mindfulness practice to reduce stress, improve focus, and build emotional regulation through structured routines and reflection.

Slow down interpretation from observation to action. Use when students or adults need to examine assumptions in conflict, dialogue, or inquiry.

Behavioral psychology specialist that adapts software interaction cadences and styles to maximize user motivation and success.

当需要将分散的注意力系统性地引导至个人成长方向，并为好奇心提供明确指引时

Temporal interval algebra for reasoning about time relationships in planning and knowledge representation

Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use windags-architect), specific tool implementation.

Persists and recalls agent knowledge across sessions using four approaches: static KB, company wiki, persistent memory, and session brain.

Compresses conversation transcripts into prioritized notes using an LLM observer, consolidates them when they grow, and recovers any missed sessions without a database or vector store.

Design a wise systems intervention from an existing analysis. Maps proposed actions against Meadows' leverage points, checks for unintended consequences, and generates alternatives.

Memory (aeaf-memory)

Extends effective context capacity through strategic compression, masking, caching, and partitioning techniques.

当感到生活失控、注意力分散，需要系统性重获专注力时

Econometrics skill for Difference-in-Differences (DID) analysis. Activates when the user asks about: "difference in differences", "DID", "DiD", "diff-in-diff", "parallel trends", "treatment group", "control group", "pre-treatment", "post-treatment", "policy evaluation", "natural experiment", "staggered DID", "event study regression", "two-way fixed effects DID", "callaway santanna", "sun and abraham", "双重差分", "倍差法", "平行趋势", "处理组", "对照组", "政策评估", "事件研究", "交错DID", "渐进处理"

Diagnose and fix retention problems using behavior design (B=MAP). Use when the user mentions "users drop off", "activation rate", "onboarding friction", "retention metrics", "why users dont complete", "churn analysis", "user activation", or "aha moment". Also trigger when analyzing cohort retention curves, designing activation milestones, reducing time-to-value for new users, or investigating why users stop after their first session. Covers the Ability Chain, prompt design, and tiny behaviors that compound. For habit loops and variable rewards, see hooked-ux. For intrinsic motivation, see drive-motivation.

Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".

Retrieve task-relevant project and global memory without loading everything. Load when the user asks what we decided, recall prior context, find memory about a feature, explain past rationale, resume a task, or check deferred ideas.

Mine winning ad angles, hooks, and creative patterns from top-performing ads

Econometrics skill for Difference-in-Differences (DID) analysis. Activates when the user asks about: "difference in differences", "DID", "DiD", "diff-in-diff", "parallel trends", "treatment group", "control group", "pre-treatment", "post-treatment", "policy evaluation", "natural experiment", "staggered DID", "event study regression", "two-way fixed effects DID", "callaway santanna", "sun and abraham", "双重差分", "倍差法", "平行趋势", "处理组", "对照组", "政策评估", "事件研究", "交错DID", "渐进处理"

AutoAugment: Learning Augmentation Strategies from Data