New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Quark Onnx Skill Sync

by amd in amd/Quark

Detect upstream Quark ONNX changes that affect the ONNX skill family and classify required updates.

MITAuto-check passedAI & LLM Engineering

Install Quark Onnx Skill Sync

skills CLI
$ npx skills add amd/Quark --skill quark-onnx-skill-sync -a claude-code

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

GitHub CLI
$ gh skill install amd/Quark quark-onnx-skill-sync --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/amd/Quark.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills-impl/meta/onnx/quark-onnx-skill-sync .claude/skills/quark-onnx-skill-sync && 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
quark-onnx-skill-sync
GitHub stars
181
Token cost
~3.3k tokens
SKILL.md length
318 words
Files
1
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Detect upstream Quark ONNX changes that affect the ONNX skill family and classify required updates.

  • Works in 5 steps: Collect: Identify all source-knowledge… → Audit: Check each source file for… → Classify: Tag each finding as… → …
  • Quark ONNX docs
  • SKILL.md covers Purpose, Inputs, Outputs: validation_report.md and Interaction Flow, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Quark Onnx Skill Sync is an agent skill from amd/Quark. Detect upstream Quark ONNX changes that affect the ONNX skill family and classify required updates. Use when Quark ONNX docs, custom-op registry, quantization config presets, calibration methods, AutoSearchPro presets, ONNX Runtime install matrix, or source behavior under quark/onnx/ may have drifted from the skill contracts. Trigger for "check if ONNX skills are up to date", "sync ONNX skills with Quark", "has Quark ONNX changed", "update ONNX skills after Quark upgrade", or when ONNX debugging reveals a…

Its SKILL.md is about 3.3k 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, covering Performance reviews and LLM inference and serving. It works with ONNX. The licence is MIT.

When your agent uses it

  • Quark ONNX docs
  • Custom-op registry
  • Quantization config presets
  • Calibration methods

Example prompts

  • “check if ONNX skills are up to date”
  • “sync ONNX skills with Quark”
  • “has Quark ONNX changed”
  • “/quark-onnx-skill-sync”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Collect: Identify all source-knowledge dependencies across ONNX skills (union of frontmatter source_knowledge + the table above).
  2. Audit: Check each source file for changes relevant to ONNX skill content (presets, algo configs, calibration methods, custom ops, ORT…
  3. Classify: Tag each finding as mechanical, semantic, or breaking.
  4. Report: Present findings in a structured validation_report.md.
  5. Confirm: Get approval before applying any fixes; never auto-apply breaking drift.

What it can do on your machine

Read from SKILL.md and the folder at commit 313cb0b. 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 (its code samples are markdown).

    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

Quark Onnx Skill Sync loads about 3.3k tokens when it runs. Until then it costs about 151 tokens; SKILL.md has 318 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~151
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k

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 amd/Quark at commit 313cb0b, republished under its MIT licence (© amd). 318 words, ~3,348 tokens.

Download SKILL.mdSave it as .claude/skills/quark-onnx-skill-sync/SKILL.md (or your agent's skills folder).
name
quark-onnx-skill-sync
description
Detect upstream Quark ONNX changes that affect the ONNX skill family and classify required updates. Use when Quark ONNX docs, custom-op registry, quantization config presets, calibration methods, AutoSearchPro presets, ONNX Runtime install matrix, or source behavior under `quark/onnx/` may have drifted from the skill contracts. Trigger for "check if ONNX skills are up to date", "sync ONNX skills with Quark", "has Quark ONNX changed", "update ONNX skills after Quark upgrade", or when ONNX debugging reveals a mismatch between skill instructions and actual `quark.onnx` behavior.
layer
meta
backend
onnx
primary_artifact
validation_report.md
source_knowledge
docs/source/install.rst, docs/source/onnx/basic_usage_onnx.rst, docs/source/onnx/user_guide_config_description.rst…

quark-onnx-skill-sync

Purpose

Audit upstream Quark ONNX source against the assumptions baked into the quark-onnx-* skill family and report which skills or contracts need updates. ONNX-side drift is dangerous because the quantization presets, calibration methods, custom-op registry, deployment-target gates, and AutoSearchPro presets are referenced by name in skill decision tables — a renamed QConfig field, a removed preset, a new calibration method, or a new custom op silently produces wrong guidance.

Inputs

  • Quark upstream ONNX source files (quark/onnx/, examples/onnx/, tutorials/onnx/, docs/source/onnx/, tools/ci/install_onnxruntime.sh)
  • Existing ONNX skill SKILL.md files under .claude/skills-impl/{l1-atomic,l2-workflows,l3-recipes}/onnx/
  • ONNX-side shared schemas under .claude/skills-impl/shared/contracts/

Outputs: validation_report.md

Lists which ONNX skills or contracts need updates after a Quark ONNX upstream change.

Schema: validation_report.schema.json

markdown
# ONNX Skill Sync Report

## What to Check

### Source Knowledge Dependencies

Each ONNX skill declares `source_knowledge` files. Check that these files still exist and that the
skill's content matches the current source:

| Skill | Source Files to Check |
|-------|----------------------|
| `quark-onnx-install` | `tools/ci/install_onnxruntime.sh`, `docs/source/install.rst`, `requirements.txt`, `quark/onnx/operators/custom_ops/build_custom_ops.py` |
| `quark-onnx-router` | `docs/source/install.rst`, `docs/source/onnx/basic_usage_onnx.rst`, `docs/source/onnx/onnx_examples.rst`, `examples/onnx/model_support.md` |
| `quark-onnx-model-intake` | `quark/onnx/__init__.py`, `quark/onnx/quantization/api.py`, `quark/onnx/quantization/config/custom_config.py`, `quark/onnx/quantization/input_check.py`, `quark/onnx/operators/custom_ops/build_custom_ops.py`, `docs/source/onnx/basic_usage_onnx.rst` |
| `quark-onnx-quant-plan` | `quark/onnx/quantization/config/custom_config.py`, `quark/onnx/quantization/config/algorithm.py`, `quark/onnx/quantization/config/config.py`, `quark/onnx/calibration/methods.py`, `docs/source/onnx/user_guide_config_description.rst`, `docs/source/onnx/appendix_full_quant_config_features.rst` |
| `quark-onnx-debug` | `quark/onnx/quantization/quantize.py`, `quark/onnx/quantization/api.py`, `quark/onnx/quantization/input_check.py`, `quark/onnx/calibration/calibrators.py`, `quark/onnx/operators/custom_ops/build_custom_ops.py`, `quark/onnx/quantizers/registry.py`, `docs/source/onnx/gpu_usage_guide.rst` |
| `quark-onnx-result-validator` | `quark/onnx/quantization/api.py`, `quark/onnx/quantization/config/custom_config.py`, `quark/onnx/operators/custom_ops/__init__.py`, `examples/onnx/yolo_quantization/quantize_yolo.py` |
| `quark-onnx-ptq-workflow` | `examples/onnx/yolo_quantization/quantize_yolo.py`, `tutorials/onnx/ryzen_ai/yolov8/`, `tutorials/onnx/ryzen_ai/resnet50/`, `docs/source/onnx/basic_usage_onnx.rst`, `docs/source/onnx/user_guide_config_description.rst`, `quark/onnx/quantization/config/custom_config.py` |
| `quark-onnx-autosearch-pro` | `quark/onnx/quantization/auto_search/auto_search_pro.py`, `quark/onnx/quantization/auto_search/qconfig_mapping.py`, `quark/onnx/quantization/auto_search/config_generator.py`, `examples/onnx/auto_search/auto_search_pro_model.py`, `docs/source/onnx/user_guide_auto_search_pro.rst` |

### Key Facts to Verify

1. **ONNX Runtime install matrix** — check `tools/ci/install_onnxruntime.sh` for the supported
   `(accelerator, EP, ORT package, ORT version)` combinations cited by `quark-onnx-install`.
2. **Python and core dependency versions** — `pyproject.toml` `requires-python`, `requirements.txt`
   (`onnx`, `onnxruntime*`, `onnxslim`, `onnxscript`) versions cited by `quark-onnx-install` / `quark-install`.
3. **Quantization presets** — check `quark/onnx/quantization/config/custom_config.py` for the
   preset list (`XINT8`, `A8W8`, `A16W8`, `BF16`, `BFP16`, `MX*`, `MXFP*`, weights-only INT4 …)
   referenced by `quark-onnx-quant-plan` and `quark-onnx-ptq-workflow`.
4. **QConfig surface** — fields cited by skill decision tables: `global_config`, `algo_config`,
   `EnableNPUCnn`, `EnableNPUTransformer`, `use_external_data_format`, `exclude`,
   `calibration_method`, `OptimDevice`. Verify each still exists in `config.py` / `custom_config.py`.
5. **Calibration methods** — `MinMax`, `Percentile`, `Entropy`, `Distribution`, `MinMSE`,
   `LayerwisePercentile` cited by `quark-onnx-quant-plan` are still present in
   `quark/onnx/calibration/methods.py` (and `calibrators.py`).
6. **Algorithm configs** — `CLEConfig`, `BiasCorrectionConfig`, `AdaRoundConfig`, `AdaQuantConfig`,
   `SmoothQuantConfig`, `QuaRotConfig`, `GPTQConfig`, `FastFinetuneConfig` cited by the plan and
   AutoSearchPro recipe still exist in `quark/onnx/quantization/config/algorithm.py`.
7. **Custom-op registry** — `BFPQuantizeDequantize`, `MXQuantizeDequantize`, the `Extended*`
   family, and the `com.amd.quark` opset domain are still registered under
   `quark/onnx/operators/custom_ops/__init__.py`. The build pipeline in
   `build_custom_ops.py` still matches `quark-onnx-install` / `quark-onnx-debug` expectations.
8. **Deployment-target gates** — `EnableNPUCnn=True`, `EnableNPUTransformer=True`, and the
   `CPU` / `CUDA` / `ROCm` execution-provider gates referenced by `quark-onnx-ptq-workflow`
   still match what `custom_config.py` accepts.
9. **AutoSearchPro presets** — `ADVANCED_SEARCH`, `XINT8_SEARCH`, `A8W8_SEARCH`, `A16W8_SEARCH`
   cited by `quark-onnx-autosearch-pro` are still defined in
   `quark/onnx/quantization/auto_search/auto_search_pro.py` and exposed by `config_generator.py`.
10. **External-data threshold** — the `>2 GB` rule that triggers
    `use_external_data_format=True` in `quark-onnx-model-intake` and the workflow still matches
    what `api.py` / `input_check.py` enforce.
11. **Already-quantized detection** — the QDQ / `com.amd.quark` domain checks that intake uses
    to stop before re-quantizing still match `input_check.py`.
12. **YOLOv8 example pin** — `examples/onnx/yolo_quantization/quantize_yolo.py` still matches
    the `quark-onnx-ptq-workflow` worked example (`example-xint8-yolov8n.md`).

### Drift Classification

- **Mechanical drift**: a preset name, calibration-method name, custom-op name, ORT version,
  or QConfig field rename. Straightforward — update the affected table or list in the skill.
- **Semantic drift**: a workflow pattern changed (e.g. AutoSearchPro now requires a two-stage
  search by default; CLE moved from `algo_config` to a pre-pass); a deployment-target gate
  was redefined; a custom-op signature changed. Requires careful skill rewriting.
- **Breaking drift**: a referenced preset, calibration method, custom op, AutoSearchPro preset,
  ORT package, or `QConfig` field was removed entirely. The skill will produce wrong guidance
  until fixed.

## Audit Process

1. **Discover dependencies**: Read `source_knowledge` from each ONNX skill's frontmatter and
   union with the table above.
2. **Check for changes**: Compare current source against what the skills assume. Look for:
   - New presets / algorithms / calibration methods not mentioned in skills (e.g. a new
     `MXFP6` preset or a new `FastFinetune` knob).
   - Removed presets / methods / custom ops still mentioned in skills (e.g. deprecated
     `BFP16Spec` field).
   - Renamed QConfig fields (e.g. `EnableNPUCnn` → `enable_npu_cnn`).
   - Changed value ranges (e.g. AutoSearchPro trial budget defaults).
   - Custom-op binary names / load paths that drift from `build_custom_ops.py`.
   - ORT EP names changing (`CUDAExecutionProvider` / `ROCMExecutionProvider` / `VitisAIExecutionProvider`).
3. **Classify each drift**: mechanical, semantic, or breaking.
4. **Report**: Produce a `validation_report.md` with the findings.

## Rules

- **Do not auto-fix breaking drift** — report it and require human confirmation before applying
  changes.
- **Mechanical drift can be flagged for batch update** — preset additions, calibration-method
  name normalizations, and ORT version bumps are safe to apply after review.
- **If no prior baseline exists**, run calibration mode: record the current state of all ONNX
  source files as the baseline for future comparisons.
- **Never edit ONNX source under audit** — `quark/onnx/`, `examples/onnx/`, `tutorials/onnx/`,
  `docs/source/onnx/`, and `tools/ci/install_onnxruntime.sh` are read-only from this skill.
  Drift is reported, not patched at the source.
- **Stay in the ONNX scope** — do not touch `quark-torch-*` skills. Torch-side drift belongs to
  `quark-torch-skill-sync`; if a finding crosses scopes (e.g. a shared schema field), surface it
  but defer the cross-cut change to the torch maintainer.

## Summary
- Checked: 8 ONNX skills, 17 source files, 4 contract schemas
- Mechanical drift: 2 findings
- Semantic drift: 1 finding
- Breaking drift: 1 finding

## Breaking Drift
### quark-onnx-quant-plan: removed calibration method
- **Skill says**: `Distribution` is a supported calibration method
- **Source says**: `Distribution` removed from `quark/onnx/calibration/methods.py` (replaced by `LayerwisePercentile`)
- **Impact**: Users selecting `Distribution` will hit `ValueError` at plan-to-script translation
- **Fix**: Drop `Distribution` row from `quark-onnx-quant-plan` calibration table; update workflow examples

## Semantic Drift
### quark-onnx-autosearch-pro: search now two-stage by default
- **Source**: `auto_search_pro.py` now runs a coarse + fine pass; old single-stage flag deprecated
- **Impact**: Skill's "single-shot search" framing is now misleading; trial budget interpretation changed
- **Fix**: Rewrite the "Search budget" section and the preset table to reflect two-stage semantics

## Mechanical Drift
### quark-onnx-quant-plan: new preset added
- **Source**: `custom_config.py` now exposes `MXFP6_E3M2` preset
- **Impact**: Users asking about MXFP6 won't see it in the preset list
- **Fix**: Add `MXFP6_E3M2` row to the preset table

### quark-onnx-install: ORT version bump
- **Source**: `tools/ci/install_onnxruntime.sh` now pins `onnxruntime-rocm==1.20.0` (was 1.19.2)
- **Impact**: Skill recommends 1.19.2; users on 1.20.0 are told to downgrade
- **Fix**: Update ROCm row in the ORT install matrix

Interaction Flow

  1. Collect: Identify all source-knowledge dependencies across ONNX skills (union of frontmatter source_knowledge + the table above).
  2. Audit: Check each source file for changes relevant to ONNX skill content (presets, algo configs, calibration methods, custom ops, ORT matrix, AutoSearchPro presets, deployment-target gates).
  3. Classify: Tag each finding as mechanical, semantic, or breaking.
  4. Report: Present findings in a structured validation_report.md.
  5. Confirm: Get approval before applying any fixes; never auto-apply breaking drift.

Recovery

  • If a source file no longer exists (was moved or deleted), this is breaking drift. Report the missing file and suggest where the information might have moved to (e.g. custom_config.py → config/presets/).
  • If tools/ci/install_onnxruntime.sh is missing or replaced, surface the gap to quark-onnx-install so its ORT matrix is not silently stale.
  • If the ONNX custom-op build pipeline (build_custom_ops.py) has changed, mark quark-onnx-install and quark-onnx-debug as potentially affected even when no string drift is observed — custom-op load failures are runtime-only.
  • If the upstream Quark repository is not accessible, report the blocked audit and which ONNX skills could not be verified.
  • If drift crosses backends (e.g. a shared/contracts/ schema field used by both torch and onnx skills), report it but hand off the cross-cut change to the torch maintainer rather than editing torch skills from here.

© amd, 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 .claude/skills-impl/meta/onnx/quark-onnx-skill-sync of amd/Quark.

Open the folder on GitHubat commit 313cb0b

Compare with similar skills

Quark Onnx Skill Sync 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.

Quark Onnx Skill Sync compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Quark Onnx Skill Sync this skillamd/Quark181—~3.3kAutomated safety check: PassMIT
Astreawarpfront/hipfire653—~2.6kAutomated safety check: PassCustom licence
Aipc Toolkitqualcomm/qai-appbuilder246—~5.7kAutomated safety check: NotesCustom licence
Add Vlm Modelintel/auto-round1.6k—~2.4kAutomated safety check: PassApache-2.0
Tensorrt Optimizationmajiayu000/claude-skill-registry6661 repos~2.4kAutomated safety check: NotesMIT
Matlab Use Visual Inspectionmatlab/matlab-agentic-toolkit1.1k—~3.1kAutomated safety check: PassCustom licence

Similar skills

  • Astrea

    warpfront/hipfire

    A skill your agent uses for hipfire quant calibration, imatrix-driven experiments, KLD/PPL quality evaluation, k-map/format selection, MQ/HFQ/HFP/MFP tradeoff work, ParoQuant-style weight transform…

    653 GitHub stars~2.6k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Aipc Toolkit

    qualcomm/qai-appbuilder

    AIPC, AI Porting Conversion. An agent skill from qualcomm/qai-appbuilder.

    246 GitHub stars~5.7k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

  • Add Vlm Model

    intel/auto-round

    Official

    Add support for a new Vision-Language Model (VLM) to AutoRound, including multimodal block handler, calibration dataset template, and special model handling.

    1.6k GitHub stars~2.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Tensorrt Optimization

    majiayu000/claude-skill-registry

    NVIDIA TensorRT model optimization and deployment. An agent skill from majiayu000/claude-skill-registry.

    666 GitHub starsUsed in 1 repo~2.4k tokens
    AI & LLM EngineeringAuto-check: notes

  • Matlab Use Visual Inspection

    matlab/matlab-agentic-toolkit

    Build machine vision inspection systems with MATLAB Visual Inspection Toolbox.

    1.1k GitHub stars~3.1k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Onboard Jetpack5 Inference Backends

    EGalahad/sim2real

    Install, convert, debug, and benchmark sim2real ONNX GPU and TensorRT inference backends on onboard JetPack 5 Orin hosts such as g1-cable.

    145 GitHub stars~1.1k tokensUpdated 10 days ago
    AI & LLM EngineeringAuto-check passed

More from amd/Quark

All 37 skills in this repo

  • Quark Skill Creator

    amd/Quark

    Author or restructure a Quark Agent Skill so it conforms to this project's template, contracts, and layer rules.

    181 GitHub stars~3.1k tokensUpdated 10 days ago
    Auto-check passed

  • Quark Torch Quant Perf

    amd/Quark

    Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.

    181 GitHub stars~3k tokensUpdated 10 days ago
    Auto-check passed

  • Quark Create Shapeshifter Pass

    amd/Quark

    Author a new ShapeShifter graph-transformation pass for AMD Quark (ONNX or PyTorch) so it conforms to the pass framework's conventions and auto-registers.

    181 GitHub stars~2.9k tokensUpdated 10 days ago
    Auto-check passed

  • Quark Env Preflight

    amd/Quark

    Collect and normalize environment facts (OS, Python, GPU, CUDA/ROCm, container state) before Quark installation or PTQ planning.

    181 GitHub stars~1.4k tokensUpdated 10 days ago
    Auto-check passed

  • Quark Install

    amd/Quark

    Install or verify the AMD Quark package and its dependencies.

    181 GitHub stars~1.8k tokensUpdated 10 days ago
    Auto-check: notes

  • Quark Onnx Autosearch Pro

    amd/Quark

    L3 recipe that runs quark.onnx.AutoSearchPro end-to-end on a user .onnx model: intake → preset selection (or custom search space) → calibration / eval data reader → standalone autosearch script…

    181 GitHub stars~3.4k tokensUpdated 10 days ago
    Auto-check passed

Works with

Categories

Questions about Quark Onnx Skill Sync

What does Quark Onnx Skill Sync do?

Detect upstream Quark ONNX changes that affect the ONNX skill family and classify required updates. Quark Onnx Skill Sync is an agent skill from amd/Quark. Detect upstream Quark ONNX changes that affect the ONNX skill family and classify required updates.

When should I use Quark Onnx Skill Sync?

Quark Onnx Skill Sync fits situations like: quark ONNX docs; custom-op registry; quantization config presets; calibration methods.

How do I install Quark Onnx Skill Sync in Claude Code?

Run `npx skills add amd/Quark --skill quark-onnx-skill-sync -a claude-code`. Or copy the skill folder (.claude/skills-impl/meta/onnx/quark-onnx-skill-sync in amd/Quark) into .claude/skills/quark-onnx-skill-sync in your project. Claude Code loads it when a task matches its description.

How do I install Quark Onnx Skill Sync in Codex?

Run `npx skills add amd/Quark --skill quark-onnx-skill-sync -a codex`. Or copy the skill folder (.claude/skills-impl/meta/onnx/quark-onnx-skill-sync in amd/Quark) into .agents/skills/quark-onnx-skill-sync in your project. Codex loads it when a task matches its description.

Can I use Quark Onnx Skill Sync 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 amd/Quark --skill quark-onnx-skill-sync -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/quark-onnx-skill-sync, .gemini/skills/quark-onnx-skill-sync, .github/skills/quark-onnx-skill-sync and .opencode/skills/quark-onnx-skill-sync in your project.

What does Quark Onnx Skill Sync need to run?

SKILL.md names no scripts, command-line tools or credentials: Quark Onnx Skill Sync is instructions for the agent only. Our summary lists: Python 3.

Does Quark Onnx Skill Sync 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 Quark Onnx Skill Sync 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 Quark Onnx Skill Sync use?

Quark Onnx Skill Sync 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 Quark Onnx Skill Sync use?

About 3.3k tokens (SKILL.md is roughly 13k 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 Quark Onnx Skill Sync?

Skills that share tags, products or a category with Quark Onnx Skill Sync: Astrea (warpfront/hipfire, 653 stars), Aipc Toolkit (qualcomm/qai-appbuilder, 246 stars), Add Vlm Model (intel/auto-round, 1.6k stars) and Tensorrt Optimization (majiayu000/claude-skill-registry, 666 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Quark Onnx Skill Sync?

amd (a GitHub organization) maintains it in amd/Quark, which has 181 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on September 28, 2026.

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