crabin

Use when bootstrapping a new personal wiki for any knowledge domain — research, codebase documentation, reading notes, competitive analysis, or any long-term knowledge accumulation project.

Use when adding a new source to a wiki — a paper, article, URL, file, transcript, or any document. One ingest may touch 5-15 wiki pages.

Use when auditing a wiki for health issues — contradictions between pages, orphan pages, broken cross-references, stale claims, missing pages, or coverage gaps. Run after every 5-10 ingests.

Use when asking a question against a personal wiki built with wiki-init and wiki-ingest. Do not answer from general knowledge — always read the wiki pages first.

Use when revising existing wiki pages because knowledge has changed, a new piece of information updates or contradicts existing content, or the user wants to directly edit wiki content with LLM assistance.

Browser automation via the agent-browser CLI. Use when you need to browse the web for research or fact-checking, extract real-time information from URLs, verify claims against live web pages, scrape structured content from websites, or interact with web apps. Triggered by tasks like searching the web, checking live sources, fetching content from a URL, browsing and summarizing, or looking up current information online.

Academic text polisher and humanizer for Chinese and English research writing. Removes AI-like patterns while preserving factual accuracy. Use when polishing academic text, reducing AI-generated patterns in papers/theses, improving naturalness of research writing while maintaining data integrity, or enhancing scholarly tone without fabricating facts. Supports both Chinese (中文) and English academic texts with configurable tone, field-specific terminology, and strict factuality controls.

Analyze research codebases and academic research workflows. Use when a user wants to automate executable research experiments in a local repository, especially ML/GAN/classifier pipelines, or when they explicitly ask for research-autopilot to handle academic research tasks such as deep research, literature review, systematic review, PRISMA/meta-analysis, fact-checking, research-question design, academic paper writing/revision/formatting/citation checks, manuscript review, peer-review simulation, or an end-to-end research-to-publication pipeline.