AGENT SKILL

tensorflow-quantum

Guide TensorFlow Quantum workflows for circuit tensors, Keras quantum layers, differentiators, datasets, and tutorial recipes.

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

01 前言 Front Matter

name
tensorflow-quantum
license
Apache 2.0
metadata
{ "disco-role": "operating" }
description
Guide TensorFlow Quantum workflows for circuit tensors, Keras quantum layers, differentiators, datasets, and tutorial recipes.
disable-model-invocation
true

02 资源文件 6

03 SKILL.md 正文

TensorFlow Quantum

Use this skill when a prompt is about the TensorFlow Quantum package or the public tensorflow_quantum module.

Route here when the user asks about

  • package install, import, version, or TF_USE_LEGACY_KERAS setup
  • circuit tensor conversion, raw execution getters, noisy execution, or tfq.math
  • tfq.layers model wiring, readout layers, or quantum-classical Keras models
  • differentiators, gradient plumbing, or tiny optimizer loops
  • dataset helpers, notebook-derived recipes, or tutorial-style examples

Sub-skill map

  • sub-skills/tensor-ops-and-execution/SKILL.md for tfq.convert_to_tensor, tfq.from_tensor, raw execution ops, tfq.noise, tfq.math, and quantum-concurrent op mode questions
  • sub-skills/keras-quantum-layers/SKILL.md for tfq.layers, append/prepend wiring, PQC/ControlledPQC families, and noisy readout layers
  • sub-skills/differentiation-and-optimizers/SKILL.md for tfq.differentiators, tfq.optimizers, and gradient/parameter-search workflows
  • sub-skills/datasets-and-tutorials/SKILL.md for tfq.datasets helpers and the notebook-style recipe summaries

Start here

  • references/installation-and-compatibility.md
  • references/api-overview.md
  • references/troubleshooting.md
  • references/repo-provenance.md when checking whether this skill still matches the checkout
  • scripts/tfq_smoke_check.py

Fast path

If the prompt is short and factual, answer from references/api-overview.md. If it asks for setup or compatibility, read references/installation-and-compatibility.md first. If it reports an error, use references/troubleshooting.md before changing the recipe.

Minimal setup reminder

  • TensorFlow Quantum supports Python 3.10-3.12.
  • Set TF_USE_LEGACY_KERAS=1 before importing TensorFlow or TFQ.
  • Install the package first, then run python scripts/tfq_smoke_check.py --quick.
  • Add --layers, --datasets, --differentiators, or --math when you need a slightly deeper smoke.

Shared route rule

Do not force a low-level tensor or backend issue into a layers or dataset route. Use the owning sub-skill so the future agent gets the right reference and smoke path on the first try.

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