A three-role pipeline (modeler → coder → paper writer) that solves math-modeling competition problems end to end with independent QA gates.
Build Word papers from official templates and convert full LaTeX manuscripts into DOCX with editable native equations, plus strict validation.
Turns a contest problem, modeling analysis and real code results into a complete, validated Word (optionally LaTeX) math-modeling paper.
A three-role pipeline that takes a math-modeling contest problem from analysis to runnable code, figures, and a full Word/LaTeX paper.
Turns PDF/PPT/Excel/Word files into structured Markdown with metadata and a parsing confidence score.
Generates short, warm companion replies via Zhipu GLM and pushes them (with a matching image) to Feishu/Discord/Telegram/WhatsApp through OpenClaw.
Generates warm, in-character encouragement via Zhipu AI (GLM-4.7-flash) and delivers it with a matching image through OpenClaw messaging.
Scrapes and cleans Chinese web-novel platform rankings, then turns the patterns into trend reports and feasibility-checked story pitches.
Parses a novel you've already written (in progress or finished) and rebuilds it into a standard, continuation-ready writing project.
Give it a book title and pen name, and it infers the genre and generates a professional web-novel cover with rendered title and author text.
Extracts business domains, flows, and process steps from a codebase and renders them as an interactive flow graph.
Answers questions about your codebase by selectively grepping a pre-built knowledge graph instead of loading it all.
Scans a Figma file through the REST API and builds an interactive knowledge graph of pages, screens, components, and design tokens.
Turns your project's knowledge graph into a complete onboarding document covering architecture, file map, and complexity hotspots.
A Clean Code review skill that scores your code 0-10 on naming, function size, error handling and tests, then lists the exact fixes to reach 10/10.
An interactive, resumable eight-phase journey that measures, untangles, and speeds up a working-but-slow codebase while logging every decision in docs/.
Turns messy competitor material — sites, pricing pages, reviews — into a decision-ready product strategy report with a positioning map, feature matrix and opportunity windows.
Evidence-driven repository triage: fixes broken environments, runs safe startup syncs, diagnoses duplicate hook output, and gates risky Git operations.
Turns a list of shell commands into polished animated terminal demo GIFs using VHS recordings.
Turns audio or video into speaker-labeled, timestamped transcripts — locally with MLX/whisper.cpp on Apple Silicon or through a remote ASR endpoint.