AGENT SKILL

datasets-and-tutorials

Route TFQ dataset helpers and notebook-style workflows.

License 许可
Apache-2.0
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
datasets-and-tutorials
license
Apache 2.0
metadata
{ "disco-role": "operating" }
description
Route TFQ dataset helpers and notebook-style workflows.
disable-model-invocation
true

02 资源文件 3

03 SKILL.md 正文

Datasets and Tutorials

Use this skill for TensorFlow Quantum prompts about dataset loaders, tuple outputs, and the small notebook-derived recipes used in the public tutorials.

Route here when the user asks about

  • tfq.datasets.excited_cluster_states
  • tfq.datasets.tfi_chain
  • tfq.datasets.xxz_chain
  • tuple contents such as circuits, labels, pauli_sums, and SpinSystemInfo
  • notebook snippets from hello_many_worlds, gradients, noise, qcnn, quantum_data, quantum_reinforcement_learning, and research_tools

Do not use this skill for

  • low-level tensor/backend mechanics; hand off to tensor-ops-and-execution
  • broader Keras layer design beyond the notebook recipes here; hand off to keras-quantum-layers
  • full notebook validation or maintainer scrubbing as a default runtime step
  • Bazel/source-build or benchmark workflows

Read first

  • references/api-reference.md
  • references/workflows.md
  • references/troubleshooting.md

Fast answer rule

If the prompt is short and factual, answer from the API reference. If it asks for a tiny worked example, use the workflow snippets. If it reports a failure, use troubleshooting before changing the recipe.

Shared smoke helper

For a tiny packaged import and round-trip check, run python scripts/tfq_smoke_check.py --quick --datasets from the root tensorflow-quantum skill directory instead of running whole notebooks.

Evidence anchors

  • Public package docs and tutorials distilled into this sub-skill's bundled references.
  • The installed-package inspection used during construction to confirm the public TFQ dataset signatures and the tiny cluster-state smoke behavior.
  • The source repository tests that establish dataset shapes, errors, and download behavior, summarized here rather than referenced directly at runtime.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351