miwrite-report-mode
Local-only conversion of research material into briefs, memos, and decision-facing reports.
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Local-only conversion of research material into briefs, memos, and decision-facing reports.
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…
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…
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.…
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…
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 …
Strategy for contributing to open source projects effectively. Covers identifying tractable issues (good first issue, help wanted), reading unfamiliar codebases efficiently, communicating with maintai…
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…
Local-only manuscript, report, and chapter review.
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…
>
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…
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.
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…
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…
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…
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…
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…
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…
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 (…
>
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…
Retrieve scholarly literature across the five package APIs into a provenance-rich inventory.
太奶讀論文 — 一位百歲阿嬤用繁體中文、生活比喻和動漫梗,帶你讀懂學術論文。當使用者提供論文 PDF、arXiv 連結、或貼上論文文字,並想理解論文內容時,一定要使用此技能。觸發詞包括:讀論文、解釋論文、看不懂、幫我理解這篇、這篇在說什麼、paper reading、explain this paper。適用於任何學術論文的直觀導讀。