Documents skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

dataset-transformation

Generates code that transforms datasets between ML schemas for model training or evaluation. Use when the user says "transform", "convert", "reformat", "change the format", or when a dataset's schema needs to change to match the target format — always use this skill for format changes rather than writing inline transformation code. Supports OpenAI chat, SageMaker SFT/DPO/RLVR/RLAIF, HuggingFace preference, Bedrock Nova, VERL, and custom JSONL formats from local files or S3.

157 repo starsObserved in 1 repos
Documents
GitHub

hve-spielberg

End-to-end video production pipeline with design thinking. 6-phase orchestrator: Discovery (design thinking + context) → Storytelling (narrative + storyboard) → Capture (Chrome DevTools screenshots + screencast clips, asciinema terminal recording) → Design (HyperFrames scene templates) → Production (HyperFrames composition) → Audio & Render (ElevenLabs + Whisper + Freesound music). Three content modes: promo (marketing), showcase (portfolio/demo), or tutorial (walkthrough/how-to). Triggers: "create video", "promo video", "showcase video", "tutorial video", "walkthrough video", "how-to video", "product video", "demo video", "launch video".

157 repo starsObserved in 1 repos
Documents
GitHub

integration-docs-style

Applies ngrok integration docs style rules when writing or editing "using ngrok with" guides, integration docs, or MDX in using-ngrok-with. Use when creating or revising integration documentation, when the user asks for style compliance, or when editing files in using-ngrok-with.

157 repo starsObserved in 1 repos
Documents
GitHub

powerbi-documentation

Create standardized documentation for Power BI semantic models and reports. Use when the user requests documentation for a Power BI project, semantic model, or report (e.g., "document this model", "create documentation for this Power BI project", "generate documentation"). This skill works with the powerbi-modeling-mcp server to extract model metadata and generate professional Word documents.

157 repo starsObserved in 1 repos
Documents
GitHub

bilibili-page-reader

Get content from Bilibili videos: official subtitles, danmaku (density/peaks/sample), comments. When no subtitles exist (no 投稿字幕), fall back to downloading audio + ASR transcription via FunASR.

156 repo starsObserved in 2 repos
Documents
GitHub

changelog-format

CHANGELOG.md format reference and examples for the SimpleORM project.

156 repo starsObserved in 1 repos
Documents
GitHub

faust-metadata-audit

Generate a compact Markdown audit of user-facing chart text (Title, Subtitle, Footnote, description_short, description_key — i.e. FAUST) for an MDim, a grapher/garden dataset, or a hand-picked list of indicators. Each field is tagged by source (override / inherited / missing) so the reader can tell what Grapher renders vs. what comes from the ETL metadata. Trigger when the user wants to review, audit, or spot-check the user-facing text of one or many charts/indicators at once — e.g. "audit the FAUST for dataset X", "dump the FAUST for dataset X", "I want to review the text of all views in this MDim", "show me the chart text for these indicators".

156 repo starsObserved in 1 repos
Documents
GitHub

owid-metadata-generation

Use when creating or enriching metadata for OWID ETL datasets - generates comprehensive YAML metadata from dataset inspection, data exploration, and web research following OWID metadata standards. Trigger when writing or editing *.meta.yml files, when a garden step has empty or minimal metadata, or when user asks to improve/add/enrich metadata.

156 repo starsObserved in 1 repos
Documents
GitHub

PPTX 演示助手

生成、编辑和读取 PowerPoint 演示文稿。支持三类任务： 1) 读取或分析现有 PPTX 文本内容； 2) 在模板或已有演示文稿上做 XML 安全编辑； 3) 从零创建新演示文稿并输出原生 .pptx 文件。 适用于 .pptx 演示文稿创建、结构化改写、模板复用、讲稿梳理与版式优化。

156 repo starsObserved in 1 repos
Documents
GitHub