ComfyUI Custom Node Builder
ConstantineB6/comfy-pilot
Helps an agent write ComfyUI custom nodes in Python, including wrapping an existing script, mapping data types and handling image batches.
Running Albucore micro-benchmarks under benchmarks/, synthetic router timings, and comparing PyPI releases with uv --no-project.
Install Albucore Benchmarks
$ npx skills add albumentations-team/albucore --skill albucore-benchmarks -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install albumentations-team/albucore albucore-benchmarks --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/albucore-benchmarks .claude/skills/albucore-benchmarks && 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 "albucore-benchmarks" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/albucore-benchmarks into .claude/skills/albucore-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "albucore-benchmarks", 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/albucore-benchmarksType 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 albucore-benchmarks -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install albumentations-team/albucore albucore-benchmarks --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/albucore-benchmarks .agents/skills/albucore-benchmarks && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "albucore-benchmarks" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/albucore-benchmarks into .agents/skills/albucore-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "albucore-benchmarks", 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 albucore-benchmarks -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install albumentations-team/albucore albucore-benchmarks --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/albucore-benchmarks .cursor/skills/albucore-benchmarks && 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 "albucore-benchmarks" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/albucore-benchmarks into .cursor/skills/albucore-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "albucore-benchmarks", 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/albucore-benchmarks--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 albucore-benchmarks -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install albumentations-team/albucore albucore-benchmarks --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/albucore-benchmarks .gemini/skills/albucore-benchmarks && 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 "albucore-benchmarks" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/albucore-benchmarks into .gemini/skills/albucore-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "albucore-benchmarks", 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 albucore-benchmarksInstalls 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 albucore-benchmarks -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/albucore-benchmarks .github/skills/albucore-benchmarks && 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 "albucore-benchmarks" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/albucore-benchmarks into .github/skills/albucore-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "albucore-benchmarks", 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 albucore-benchmarks -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 albucore-benchmarks --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/albucore-benchmarks .opencode/skills/albucore-benchmarks && 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 "albucore-benchmarks" agent skill from https://github.com/albumentations-team/albucore/tree/main/.codex/skills/albucore-benchmarks into .opencode/skills/albucore-benchmarks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "albucore-benchmarks", 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
albucore-benchmarks- GitHub stars
- 123
- Token cost
- ~1.5k tokens
- SKILL.md length
- 590 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Running Albucore micro-benchmarks under benchmarks/, synthetic router timings, and comparing PyPI releases with uv --no-project.
- Adding benchmarks
- SKILL.md covers Layout, Canonical Shape Grid, Compare the current tree with… and Docs
- Calls uv and python
- Comparing performance across versions
What it does
Albucore Benchmarks is an agent skill from albumentations-team/albucore. Running Albucore micro-benchmarks under benchmarks/, synthetic router timings, and comparing PyPI releases with uv --no-project. Use when adding benchmarks, comparing performance across versions, or documenting benchmark workflow.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering. It works with Python and NumPy. 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
- Adding benchmarks
- Comparing performance across versions
- Documenting benchmark workflow
Example prompts
- “/albucore-benchmarks”
Requirements
- Python 3
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
Shell commands in SKILL.md call:
uvpython
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
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
Albucore Benchmarks loads about 1.5k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 590 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). 590 words, ~1,484 tokens.
Download SKILL.mdSave it as
.claude/skills/albucore-benchmarks/SKILL.md (or your agent's skills folder).- name
- albucore-benchmarks
- description
- Running Albucore micro-benchmarks under benchmarks/, synthetic router timings, and comparing PyPI releases with uv --no-project. Use when adding benchmarks, comparing performance across versions, or documenting benchmark workflow.
Albucore Benchmarks
Before designing a performance comparison, read ../performance-optimization/SKILL.md and
../../../docs/performance-optimization.md completely. Extend the benchmark along the dimension that controls the
candidate, such as label density for bincount, table and channel layout for LUTs, or output size and dtype for random
generation.
Use exactly one CPU thread per process for every candidate, following the thread controls in the canonical performance guide. Benchmark additional thread counts only when the user explicitly requests thread scaling.
Layout
benchmarks/- Python timing scripts. Run from repo root:uv run python benchmarks/<script>.py.benchmarks/timing.py- Sharedmedian_mshelper for scripts executed aspython benchmarks/foo.py../benchmark.sh- Dataset-driven runner; expects an externalbenchmarkpackage that is not always present in-tree. Prefer synthetic scripts for CI-style checks.benchmarks/benchmark_router_synthetic.py- Times public routers on syntheticuint8andfloat32arrays: HWC, plus NHWC formean,std, andmean_stdonly.benchmarks/compare_router_json.py- Builds a Markdown table from two JSON outputs.benchmarks/benchmark_resize3d_tensor.py- Times direct Tensor, zero-copy Tensor→NumPy→Tensor, and publicresize3droutes for contiguous and channel-last-strided CPUCDHWTensors.benchmarks/benchmark_warp_affine3d.py- Times full single-volume NumPyDHWCaffine paths, including the NumPy→Torch bridge and public router.benchmarks/benchmark_warp_affine3d_tensor.py- Times native Torch affine-grid, manual-grid and coverage-fill probes, and public single-volumeCDHWrouting.benchmarks/benchmark_warp_affine3d_batch.pyandbenchmarks/benchmark_remap3d_batch.py- Compare full rank-5 paths: per-volume calls,N × Cfolding, direct native sampling, public dispatch, and Tensor/NumPy bridges.
Canonical Shape Grid
Benchmark shape sweeps use channel-last Albucore conventions.
HWC images:
128x160with 1, 3, 9 channels - small / warm-cache, non-square.240x320with 1, 3, 9 channels - mid-size crop, non-square.480x640with 1, 3, 9 channels - typical augmentation training crop, non-square.768x1024with 1, 3, 9 channels - high-res / full-image pass, non-square.
Use non-square H/W pairs so height-width swaps fail visibly. Avoid square-only benchmark grids.
DHWC volumes:
16x128x160x1,16x128x160x3- thin slab, non-square in-plane.32x128x160x1,32x128x160x3- common nnU-Net patch depth.64x128x160x3- deeper slab.96x128x160x1- deep single-channel slab.48x240x320x3- large in-plane, multi-channel.
For resize3d, also include C=5, unit input/output spatial axes, and an explicit D*C value on both sides of the OpenCV encoded-channel boundary. Time its public NumPy route end-to-end, including channel packing, Torch conversions, and output repair. For Tensor input, sweep contiguous and channel-last-strided CDHW, direct interpolation, the zero-copy bridge, and the public router. Use uv run python benchmarks/benchmark_resize3d.py --quick and uv run python benchmarks/benchmark_resize3d_tensor.py --quick while iterating; record any resulting routing decision in docs/numkong-performance.md or a focused report under benchmarks/results/.
Show full SKILL.md (211 more words)Show less
For warp_affine3d, benchmark both NumPy DHWC/NDHWC and CPU Tensor CDHW/NCDHW. The single-volume matrix
uses uint8/float32, C=1/3/5/9, canonical output sizes, nearest/trilinear interpolation, one 3×4 forward matrix,
and zero/nonzero fill. The batch matrix also varies N=1/4/16; compare per-volume calls, N × C folding, direct
native sampling, public batch dispatch, and Tensor/NumPy bridges. Batch scripts time contiguous NumPy inputs;
correctness tests cover
supported strided and read-only inputs. Tensor timings include contiguous and channel-last-strided layouts. Test the
equivalent homogeneous 4×4 representation as a contract.
Run the single-volume scripts and benchmark_warp_affine3d_batch.py --quick --threads 1 while developing.
A manual grid, coverage sampler, tiled route, or native extension remains diagnostic until it has exact correctness
parity and a sustained full-path win.
remap3d uses the same rank-4/rank-5 volume layouts and applies one normalized float32 grid to every batch item. Its
batch benchmark also checks NumPy and Tensor grid containers independently of the volume container.
Channel choices: 1 for grayscale, 3 for RGB / 3-channel, and 9 for hyperspectral paths that exceed MAX_OPENCV_WORKING_CHANNELS=4.
Compare the current tree with a previous release
uv run python benchmarks/benchmark_router_synthetic.py \
--output-json benchmarks/results/router-current.json
uv run --no-project --with albucore==<previous-version> --with opencv-python-headless \
--with numkong --with stringzilla --with numpy \
python benchmarks/benchmark_router_synthetic.py \
--output-json benchmarks/results/router-previous.json
uv run python benchmarks/compare_router_json.py \
benchmarks/results/router-current.json \
benchmarks/results/router-previous.json \
benchmarks/results/REPORT_router_current_vs_previous.mdReplace <previous-version> with the release that answers the current question. Use --quick for smaller
shape/channel grids while iterating, and do not accumulate version-specific baselines in the repository.
Docs
- Current NumKong route decisions:
docs/numkong-performance.md - Generated benchmark evidence:
benchmarks/results/ - General performance policy:
docs/performance-optimization.md
© 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
Just SKILL.md in .codex/skills/albucore-benchmarks of albumentations-team/albucore.
Open the folder on GitHubat commit 249d10b
Compare with similar skills
Albucore Benchmarks 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 |
|---|---|---|---|---|---|---|
| Albucore Benchmarks this skillalbumentations-team/albucore | 123 | — | ~1.5k | Automated safety check: Pass | MIT | |
| ComfyUI Custom Node BuilderConstantineB6/comfy-pilot | 230 | — | ~897 | Automated safety check: Pass | MIT | |
| Xtbloom Run Python Inferencejinzhezenggroup/computational-chemistry-agent-skills | 148 | — | ~1.3k | Automated safety check: Pass | LGPL-3.0 | |
| RAG Company Knowledge AssistantHermes-brasil/hermes-brasil | 154 | — | ~1.1k | Automated safety check: Pass | MIT | |
| FAISS Similarity SearchOrchestra-Research/AI-Research-SKILLs | 13k | 6 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Python Performance Optimizationwshobson/agents | 40k | 13 repos | ~814 | Automated safety check: Pass | MIT |
Similar skills
Xtbloom Run Python Inference
jinzhezenggroup/computational-chemistry-agent-skills
Write, review, and run high-level xTBloom Python GFN2-xTB inference with Calculator, Structure, and BatchCalculator, including single systems, repeated geometry updates, heterogeneous ragged…
RAG Company Knowledge Assistant
Hermes-brasil/hermes-brasil
Portuguese guide to building a retrieval-augmented generation assistant over a company's documents, with embeddings, section-based chunking, retrieval and a client workflow.
FAISS Similarity Search
Orchestra-Research/AI-Research-SKILLs
Sets up FAISS for fast nearest-neighbor search over large collections of dense vectors, choosing between Flat, IVF, HNSW and product quantization indexes.
Python Performance Optimization
wshobson/agents
Profiles slow Python code with cProfile and memory profilers, then applies targeted fixes for CPU, memory, I/O and query bottlenecks.
Test Design
jjjkkkjjj/Matft
Procedure for designing and writing Matft's XCTest cases with high coverage — boundary values, dtypes, memory layouts, NaN/inf, empty arrays, broadcasting, platform differences, performance and…
More from albumentations-team/albucore
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.
Performance Optimization
albumentations-team/albucore
Systematic performance audit for Albucore runtime code. An agent skill from albumentations-team/albucore.
Torch Performance Optimization
albumentations-team/albucore
Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions.
Related
Categories
Questions about Albucore Benchmarks
What does Albucore Benchmarks do?
Running Albucore micro-benchmarks under benchmarks/, synthetic router timings, and comparing PyPI releases with uv --no-project. Albucore Benchmarks is an agent skill from albumentations-team/albucore. Running Albucore micro-benchmarks under benchmarks/, synthetic router timings, and comparing PyPI releases with uv --no-project.
When should I use Albucore Benchmarks?
Albucore Benchmarks fits situations like: adding benchmarks; comparing performance across versions; documenting benchmark workflow.
How do I install Albucore Benchmarks in Claude Code?
Run `npx skills add albumentations-team/albucore --skill albucore-benchmarks -a claude-code`. Or copy the skill folder (.codex/skills/albucore-benchmarks in albumentations-team/albucore) into .claude/skills/albucore-benchmarks in your project. Claude Code loads it when a task matches its description.
How do I install Albucore Benchmarks in Codex?
Run `npx skills add albumentations-team/albucore --skill albucore-benchmarks -a codex`. Or copy the skill folder (.codex/skills/albucore-benchmarks in albumentations-team/albucore) into .agents/skills/albucore-benchmarks in your project. Codex loads it when a task matches its description.
Can I use Albucore Benchmarks 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 albucore-benchmarks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/albucore-benchmarks, .gemini/skills/albucore-benchmarks, .github/skills/albucore-benchmarks and .opencode/skills/albucore-benchmarks in your project.
What does Albucore Benchmarks need to run?
Going by SKILL.md and its folder, Albucore Benchmarks needs the command-line tools its instructions call (uv and python). Our summary lists: Python 3.
Does Albucore Benchmarks access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Albucore Benchmarks 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 Albucore Benchmarks use?
Albucore Benchmarks 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 Albucore Benchmarks use?
About 1.5k tokens (SKILL.md is roughly 5.9k 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 Albucore Benchmarks?
Skills that share tags, products or a category with Albucore Benchmarks: ComfyUI Custom Node Builder (ConstantineB6/comfy-pilot, 230 stars), Xtbloom Run Python Inference (jinzhezenggroup/computational-chemistry-agent-skills, 148 stars), RAG Company Knowledge Assistant (Hermes-brasil/hermes-brasil, 154 stars) and FAISS Similarity Search (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Albucore Benchmarks?
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.