Loop
alirezarezvani/claude-skills
Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly).
Apply prefetch optimization to FlyDSL kernel loops: pre-load the first iteration's data before the loop, issue async loads for the next iteration inside the loop body, and swap buffers at the loop…
$ npx skills add ROCm/FlyDSL --skill prefetch-data-load -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ROCm/FlyDSL prefetch-data-load --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ROCm/FlyDSL.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/prefetch-data-load .claude/skills/prefetch-data-load && rm -rf skills-srcUse ~/.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/
Install the "prefetch-data-load" agent skill from https://github.com/ROCm/FlyDSL/tree/main/.claude/skills/prefetch-data-load into .claude/skills/prefetch-data-load/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prefetch-data-load", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ROCm/FlyDSL/tree/main/.claude/skills/prefetch-data-loadType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ROCm/FlyDSL --skill prefetch-data-load -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ROCm/FlyDSL prefetch-data-load --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ROCm/FlyDSL.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/prefetch-data-load .agents/skills/prefetch-data-load && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prefetch-data-load" agent skill from https://github.com/ROCm/FlyDSL/tree/main/.claude/skills/prefetch-data-load into .agents/skills/prefetch-data-load/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prefetch-data-load", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ROCm/FlyDSL --skill prefetch-data-load -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ROCm/FlyDSL prefetch-data-load --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ROCm/FlyDSL.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/prefetch-data-load .cursor/skills/prefetch-data-load && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "prefetch-data-load" agent skill from https://github.com/ROCm/FlyDSL/tree/main/.claude/skills/prefetch-data-load into .cursor/skills/prefetch-data-load/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prefetch-data-load", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ROCm/FlyDSL.git --path .claude/skills/prefetch-data-load--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ROCm/FlyDSL --skill prefetch-data-load -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ROCm/FlyDSL prefetch-data-load --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ROCm/FlyDSL.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/prefetch-data-load .gemini/skills/prefetch-data-load && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "prefetch-data-load" agent skill from https://github.com/ROCm/FlyDSL/tree/main/.claude/skills/prefetch-data-load into .gemini/skills/prefetch-data-load/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prefetch-data-load", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ROCm/FlyDSL prefetch-data-loadInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ROCm/FlyDSL --skill prefetch-data-load -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ROCm/FlyDSL.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/prefetch-data-load .github/skills/prefetch-data-load && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "prefetch-data-load" agent skill from https://github.com/ROCm/FlyDSL/tree/main/.claude/skills/prefetch-data-load into .github/skills/prefetch-data-load/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prefetch-data-load", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ROCm/FlyDSL --skill prefetch-data-load -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ROCm/FlyDSL prefetch-data-load --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ROCm/FlyDSL.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/prefetch-data-load .opencode/skills/prefetch-data-load && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "prefetch-data-load" agent skill from https://github.com/ROCm/FlyDSL/tree/main/.claude/skills/prefetch-data-load into .opencode/skills/prefetch-data-load/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prefetch-data-load", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
prefetch-data-loadApply prefetch optimization to FlyDSL kernel loops: pre-load the first iteration's data before the loop, issue async loads for the next iteration inside the loop body, and swap buffers at the loop…
Prefetch Data Load is an agent skill from ROCm/FlyDSL. Apply prefetch optimization to FlyDSL kernel loops: pre-load the first iteration's data before the loop, issue async loads for the next iteration inside the loop body, and swap buffers at the loop tail via runtime loop-carried values. This overlaps data load latency with compute instructions. Use when a kernel has a loop where bufferload feeds into MFMA/compute and load latency is exposed. Usage: /prefetch-data-load
Its SKILL.md is about 4.4k 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.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 1941889. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadEditBashGrepGlobAgentFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are python and sql).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Prefetch Data Load loads about 4.4k tokens when it runs. Until then it costs about 110 tokens; SKILL.md has 1,591 words of instructions outside code blocks.
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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Edit, Bash, Grep, Glob, AgentAutomated 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.
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,591 words (~4,448 tokens).
“Apply software prefetch (double-buffering) to overlap async data loads with compute in FlyDSL GPU kernel loops.”
Just SKILL.md in .claude/skills/prefetch-data-load of ROCm/FlyDSL.
Open the folder on GitHubat commit 1941889
Prefetch Data Load 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Prefetch Data Load this skillROCm/FlyDSL | 288 | — | ~4.4k | Automated safety check: Notes | Custom licence | |
| Loopalirezarezvani/claude-skills | 28k | 2 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Autonomous Loopsaffaan-m/ECC | 275k | 4 repos | ~5.8k | Automated safety check: Pass | MIT | |
| Loopasgeirtj/system_prompts_leaks | 69k | — | ~2.2k | Automated safety check: Warn | CC0-1.0 | |
| Loop Design Checkaffaan-m/ECC | 275k | 1 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Recurring Prompt LoopQwenLM/qwen-code | 28k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 |
alirezarezvani/claude-skills
Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly).
affaan-m/ECC
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
asgeirtj/system_prompts_leaks
Run a prompt or slash command on a recurring interval (e.g. An agent skill from asgeirtj/system_prompts_leaks.
affaan-m/ECC
Design a goal-oriented agent loop or review one for failure modes: spinning, Goodhart-gaming the verifier, or running a wrong answer to completion.
QwenLM/qwen-code
Runs a prompt now and repeats it on a fixed interval or through self-paced wakeups, with subcommands to list or clear scheduled loop jobs.
ruvnet/ruflo
Run an autonomous /loop iteration -- check progress, work on next task, schedule next wake
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.
ROCm/FlyDSL
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.
ROCm/FlyDSL
Review a FlyDSL PR, commit, branch, kernel, or consuming module for API-stability compliance.
ROCm/FlyDSL
Connect to a remote host via SSH and build a Docker image with rocprofv3, aiter, and FlyDSL.
ROCm/FlyDSL
Debug FlyDSL GPU kernels that produce NaN, inf, wrong results, or crash.
ROCm/FlyDSL
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.
Apply prefetch optimization to FlyDSL kernel loops: pre-load the first iteration's data before the loop, issue async loads for the next iteration inside the loop body, and swap buffers at the loop…. Prefetch Data Load is an agent skill from ROCm/FlyDSL. Apply prefetch optimization to FlyDSL kernel loops: pre-load the first iteration's data before the loop, issue async loads for the next iteration inside the loop body, and swap buffers at the loop tail via runtime loop-carried values.
Prefetch Data Load fits situations like: A kernel has a loop where bufferload feeds into MFMA/compute and load latency is exposed.
Run `npx skills add ROCm/FlyDSL --skill prefetch-data-load -a claude-code`. Or copy the skill folder (.claude/skills/prefetch-data-load in ROCm/FlyDSL) into .claude/skills/prefetch-data-load in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ROCm/FlyDSL --skill prefetch-data-load -a codex`. Or copy the skill folder (.claude/skills/prefetch-data-load in ROCm/FlyDSL) into .agents/skills/prefetch-data-load in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ROCm/FlyDSL --skill prefetch-data-load -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prefetch-data-load, .gemini/skills/prefetch-data-load, .github/skills/prefetch-data-load and .opencode/skills/prefetch-data-load in your project.
SKILL.md names no scripts, command-line tools or credentials: Prefetch Data Load is instructions for the agent only. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Edit, Bash, Grep, Glob, Agent.
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.
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.
Prefetch Data Load has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
About 4.4k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Prefetch Data Load: Loop (alirezarezvani/claude-skills, 28k stars), Autonomous Loops (affaan-m/ECC, 275k stars), Loop (asgeirtj/system_prompts_leaks, 69k stars) and Loop Design Check (affaan-m/ECC, 275k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ROCm (a GitHub organization) maintains it in ROCm/FlyDSL, which has 288 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 8, 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.