Skill 资源库

AI Skill 资源库

把 Skill 的源码、资源快照、README、包体和安装信号放进一个可搜索、可筛选的公开目录。

personTashanworldKey 暂未确认

miwrite-read

Local-only close reading for papers, reports, policy texts, and chapters.

download3deployed_code—star0
personTashanworldKey 暂未确认

model-pruning

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabli…

download3deployed_code—star0
personTashanworldKey 暂未确认

music-generation

Use this skill when the user requests to generate, create, compose, or produce music or songs — background music, theme songs, jingles, or instrumental tracks. Generates a song from a style/mood promp…

download3deployed_code—star0
personTashanworldKey 暂未确认

nemo-curator

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, N…

download3deployed_code—star0
personTashanworldKey 暂未确认

nnsight-remote-interpretability

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (…

download3deployed_code—star0
personTashanworldKey 暂未确认

optimizing-attention-flash

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory iss…

download3deployed_code—star0
personTashanworldKey 暂未确认

paper-discovery

Retrieve scholarly literature across the five package APIs into a provenance-rich inventory.

download3deployed_code—star0
personTashanworldKey 暂未确认

moe-training

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures l…

download3deployed_code—star0
personTashanworldKey 暂未确认

napari-workflow-builder

build reproducible napari-centered bioimage analysis workflows in python using numpy, scipy, scikit-image, tifffile, pandas, matplotlib, and napari. use when the task involves interactive image inspec…

download3deployed_code—star0
personTashanworldKey 暂未确认

nemo-guardrails

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.…

download3deployed_code—star0
personTashanworldKey 暂未确认

notebooklm-brief-verifier

Compare a downloaded NotebookLM brief against the source bundle research-hub uploaded, and report missed sources, unsupported claims, contradictions, and recommended follow-up prompts. Use when the us…

download3deployed_code—star0
personTashanworldKey 暂未确认

opentrons-lab-automation

Use OpentronsAgent for Opentrons lab automation workflows. Applies when requests mention Opentrons lab automation protocols robots, or when a user needs guarded API/tool access, provenance review, or …

download3deployed_code—star0
personTashanworldKey 暂未确认

oss-contribution

Strategy for contributing to open source projects effectively. Covers identifying tractable issues (good first issue, help wanted), reading unfamiliar codebases efficiently, communicating with maintai…

download3deployed_code—star0
personTashanworldKey 暂未确认

paper-memory-builder

Convert a paper draft + figures + Zotero metadata into reusable .paper/claims.yml and .paper/figures.yml files so the academic-writing-skills skill can do writing, revision, and audit passes without r…

download3deployed_code—star0
personTashanworldKey 暂未确认

multi-perspective

Explore a research question through several independent analytical perspectives and synthesize their agreements and disagreements. Use when one line of reasoning is insufficient and distinct viewpoint…

download3deployed_code—star0
personTashanworldKey 暂未确认

neurokit2

Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activi…

download3deployed_code—star0
personTashanworldKey 暂未确认

openapi-spec-generation

Generate and maintain OpenAPI 3.1 specifications from code, design-first specs, and validation patterns. Use when creating API documentation, generating SDKs, or ensuring API contract compliance.

download3deployed_code—star0
personTashanworldKey 暂未确认

optimize-for-gpu

GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user mentions GPU/CUDA/NVIDIA acceleration, or wants…

download3deployed_code—star0
personTashanworldKey 暂未确认

oss-project-setup

Setting up an open source project from scratch with the right files, conventions, and infrastructure to invite contributions and ensure long-term maintainability. Covers license selection (MIT, Apache…

download3deployed_code—star0
personTashanworldKey 暂未确认

paper-readability-check

Check an academic paper draft against sentence- and paragraph-level readability criteria, then produce revised text and a before/after report with checklist references. Use for paper drafts, manuscrip…

download3deployed_code—star0