SuperAPI AI DirectoryFind an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
25,512 results
Alipay agent wallet/AI payment product introduction skill. Use when the user wants to obtain product introductions related to Alipay AI payment and agent wallet. Trigger conditions: 1) The user asks "What is Alipay AI payment", "agent wallet introduction", "AI payment product"; 2) The user wants to understand the features of Alipay agent wallet. Keywords: product introduction, AI payment, agent wallet, aipay, 402, paid resource.
Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:ar-resume or asks to pick up a…
Decompose a top-line metric into a quantified metric tree with mathematical relationships, size each node, and identify where the real leverage is. Use when a…
Show status of all features in .dev/. Scans feature folders using parallel agents, generates a status report, and offers to archive completed features. Use to…
Add new capabilities to OpenClaw — plugins, hooks, agents, channels, nodes, models, devices, and webhooks. Use when extending the system with new integrations…
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
Author ComfyUI-LoRA-Manager nodes from the panel. Use when adding a LoRA Manager loader, stacker, prompt, or text node, or when panel_add_node refuses…
Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates. Use this whenever the orchestrator was…
Ascend TensorFlow Community migration and adaptation Skill, suitable for natively deploying TensorFlow 2.x-based models to Huawei Ascend NPU without TF-to-PyTorch conversion, covering aarch64 source compilation of TF 2.6.5, tfplugin installation, use of the automatic migration tool, manual adaptation, and accuracy verification.
Ascend NPU migration and reproduction Skill for the Boltz2 protein structure prediction model, suitable for preparing weights, adapting Lightning and CUDA-only kernels on Huawei Ascend 910, 910B, and 910C, completing Boltz2 end-to-end structure prediction inference, and consolidating reproducible environments and validation commands.
DeepFRI TensorFlow to PyTorch conversion and Ascend NPU migration Skill, suitable for TF model analysis, PyTorch rewriting, layer-by-layer weight mapping, NPU inference and accuracy verification in protein function prediction scenarios, especially suitable for use when DeepFRI CNN or GCN paths need to be run on Ascend.
DeepFRI TensorFlow native Ascend NPU migration Skill, suitable for scenarios that do not perform TF-to-PyTorch conversion but instead directly use TensorFlow 2.6.5 and npu_device to run DeepFRI on Huawei Ascend, covering source code compilation, tfplugin installation, code adaptation, inference, and CPU comparison verification.
Ascend NPU migration Skill for the GENERator DNA sequence generation model, suitable for migrating a HuggingFace Transformers-based Causal LM from CUDA to Huawei Ascend NPU, covering environment setup, dependency installation, code adaptation, multiprocessing handling, and sequence recovery validation.
OligoFormer Ascend NPU Migration Skill, suitable for migrating a PyTorch Transformer-based siRNA efficacy prediction model to Huawei Ascend NPU, covering environment setup, RNA-FM dependency installation, code adaptation, inference validation, and optional training workflow.
ProteinBERT Ascend NPU deployment and migration Skill, suitable for converting the TensorFlow or Keras version of ProteinBERT into an implementation based on PyTorch and torch_npu, covering weight conversion, embedding extraction, fine-tuning training, attention visualization, and GPU and NPU accuracy verification.
A general Skill for rewriting TensorFlow or Keras models to PyTorch, suitable for completing layer mapping, weight conversion, layer-by-layer numerical verification, and end-to-end accuracy comparison on Huawei Ascend NPU or other platforms that depend on the PyTorch ecosystem, and especially suitable for cross-framework migration of scientific models such as ProteinBERT and DeepFRI.
Build an automated workflow for the vLLM-ascend project, process closed Issues and generate a Debug FAQ. Use when users want to process closed issues from vLLM-ascend repository, generate debug FAQ, categorize…
Automatically fetch InferenceX benchmark data and generate daily performance reports for LLM inference on various hardware (NVIDIA, AMD, etc.). Supports email…
Guide and automate the collection of Profiling data for MindSpeed-MM model training on Ascend NPU. By identifying the training script, automatically locate the configuration file and enable the built-in Profiler, supporting static collection (specified start/end steps) and dynamic collection (runtime dynamic on/off), supporting the Megatron engine (tools.json) and standalone FSDP2…
Use when auditing or updating .gitattributes export-ignore coverage so dev-only files (lint configs, CI, tests, docs, build tooling) don't ship in the…
Spin up an instant browser voice session (OpenAI Realtime gpt-realtime-2) to close a topic in a short conversation instead of working through documents.…
Comprehensive audit skill for agents and skills across the plugin ecosystem. This skill should be used when the user asks to "audit agents", "review skill…
This skill should be used when the user says "deploy a team", "spin up agents to work on this", "use all our agents", "coordinate specialists", or wants to…
Route to the right agent, skill, or service provider. Use for "who handles X?", "what agents are available?", "team roster", "what skills are available?",…