Operations assistant for reviewing issues, querying data, transforming JSON payloads, and drafting Slack-ready updates.

Interactive GitHub maintainer copilot with explicit approval gates for write actions.

Research assistant for crawling public sources, extracting structured content, and producing concise summaries.

Split markdown or text into deterministic chunks with heading context, overlap, and fallback subdivision for oversized content.

Apply deterministic transformation operations to JSON objects and arrays.

Extract structured tables from HTML or CSV sources into normalized rows and columns.

Convert local documents into normalized markdown or plain text with lightweight metadata.

Query CSV data with structured filter, sort, select, and aggregate operations.

Extract text from PDFs, either from a URL or base64-encoded PDF data.

Post or update Slack messages using a compact action surface for agent notifications.

Fetch a web page and return cleaned content, metadata, and discovered links.

Read and update GitHub issues using a compact, agent-friendly action surface.

Crawl a bounded set of pages while respecting robots.txt, depth limits, and URL filters.

Convert raw HTML into Markdown and plain text, with optional main-content extraction.

Make HTTP requests (GET/POST/etc.) and return normalized response metadata and content.

Summarize long text to a concise abstract.

Sentiment analysis using VADER.

Fetch a Wikipedia URL and return title, text, and image URLs.

Translate text into a target language using LLM.

Resize an image from a URL. Returns base64 JPEG.

Uppercases text and (optionally) summarizes, extracts keywords, and estimates sentiment.