SkillCheatSheet
optimizing-attention-flash
An AI agent skill from Orchestra-Research/AI-Research-SKILLs, scored 70 out of 100 by code.
Code score by group
It loses the most points in Done criteria (11), the group that checks whether there is a checklist and a step that verifies the work.
What the author says it does
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.
This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.
- Repository
- Orchestra-Research/AI-Research-SKILLs
- Folder
- 10-optimization/flash-attention
- License
- MIT
- GitHub stars
- 14,480
- SKILL.md lines
- 368
- Other files
- 2
Add optimizing-attention-flash to your agent
npx skills add Orchestra-Research/AI-Research-SKILLs --skill optimizing-attention-flashThe command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.
Labelled for
More skills from Orchestra-Research/AI-Research-SKILLs
-
pytorch-fsdp2
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU…
Verified82B -
systems-paper-writing
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific ch…
Verified82B -
evolving-ai-agents
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing…
77B -
brainstorming-research-ideas
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking…
76B -
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architect…
74B -
miles-rl-training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignme…
73B -
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight pr…
73B -
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, o…
72B
All skills in Orchestra-Research/AI-Research-SKILLs
Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.