Configure G1 Sim2real
EGalahad/sim2real
Install, repair, and verify sim2real on G1 robot computers. An agent skill from EGalahad/sim2real.
Build ONNX export and validation commands, package/load timm models via Hugging Face Hub or local directories, use Torch Hub compatibility, and safely clean or average checkpoints.
Install Export And Interoperability
$ npx skills add VectorSpaceLab/AREX-Skill --skill export-and-interoperability -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill export-and-interoperability --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/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability .claude/skills/export-and-interoperability && 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 "export-and-interoperability" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability into .claude/skills/export-and-interoperability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "export-and-interoperability", 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/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperabilityType 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 VectorSpaceLab/AREX-Skill --skill export-and-interoperability -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill export-and-interoperability --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability .agents/skills/export-and-interoperability && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "export-and-interoperability" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability into .agents/skills/export-and-interoperability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "export-and-interoperability", 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 VectorSpaceLab/AREX-Skill --skill export-and-interoperability -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill export-and-interoperability --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability .cursor/skills/export-and-interoperability && 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 "export-and-interoperability" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability into .cursor/skills/export-and-interoperability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "export-and-interoperability", 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/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability--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 VectorSpaceLab/AREX-Skill --skill export-and-interoperability -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill export-and-interoperability --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability .gemini/skills/export-and-interoperability && 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 "export-and-interoperability" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability into .gemini/skills/export-and-interoperability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "export-and-interoperability", 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 VectorSpaceLab/AREX-Skill export-and-interoperabilityInstalls 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 VectorSpaceLab/AREX-Skill --skill export-and-interoperability -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability .github/skills/export-and-interoperability && 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 "export-and-interoperability" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability into .github/skills/export-and-interoperability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "export-and-interoperability", 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 VectorSpaceLab/AREX-Skill --skill export-and-interoperability -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill export-and-interoperability --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability .opencode/skills/export-and-interoperability && 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 "export-and-interoperability" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability into .opencode/skills/export-and-interoperability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "export-and-interoperability", 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
export-and-interoperability- GitHub stars
- 328
- Token cost
- ~1k tokens
- SKILL.md length
- 420 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 159
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Build ONNX export and validation commands, package/load timm models via Hugging Face Hub or local directories, use Torch Hub compatibility, and safely clean or average checkpoints.
- Tasks that involve Model hubs and datasets
- SKILL.md covers Routing Checklist, High-Value Defaults, Boundary Routing and Bundled Helpers
- Runs Python scripts from its folder; calls python
What it does
Export And Interoperability is an agent skill from VectorSpaceLab/AREX-Skill. Build ONNX export and validation commands, package/load timm models via Hugging Face Hub or local directories, use Torch Hub compatibility, and safely clean or average checkpoints.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/export-checkpoint-workflows.md`, `references/hub-and-conversion.md` and `references/troubleshooting.md`).
It sits in AI & LLM Engineering, covering Model hubs and datasets. It works with ONNX and Hugging Face. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Model hubs and datasets
Example prompts
- “/export-and-interoperability”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. 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
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
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
Export And Interoperability loads about 1k tokens when it runs, and up to ~6.3k if it reads all its reference files. Until then it costs about 52 tokens; SKILL.md has 420 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); the scripts in this folder are not scanned.
SKILL.md
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its Apache-2.0 licence (© VectorSpaceLab). 420 words, ~1,046 tokens.
Download SKILL.mdSave it as
.claude/skills/export-and-interoperability/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- export-and-interoperability
- description
- Build ONNX export and validation commands, package/load timm models via Hugging Face Hub or local directories, use Torch Hub compatibility, and safely clean or average checkpoints.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- Apache 2.0
Export and Interoperability
Use this sub-skill when a task asks for timm model export, ONNX Runtime validation, pretrained model interchange through Hugging Face Hub or local directories, Torch Hub compatibility, or checkpoint cleanup/averaging before sharing weights.
Routing Checklist
- Use
references/export-checkpoint-workflows.mdfor ONNX export/validation command options, dynamic input caveats,exportable=True, reparameterization, checkpoint cleaning, checkpoint averaging, hash naming, and safetensors choices. - Use
references/hub-and-conversion.mdforhf-hub:andlocal-dir:model names,push_to_hf_hub, localconfig.jsonplus weight-file expectations, Torch Hub behavior, and conversion-script caveats. - Use
references/troubleshooting.mdfor missing optional dependencies, unsupported ONNX ops, dynamic-shape failures, checkpoint prefix/EMA mismatches, safe loading failures, local-dir packaging mistakes, Hugging Face auth/cache/network issues, and external conversion requirements. - Use
scripts/timm_onnx_command_builder.pyto print dryonnx_export.pyandonnx_validate.pycommands without importing timm or requiring ONNX dependencies. - Use
scripts/timm_checkpoint_tools.pyfor self-contained checkpoint inspection, dry command construction for cleaning/averaging, and bundled averaging; cleaning remains a generated command for a timm script checkout rather than a write action inside this helper.
High-Value Defaults
- Start ONNX work with a small, common model and static shape:
--model resnet18 --batch-size 1 --input-size 3 224 224; add--dynamic-sizeonly when deployment needs variable height/width. - Export through timm's export path, not ad hoc tracing: create models with
exportable=True, use--checkpointfor local weights, and add--reparamfor models that expose reparameterization before deployment. - Treat
--check-forwardas optional verification because it requires ONNX/ONNX Runtime support and may expose numerical or operator-coverage differences rather than command-construction mistakes. - Prefer safetensors for shared cleaned or averaged weights when the dependency is installed; keep
.pthonly for legacy consumers that need PyTorch serialization. - Keep checkpoint tools non-destructive: never overwrite an existing output, inspect candidate keys first, and decide whether EMA weights should be used before cleaning or averaging.
- For hosted or portable timm models, package both
config.jsonand a recognized weight filename; use exacthf-hub:org/model@revisionorlocal-dir:/path/to/model_dirsource prefixes when loading.
Show full SKILL.md (115 more words)Show less
Boundary Routing
- Use
../model-library/for ordinarytimm.create_model, model discovery, pretrained config inspection, feature extraction, and generic checkpoint mismatch analysis before export. - Use
../cli-workflows/fortrain.py,validate.py, andinference.pycommands that are not ONNX-specific. - Use
../benchmarking-and-results/when the task is performance measurement rather than export or validation correctness. - Treat framework conversion scripts as reference-only starting points; do not promise turnkey conversion unless the external checkpoint format, framework package, and architecture mapping are available.
Bundled Helpers
python scripts/timm_onnx_command_builder.py export \
--output model.onnx --model resnet18 --input-size 3 224 224 --batch-size 1 --check-forwardpython scripts/timm_checkpoint_tools.py inspect \
--checkpoint model_best.pth.tarThe helpers are intentionally conservative. The ONNX builder prints commands only. The checkpoint helper can inspect checkpoints, construct clean/average commands, and run bundled checkpoint averaging with overwrite refusal; checkpoint cleaning is emitted as a command for a trusted timm script checkout.
© VectorSpaceLab, Apache-2.0. 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 5 other files (scripts, references) in skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/export-checkpoint-workflows.md
- references/hub-and-conversion.md
- references/troubleshooting.md
- scripts/timm_checkpoint_tools.py
- scripts/timm_onnx_command_builder.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Export And Interoperability 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 |
|---|---|---|---|---|---|---|
| Export And Interoperability this skillVectorSpaceLab/AREX-Skill | 328 | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Configure G1 Sim2realEGalahad/sim2real | 145 | — | ~1.5k | Automated safety check: Pass | None | |
| Xybrid Initxybrid-ai/xybrid | 465 | — | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Community Model ConversionRisorseArtificiali/anti-vocale | 117 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Quark Torch Exportamd/Quark | 181 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Publish Modelayutaz/piper-plus | 218 | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Xybrid Init
xybrid-ai/xybrid
Generate model metadata for an ML model so it works with xybrid.
Community Model Conversion
RisorseArtificiali/anti-vocale
Convert a HuggingFace ASR fine-tune into a sherpa-onnx external model, publish it, and add it to the Anti-Vocale community catalog.
Quark Torch Export
amd/Quark
Prepare export and downstream evaluation handoff for a planned or completed Quark PTQ run.
Publish Model
ayutaz/piper-plus
学習済み Lightning checkpoint (.ckpt) を ONNX export → sanity check → RTF benchmark → HuggingFace upload まで連鎖実行する read-mostly skill。
Quark Torch Ptq
amd/Quark
Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan, create reproducible artifacts, request…
More from VectorSpaceLab/AREX-Skill
All 159 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Related
Works with
Categories
Questions about Export And Interoperability
What does Export And Interoperability do?
Build ONNX export and validation commands, package/load timm models via Hugging Face Hub or local directories, use Torch Hub compatibility, and safely clean or average checkpoints. Export And Interoperability is an agent skill from VectorSpaceLab/AREX-Skill. Build ONNX export and validation commands, package/load timm models via Hugging Face Hub or local directories, use Torch Hub compatibility, and safely clean or average checkpoints.
When should I use Export And Interoperability?
Export And Interoperability fits situations like: tasks that involve Model hubs and datasets.
How do I install Export And Interoperability in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill export-and-interoperability -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability in VectorSpaceLab/AREX-Skill) into .claude/skills/export-and-interoperability in your project. Claude Code loads it when a task matches its description.
How do I install Export And Interoperability in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill export-and-interoperability -a codex`. Or copy the skill folder (skills/repositories/repo-skills/timm/sub-skills/export-and-interoperability in VectorSpaceLab/AREX-Skill) into .agents/skills/export-and-interoperability in your project. Codex loads it when a task matches its description.
Can I use Export And Interoperability 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 VectorSpaceLab/AREX-Skill --skill export-and-interoperability -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/export-and-interoperability, .gemini/skills/export-and-interoperability, .github/skills/export-and-interoperability and .opencode/skills/export-and-interoperability in your project.
What does Export And Interoperability need to run?
Going by SKILL.md and its folder, Export And Interoperability needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Export And Interoperability 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 Export And Interoperability 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Export And Interoperability use?
Export And Interoperability is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Export And Interoperability use?
About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.3k tokens, read only when the agent opens those files.
What are the alternatives to Export And Interoperability?
Skills that share tags, products or a category with Export And Interoperability: Configure G1 Sim2real (EGalahad/sim2real, 145 stars), Xybrid Init (xybrid-ai/xybrid, 465 stars), Community Model Conversion (RisorseArtificiali/anti-vocale, 117 stars) and Quark Torch Export (amd/Quark, 181 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Export And Interoperability?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 328 GitHub stars. The repository holds 159 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.