Turns audio and video into speaker-labeled, timestamped transcripts — and owns ASR audio preprocessing as a first-class job.
Turns raw meeting transcripts into structured, evidence-backed minutes with decisions, owners, and action items.
Diagnoses and repairs broken repository setups, then standardizes onboarding docs and safe Git workflows.
Fetch real, citable Bilibili video metadata, live engagement stats, and full danmaku text from a BVID, av number, b23.tv link, or URL — no login required.
Searches every Claude Code (and optionally Codex) session archive and recovers deleted files byte-for-byte from file-history snapshots.
Turns a frontend project or webpage into a cinematic product promo video using Remotion, real page screenshots, 2.5D camera moves, beat-synced cuts and sound design.
A three-mode translation skill (quick / normal / refined) with glossary merging, markdown chunking and a publication-quality review pipeline.
Composes and publishes tweets, images, videos, quote tweets and long-form Markdown Articles to X using a real, logged-in Chrome browser.
Give it a YouTube link and get the transcript, translation, chapters and cover image as Markdown or SRT.
Turns any article or idea into a 1–10 image card series for social media, with 12 styles, 8 layouts and 3 palettes.
Turns any article or document into a style-consistent set of slide images and merges them into PPTX and PDF.
Unpacks an installed Electron app's app.asar and rebuilds the original source tree from .js.map files when available.
A universal release workflow that auto-detects your version file, bumps semver, writes multi-language changelogs, and publishes tags plus GitHub Releases.
Generates professional dark-themed, self-contained SVG diagrams across nine types — architecture, flowchart, sequence, mind map, timeline and more.
Turns plain text or rough markdown into a clean, scannable article with frontmatter, headings, lists and tables — without changing a single word of the original.
Turns any content into a publication-ready infographic by combining 21 layout types with 22 visual styles.
One CLI-backed skill that generates images through 10+ providers — OpenAI, Google, DashScope, MiniMax, Replicate and more.
Turns Markdown files into beautifully styled, inline-CSS HTML ready to paste into WeChat or any editor.
Turns a topic or article into a full educational comic — storyboard, consistent characters, generated pages, and a merged PDF.