Agent skill

Lds Optimization

by ROCm in ROCm/FlyDSL

Optimize LDS (Local Data Share / shared memory) access patterns in FlyDSL GPU kernels.

Custom licenceAuto-check: notes

Install Lds Optimization

skills CLI
$ npx skills add ROCm/FlyDSL --skill lds-optimization -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ROCm/FlyDSL lds-optimization --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ROCm/FlyDSL.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/lds-optimization .claude/skills/lds-optimization && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
lds-optimization
GitHub stars
287
Token cost
~5.8k tokens
SKILL.md length
2,160 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
Custom licence

At a glance

Optimize LDS (Local Data Share / shared memory) access patterns in FlyDSL GPU kernels.

  • Works in 2 steps: Identify LDS-heavy regions → Classify the bottleneck type
  • Trace analysis shows dsread/dswrite/lgkmcnt as a bottleneck
  • SKILL.md covers When To Use, LDS Architecture on CDNA3…, LDS Architecture on CDNA4… and Diagnosing LDS Bottlenecks…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Lds Optimization is an agent skill from ROCm/FlyDSL. Optimize LDS (Local Data Share / shared memory) access patterns in FlyDSL GPU kernels. Diagnose bank conflicts and high lgkmcnt stalls from ATT trace data, then apply swizzle or padding layouts to eliminate conflicts. Also increase the distance between LDS write and subsequent LDS read to hide LDS latency. LDS read preceded by write always requires a sync (swaitcnt lgkmcnt or sbarrier). Use when trace analysis shows dsread/dswrite/lgkmcnt as a bottleneck. Usage: /lds-optimization

Its SKILL.md is about 5.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: FlyDSL is the Python front‑end of the project: a Flexible Layout Python DSL for expressing tiling, partitioning, data movement, and kernel structure at a high level.

When your agent uses it

  • Trace analysis shows dsread/dswrite/lgkmcnt as a bottleneck

Example prompts

  • “/lds-optimization”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Read, Edit, Bash, Grep, Glob, Agent

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Identify LDS-heavy regions
  2. Classify the bottleneck type

What it can do on your machine

Read from SKILL.md and the folder at commit 1941889. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Edit
    • Bash
    • Grep
    • Glob
    • Agent

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lds Optimization loads about 5.8k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 2,160 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~5.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Edit, Bash, Grep, Glob, Agent

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,160 words (~5,811 tokens).

“Diagnose and fix LDS (shared memory) performance issues in FlyDSL kernels on AMD CDNA GPUs (MI300X/MI308/MI350).”

— opening of SKILL.md by ROCm, Custom licence
name
lds-optimization
allowed-tools
Read, Edit, Bash, Grep, Glob, Agent

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/lds-optimization of ROCm/FlyDSL.

Open the folder on GitHubat commit 1941889

Compare with similar skills

Lds Optimization next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Lds Optimization compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lds Optimization this skillROCm/FlyDSL287—~5.8kAutomated safety check: NotesCustom licence
SQL Optimizationgithub/awesome-copilot40k2 repos~2.3kAutomated safety check: PassMIT
Agent Performance Optimizerruvnet/ruflo74k2 repos~3.6kAutomated safety check: PassMIT
Database Optimizerdavila7/claude-code-templates32k7 repos~2.5kAutomated safety check: PassMIT
Prompt Optimizeraffaan-m/ECC274k2 repos~2.4kAutomated safety check: PassMIT
Cost Optimizeruvnet/ruflo74k—~997Automated safety check: NotesMIT

Similar skills

  • SQL Optimization

    github/awesome-copilot

    Official

    Universal SQL performance optimization assistant for comprehensive query tuning, indexing strategies, and database performance analysis across all SQL databases (MySQL, PostgreSQL, SQL Server…

    40k GitHub starsUsed in 2 repos~2.3k tokens
    DatabasesAuto-check passed
  • Agent skill for performance-optimizer - invoke with $agent-performance-optimizer

    74k GitHub starsUsed in 2 repos~3.6k tokens
    Auto-check passed
  • Database Optimizer

    davila7/claude-code-templates

    Expert database optimizer specializing in modern performance tuning, query optimization, and scalable architectures.

    32k GitHub starsUsed in 7 repos~2.5k tokens
    DatabasesAuto-check passed
  • Prompt Optimizer

    affaan-m/ECC

    分析原始提示,识别意图和差距,匹配ECC组件(技能/命令/代理/钩子),并输出一个可直接粘贴的优化提示。仅提供咨询角色——绝不自行执行任务。触发时机:当用户说“优化提示”、“改进我的提示”、“如何编写提示”、“帮我优化这个指令”或明确要求提高提示质量时。中文等效表达同样触发:“优化prompt”、“改进prompt”、“怎么写prompt”、“帮我优化这个指令”。不触发时机:当用户希望直接执行任…

    274k GitHub starsUsed in 2 repos~2.4k tokens
    DevelopmentAuto-check passed
  • Cost Optimize

    ruvnet/ruflo

    Analyze token usage patterns and recommend cost optimizations with estimated savings

    74k GitHub stars~997 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Caveman Optimization Evaluator

    JuliusBrussee/caveman

    Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue.

    110k GitHub starsUsed in 1 repo~1.2k tokens
    AI & LLM EngineeringAuto-check passed

More from ROCm/FlyDSL

All 19 skills in this repo
  • Llvm

    ROCm/FlyDSL

    Tune and analyse a FlyDSL kernel at the LLVM level: pick a compile hint, function attribute, or AMDGPU backend flag, then PROVE it reached codegen.

    287 GitHub stars~4.9k tokensUpdated today
    Auto-check: notes
  • Detect per-kernel GPU resource regressions (VGPR, SGPR, register spills, scratch, static LDS) by diffing the final ISA before and after a change, using its isaresourcetable.py helper.

    287 GitHub stars~2.7k tokensUpdated today
    Auto-check: notes
  • API Stability

    ROCm/FlyDSL

    Review a FlyDSL PR, commit, branch, kernel, or consuming module for API-stability compliance.

    287 GitHub stars~3.2k tokensUpdated today
    Auto-check: notes
  • Build Rocm Image

    ROCm/FlyDSL

    Connect to a remote host via SSH and build a Docker image with rocprofv3, aiter, and FlyDSL.

    287 GitHub stars~1.2k tokensUpdated today
    Auto-check: notes
  • Debug FlyDSL GPU kernels that produce NaN, inf, wrong results, or crash.

    287 GitHub stars~2.6k tokensUpdated today
    Auto-check: notes
  • Guided step-by-step wizard for producing a new FlyDSL GPU kernel from a requirement: classify the kernel type, pick a skeleton, fill in compute, add control flow / sync / LDS, then test on GPU.

    287 GitHub stars~4.6k tokensUpdated today
    Auto-check: notes

Questions about Lds Optimization

What does Lds Optimization do?

Optimize LDS (Local Data Share / shared memory) access patterns in FlyDSL GPU kernels. Lds Optimization is an agent skill from ROCm/FlyDSL. Optimize LDS (Local Data Share / shared memory) access patterns in FlyDSL GPU kernels.

When should I use Lds Optimization?

Lds Optimization fits situations like: trace analysis shows dsread/dswrite/lgkmcnt as a bottleneck.

How do I install Lds Optimization in Claude Code?

Run `npx skills add ROCm/FlyDSL --skill lds-optimization -a claude-code`. Or copy the skill folder (.claude/skills/lds-optimization in ROCm/FlyDSL) into .claude/skills/lds-optimization in your project. Claude Code loads it when a task matches its description.

How do I install Lds Optimization in Codex?

Run `npx skills add ROCm/FlyDSL --skill lds-optimization -a codex`. Or copy the skill folder (.claude/skills/lds-optimization in ROCm/FlyDSL) into .agents/skills/lds-optimization in your project. Codex loads it when a task matches its description.

Can I use Lds Optimization in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ROCm/FlyDSL --skill lds-optimization -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lds-optimization, .gemini/skills/lds-optimization, .github/skills/lds-optimization and .opencode/skills/lds-optimization in your project.

What does Lds Optimization need to run?

SKILL.md names no scripts, command-line tools or credentials: Lds Optimization is instructions for the agent only. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Edit, Bash, Grep, Glob, Agent.

Does Lds Optimization access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Lds Optimization safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Lds Optimization use?

Lds Optimization has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Lds Optimization use?

About 5.8k tokens (SKILL.md is roughly 23k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Lds Optimization?

Skills that share tags, products or a category with Lds Optimization: SQL Optimization (github/awesome-copilot, 40k stars), Agent Performance Optimizer (ruvnet/ruflo, 74k stars), Database Optimizer (davila7/claude-code-templates, 32k stars) and Prompt Optimizer (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lds Optimization?

ROCm (a GitHub organization) maintains it in ROCm/FlyDSL, which has 287 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 7, 2026.

Source: ROCm/FlyDSL on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.