Daniel AvilaCreated claude-code-templates, 32k+ GitHub stars341 installs on skills.shOptimizing Attention Flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction.
3 static scans, 0 counted findings.
Edge checks it again each time your agent loads it.
What 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.
Why Daniel Avila
Co-founder of CodeGPT. Each fact links its public source.
- 32k+ GitHub stars on claude-code-templates
His CLI for configuring and monitoring Claude Code has over 32,000 stars.
GitHub - Co-founder of CodeGPT, 2M+ downloads
He co-founded CodeGPT, which has over 2 million downloads.
Personal site
How it works
- 1Copy
Try for free gives you one prompt.
- 2Paste
Paste it into Claude Code, Codex or Cursor.
- 3Ask
Ask for the outcome. Your agent loads Optimizing Attention Flash.
3 static scans, 0 counted findings.
Security state at 2026-09-30: reviewed. Static scans check the code, not how well the skill works.
State definitionsSelect the Files tab to load SKILL.md.
Skill details
Security scansReviewed
3 static scans, 0 counted findings. Security state at 2026-09-30: reviewed. Edge checks it again each time your agent loads it.
Edge static checks (Edge-run): edge-static/1.0.1. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Raw findings: .
Cisco skill-scanner (Edge-run): cisco-skill-scanner/2.1.0. Scope: Local static, YARA, pipeline and behavioral analyzers; no LLM or AI Defense analysis. Raw findings: 3.
Semgrep Edge rules (Edge-run): semgrep/1.178.0+edge-rules.c15016a36fd3+offline-v1. Scope: Six Edge-authored static rules with Semgrep CE; offline execution and metrics disabled. Semgrep-maintained rules excluded. Raw findings: .
- Edge static checks
- Pass · 0 counted findings · 2026-09-27
- Cisco skill-scanner
- Pass · 0 counted findings · 2026-09-27
- Semgrep Edge rules
- Pass · 0 counted findings · 2026-09-27
Creator, source & licencedavila7
From the davila7 public repository. Edge did not write or edit this skill.
- Repository
- davila7/claude-code-templates
- Skill file
- View source at revision
- Revision
- 6af7cdf57b810aca5e544a0f695bf058f1c2a744
- Package hash
- sha256:6e2b95f9f6029a3ee34cf31b4f044633487916e14aca907c2ba178be3fbf9748
- Licence
- MIT
- Description
- 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.
Quoted from the skill’s own description
Read skill files3 files
3 files, 24.2 KB at revision 6af7cdf57b81.
Questions about Optimizing Attention Flash
What does Optimizing Attention Flash do?
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Published by Daniel Avila (davila7/claude-code-templates).
Is Optimizing Attention Flash safe to use?
Edge security state: Reviewed (3 Edge-run static scans, scanned Sep 30, 2026). The Evidence tab shows the scan.
How do I use Optimizing Attention Flash in Claude Code, Codex or Cursor?
Click Try for free, pick your agent and follow its one step. Edge is free, with no Edge account.