跳到正文
cccskills
免费在 GitHub 公开

alibi

Routes Alibi users to the right explanation, confidence, prototype, or optional-backend workflow and points them to the bundled helpers needed to run it.

中文简介正在准备中。当前显示原文说明。

VectorSpaceLab/AREX-Skill
查看安装方法

包含的文件（39）

  • SKILL.md2.6 KB
  • references/api-reference.md4.0 KB
  • references/optional-dependencies.md1.9 KB
  • references/repo-provenance.md1.4 KB
  • references/repo-routing-metadata.json308 B
  • references/troubleshooting.md2.5 KB
  • references/workflows.md2.2 KB
  • scripts/check_optional_backends.py3.2 KB
  • scripts/core_smoke.py2.0 KB
  • sub-skills/anchors-local-explanations/references/anchor-text.md1.4 KB
  • sub-skills/anchors-local-explanations/references/api-reference.md1.9 KB
  • sub-skills/anchors-local-explanations/references/troubleshooting.md2.2 KB
  • sub-skills/anchors-local-explanations/references/workflows.md2.2 KB
  • sub-skills/anchors-local-explanations/scripts/check_spacy_model.py1.3 KB
  • sub-skills/anchors-local-explanations/scripts/smoke_anchor_image.py1.4 KB
  • sub-skills/anchors-local-explanations/scripts/smoke_anchor_tabular.py941 B
  • sub-skills/anchors-local-explanations/SKILL.md2.6 KB
  • sub-skills/attribution-and-shap/references/api-reference.md1.8 KB
  • sub-skills/attribution-and-shap/references/troubleshooting.md1.9 KB
  • sub-skills/attribution-and-shap/references/workflows.md2.2 KB
  • sub-skills/attribution-and-shap/scripts/check_optional_attribution_backends.py1.5 KB
  • sub-skills/attribution-and-shap/SKILL.md2.3 KB
  • sub-skills/confidence-prototypes-utilities/references/api-reference.md1.5 KB
  • sub-skills/confidence-prototypes-utilities/references/saving.md1.2 KB
  • sub-skills/confidence-prototypes-utilities/references/troubleshooting.md1.8 KB
  • sub-skills/confidence-prototypes-utilities/references/workflows.md2.4 KB
  • sub-skills/confidence-prototypes-utilities/scripts/smoke_confidence_prototypes.py1.8 KB
  • sub-skills/confidence-prototypes-utilities/SKILL.md2.4 KB
  • sub-skills/counterfactuals-and-similarity/references/api-reference.md3.0 KB
  • sub-skills/counterfactuals-and-similarity/references/backend-notes.md1.4 KB
  • sub-skills/counterfactuals-and-similarity/references/troubleshooting.md1.9 KB
  • sub-skills/counterfactuals-and-similarity/references/workflows.md2.6 KB
  • sub-skills/counterfactuals-and-similarity/scripts/check_optional_counterfactual_backends.py1.8 KB
  • sub-skills/counterfactuals-and-similarity/SKILL.md2.5 KB
  • sub-skills/global-tabular-explanations/references/api-reference.md2.1 KB
  • sub-skills/global-tabular-explanations/references/troubleshooting.md2.2 KB
  • sub-skills/global-tabular-explanations/references/workflows.md2.6 KB
  • sub-skills/global-tabular-explanations/scripts/smoke_global_tabular.py1.9 KB
  • sub-skills/global-tabular-explanations/SKILL.md2.4 KB

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

Alibi

Alibi is a Python library for model explanation, confidence scoring, prototype selection, and explanation persistence.

When to use this skill

Use this skill when a user asks how to:

  • install Alibi or choose extras
  • inspect public Alibi APIs
  • run a small reproducible Alibi workflow
  • decide which explanation family fits a task
  • diagnose MissingDependency, backend, or predictor-shape issues

First reads

  • references/workflows.md for the route map
  • references/optional-dependencies.md for extras and MissingDependency placeholders
  • references/troubleshooting.md for import, backend, and workflow failures
  • references/repo-provenance.md when checking staleness or before refresh work
  • references/api-reference.md for verified constructor signatures and return shapes

Minimal install and import

  • python -m pip install alibi
  • From a checkout: python -m pip install -e .
  • Minimal import check: python -c "import alibi; print(alibi.__version__)"
  • If the import trips over a spaCy / click issue, repair the base environment before assuming the package is broken.

Route map

sub-skills/global-tabular-explanations/

Use for ALE, partial dependence, PD variance, permutation importance, and other global tabular feature-effect workflows.

sub-skills/anchors-local-explanations/

Use for AnchorTabular, AnchorText, and AnchorImage workflows, including text sampling and image segmentation guidance.

sub-skills/attribution-and-shap/

Use for KernelShap, TreeShap, and IntegratedGradients, plus optional SHAP / TensorFlow backend selection.

sub-skills/counterfactuals-and-similarity/

Use for Counterfactual, CEM, CounterfactualProto, CounterfactualRL, and GradientSimilarity workflows.

sub-skills/confidence-prototypes-utilities/

Use for TrustScore, LinearityMeasure, ProtoSelect, and save/load round-trips.

Helper scripts

  • scripts/core_smoke.py runs a tiny CPU smoke across the base tabular workflows.
  • scripts/check_optional_backends.py reports which optional exports are placeholders and which extra enables them.

What not to do

  • Do not treat a MissingDependency placeholder as a verified runtime path.
  • Do not send users to the source checkout for docs, examples, or notebooks.
  • Do not assume optional backends are installed until the helper says so.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护，适用 Google 的隐私权政策和服务条款。

同一仓库的技能

3d-resnets-pytorch

免费

Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.

中文简介正在准备中。当前显示原文说明。

VectorSpaceLab/AREX-Skill3392026年9月3日 更新

3ddfa

免费

Guide 3DDFA Python inference, geometry rendering, training/evaluation, and optional C++ ONNX workflows for 3D dense face alignment.

中文简介正在准备中。当前显示原文说明。

VectorSpaceLab/AREX-Skill3392026年9月3日 更新

3ddfa-v2

免费

Routes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.

中文简介正在准备中。当前显示原文说明。

VectorSpaceLab/AREX-Skill3392026年9月3日 更新

ab3dmot

免费

Operate AB3DMOT 3D multi-object tracking workflows for KITTI and nuScenes data, tracking, evaluation, and visualization.

中文简介正在准备中。当前显示原文说明。

VectorSpaceLab/AREX-Skill3392026年9月3日 更新

accelerate

免费

Use Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model inference/offload, checkpointing, tracking, and troubleshooting.

中文简介正在准备中。当前显示原文说明。

VectorSpaceLab/AREX-Skill3392026年9月3日 更新

acme

免费

Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.

中文简介正在准备中。当前显示原文说明。

VectorSpaceLab/AREX-Skill3392026年9月3日 更新

查看 VectorSpaceLab 的全部技能

报告此技能的问题