LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
Systematic performance audit for Albucore runtime code. An agent skill from albumentations-team/albucore.
Install Performance Optimization
$ npx skills add albumentations-team/albucore --skill performance-optimization -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install albumentations-team/albucore performance-optimization --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/albumentations-team/albucore.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/performance-optimization .claude/skills/performance-optimization && 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 "performance-optimization" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/performance-optimization into .claude/skills/performance-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-optimization", 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/albumentations-team/albucore/tree/main/.codex/skills/performance-optimizationType 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 albumentations-team/albucore --skill performance-optimization -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install albumentations-team/albucore performance-optimization --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/albumentations-team/albucore.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/performance-optimization .agents/skills/performance-optimization && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "performance-optimization" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/performance-optimization into .agents/skills/performance-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-optimization", 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 albumentations-team/albucore --skill performance-optimization -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install albumentations-team/albucore performance-optimization --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/albumentations-team/albucore.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/performance-optimization .cursor/skills/performance-optimization && 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 "performance-optimization" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/performance-optimization into .cursor/skills/performance-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-optimization", 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/albumentations-team/albucore.git --path .codex/skills/performance-optimization--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 albumentations-team/albucore --skill performance-optimization -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install albumentations-team/albucore performance-optimization --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/albumentations-team/albucore.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/performance-optimization .gemini/skills/performance-optimization && 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 "performance-optimization" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/performance-optimization into .gemini/skills/performance-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-optimization", 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 albumentations-team/albucore performance-optimizationInstalls 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 albumentations-team/albucore --skill performance-optimization -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/albumentations-team/albucore.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/performance-optimization .github/skills/performance-optimization && 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 "performance-optimization" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/performance-optimization into .github/skills/performance-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-optimization", 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 albumentations-team/albucore --skill performance-optimization -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install albumentations-team/albucore performance-optimization --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/albumentations-team/albucore.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/performance-optimization .opencode/skills/performance-optimization && 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 "performance-optimization" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/performance-optimization into .opencode/skills/performance-optimization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-optimization", 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.
Facts
- Skill name
performance-optimization- GitHub stars
- 123
- Token cost
- ~743 tokens
- SKILL.md length
- 303 words
- Files
- 2
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Systematic performance audit for Albucore runtime code. An agent skill from albumentations-team/albucore.
- Works in 7 steps: Establish correctness and public-router… → Run every stage of the canonical… → Treat delete-first, vectorization, LUT,… → …
- Optimizing atomic image operations
- SKILL.md covers Workflow, Albucore Boundary and Required Handoff
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Performance Optimization is an agent skill from albumentations-team/albucore. Systematic performance audit for Albucore runtime code. Use whenever implementing, reviewing, profiling, or optimizing atomic image operations, backend routing, reductions, label maps, LUTs, random generation, dtype conversions, allocation-heavy paths, batch or volume kernels, or in-place behavior.
Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Development, covering Performance optimization. The repository describes itself as: A high-performance image processing library designed to optimize and extend the Albumentations library with specialized functions for advanced image transformations. Perfect for… The licence is MIT.
When your agent uses it
- Optimizing atomic image operations
- Backend routing
- Random generation
- Dtype conversions
Example prompts
- “/performance-optimization”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Establish correctness and public-router performance baselines before editing.
- Run every stage of the canonical optimization pass. Do not stop after finding the first plausible improvement.
- Treat delete-first, vectorization, LUT, random generation, bincount, backend selection, routing thresholds, and
- Compare the complete public path, including dispatch, dtype conversion, contiguity, allocation, clipping, and shape
- Read ../albucore-benchmarks/SKILL.md completely before measuring. Extend the matrix along the dimension that
- Add or preserve correctness tests for every accepted route and its boundary cases.
- Update benchmark evidence and route documentation when public routing changes.
What it can do on your machine
Read from SKILL.md and the folder at commit 249d10b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
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
Performance Optimization loads about 743 tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 303 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.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
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
The full file from albumentations-team/albucore at commit 249d10b, republished under its MIT licence (© albumentations-team). 303 words, ~743 tokens.
Download SKILL.mdSave it as
.claude/skills/performance-optimization/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- performance-optimization
- description
- Systematic performance audit for Albucore runtime code. Use whenever implementing, reviewing, profiling, or optimizing atomic image operations, backend routing, reductions, label maps, LUTs, random generation, dtype conversions, allocation-heavy paths, batch or volume kernels, or in-place behavior.
Performance Optimization
Read ../../../docs/performance-optimization.md completely before inspecting or changing runtime code. That document
is the canonical shared workflow for Albucore and AlbumentationsX.
When the sibling AlbumentationsX checkout is available, verify the fallback copy with
cmp -s docs/performance-optimization.md ../AlbumentationsX/.codex/skills/performance-optimization/references/performance-optimization.md.
A mismatch blocks completion.
Workflow
- Establish correctness and public-router performance baselines before editing.
- Run every stage of the canonical optimization pass. Do not stop after finding the first plausible improvement.
- Treat delete-first, vectorization, LUT, random generation,
bincount, backend selection, routing thresholds, and in-place mutation as benchmark questions. - Compare the complete public path, including dispatch, dtype conversion, contiguity, allocation, clipping, and shape repair.
- Read
../albucore-benchmarks/SKILL.mdcompletely before measuring. Extend the matrix along the dimension that controls the candidate. - Add or preserve correctness tests for every accepted route and its boundary cases.
- Update benchmark evidence and route documentation when public routing changes.
Albucore Boundary
Accept reusable atomic array operations with stable image semantics. Keep augmentation policy, stochastic parameter sampling, target dispatch, and annotation rules in AlbumentationsX.
Before adding an atom:
- search Albucore for an existing router or lower-level operation;
- search AlbumentationsX for duplicate local implementations;
- define dtype, shape, channel, contiguity, aliasing, and error contracts;
- benchmark all viable backends before exposing a route.
Albucore routers are called after the upstream validation boundary. The caller owns container type, rank/layout, dtype, device, contiguity, autograd, and operation-control validation. Do not duplicate those checks in the runtime router; retain only backend dispatch and kernel-required normalization. Invalid direct calls are outside the low-level contract and must not add hot-path branches.
Required Handoff
Report:
- work deleted or avoided;
- full-array passes, copies, conversions, and allocations removed;
- vectorization and grouped-reduction candidates evaluated;
- LUT, random-generator, and backend candidates compared;
- routing thresholds and safe in-place decisions;
- AlbumentationsX duplicates replaced or follow-up extraction opportunities;
- correctness evidence, benchmark matrix, regressions, and rejected candidates.
© albumentations-team, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .codex/skills/performance-optimization of albumentations-team/albucore.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 249d10b
Compare with similar skills
Performance 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Performance Optimization this skillalbumentations-team/albucore | 123 | — | ~743 | Automated safety check: Pass | MIT | |
| LLM Torch Profiler Analysissgl-project/sglang | 37k | 2 repos | ~6.4k | Automated safety check: Pass | Apache-2.0 | |
| ExecuTorch Binary Size Reductionpytorch/executorch | 5.1k | — | ~793 | Automated safety check: Pass | Custom licence | |
| The Art of Debuggingstas00/the-art-of-debugging | 1.7k | — | ~6.1k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| Cudatechnillogue/ptx-isa-markdown | 229 | — | ~2.5k | Automated safety check: Pass | None | |
| Dataset Profileroxbshw/LLM-Agents-Ecosystem-Handbook | 552 | — | ~492 | Automated safety check: Pass | MIT |
Similar skills
ExecuTorch Binary Size Reduction
pytorch/executorch
Measures and shrinks the ExecuTorch runtime binary by building a size test, analyzing it with bloaty and landing each reduction as its own pull request.
The Art of Debugging
stas00/the-art-of-debugging
Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.
Cuda
technillogue/ptx-isa-markdown
CUDA kernel development, debugging, and performance optimization for Claude Code.
Dataset Profiler
oxbshw/LLM-Agents-Ecosystem-Handbook
A skill your agent uses when first encountering a new dataset — produces a structured profile (schema, missingness, distributions, outliers, gotchas) before any analysis.
Veomni Profile
ByteDance-Seed/VeOmni
A skill your agent uses for performance profiling and optimization.
More from albumentations-team/albucore
Albucore Benchmarks
albumentations-team/albucore
Running Albucore micro-benchmarks under benchmarks/, synthetic router timings, and comparing PyPI releases with uv --no-project.
Albucore Conventions
albumentations-team/albucore
Albucore image processing conventions - shapes (H,W,C), dtypes (uint8/float32), benchmark-driven backend routing (OpenCV, NumPy, Torch CPU, LUT, NumKong), tests, and lockfile discipline.
Albucore Public API
albumentations-team/albucore
Albucore star-exported API (all), routers vs albucore.functions shims, and dependents such as Albumentations.
Torch Performance Optimization
albumentations-team/albucore
Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions.
Related
Categories
Questions about Performance Optimization
What does Performance Optimization do?
Systematic performance audit for Albucore runtime code. An agent skill from albumentations-team/albucore. Performance Optimization is an agent skill from albumentations-team/albucore. Systematic performance audit for Albucore runtime code.
When should I use Performance Optimization?
Performance Optimization fits situations like: optimizing atomic image operations; backend routing; random generation; dtype conversions.
How do I install Performance Optimization in Claude Code?
Run `npx skills add albumentations-team/albucore --skill performance-optimization -a claude-code`. Or copy the skill folder (.codex/skills/performance-optimization in albumentations-team/albucore) into .claude/skills/performance-optimization in your project. Claude Code loads it when a task matches its description.
How do I install Performance Optimization in Codex?
Run `npx skills add albumentations-team/albucore --skill performance-optimization -a codex`. Or copy the skill folder (.codex/skills/performance-optimization in albumentations-team/albucore) into .agents/skills/performance-optimization in your project. Codex loads it when a task matches its description.
Can I use Performance 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 albumentations-team/albucore --skill performance-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/performance-optimization, .gemini/skills/performance-optimization, .github/skills/performance-optimization and .opencode/skills/performance-optimization in your project.
What does Performance Optimization need to run?
SKILL.md names no scripts, command-line tools or credentials: Performance Optimization is instructions for the agent only.
Does Performance 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 Performance Optimization safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Performance Optimization use?
Performance Optimization is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Performance Optimization use?
About 743 tokens (SKILL.md is roughly 3k 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 Performance Optimization?
Skills that share tags, products or a category with Performance Optimization: LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), ExecuTorch Binary Size Reduction (pytorch/executorch, 5.1k stars), The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars) and Cuda (technillogue/ptx-isa-markdown, 229 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Performance Optimization?
albumentations-team (a GitHub organization) maintains it in albumentations-team/albucore, which has 123 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 5, 2026.
Source: albumentations-team/albucore on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.