Auto-detects your project's version file and changelogs, then bumps, documents, tags and publishes a release end to end.
Unpacks an installed Electron app's app.asar, restoring original sources from .js.map files or Prettier-formatting minified code.
Turns a topic or article into a full educational comic — storyboard, character sheet, per-page images, and a merged PDF.
Converts Markdown into styled, inline-CSS HTML that is ready to paste into WeChat and other publishing platforms.
Analyzes an article, picks the spots that need visuals, and generates a consistent image set using a Type × Style × Palette system before inserting them back into the text.
Converts DOCX, PDF and PPTX files into clean Markdown with eight automatic post-processing fixes.
A conversational package manager for Claude Code skills — search, install, update and remove skills from the CCPM registry without typing CLI commands.
Converts a PDF into one self-contained, readable HTML file preserving images, tables, charts and reading order — with optional translation.
A P0–P7 research pipeline with parallel subagents, a locked citation registry, source-type governance and mandatory counter-review for traceable reports.
Verifies factual claims in your documents against authoritative sources and applies corrections only after your approval.
Turns phone photos of paper documents into clean, scanner-looking A4 PDFs — with content-based page ordering and a mandatory full-document check.
Reliably download YouTube videos/audio in high quality and header-protected HLS (m3u8) streams using yt-dlp and ffmpeg.
Turns a plain-English request like "find dentists in Berlin" into a validated, locally-run Docker crawl of Google Maps for business leads, contacts, and reviews.
Teaches Claude to read, merge, split, extract tables from, OCR and generate PDFs with Python and CLI tools.
An end-to-end skill for generating, editing, extracting from, and visually QA-ing PowerPoint .pptx/.potx files.
Teaches Claude to drive a real Chrome browser through the agent-browser CLI using accessibility-tree snapshots and compact @eN refs for clicking, filling, extracting and screenshotting.
Create polished Word documents, edit existing ones at the XML level, and handle tracked changes and comments reliably.
One CLI for AI image generation across a dozen providers (OpenAI, Google, DashScope, Replicate and more) with reference images and batch mode.
Picks a multi-agent orchestration pattern from requirements, generates and validates provider-ready tool schemas, and evaluates run logs for cost, latency, and bottlenecks.
Compiles a goal into a verifiable task plan and drives a bounded agent loop with machine-run checks, retry caps, and human escalation.