For AI agents#
correspond ships artifacts for coding agents alongside its code. This page lists
them, says where each lives in the repository, and points at the
machine-readable copies of this documentation.
Skills#
Skills are folders holding a SKILL.md (the Agent Skills format): a description that tells an agent when to use it and a body with the procedure. Install one into your agent with gh skill (any host: --agent claude-code, copilot, cursor, codex, gemini), or use the copy bundled in the wheel.
correspond#
Read, listen to and send messages on the operator’s channels through one CLI, correspond - GitHub issues, pull requests and discussions; email; ntfy and macOS notifications; a Telegram bot; a web feedback inbox - and do it safely. Use when asked to read a GitHub issue or discussion thread, check a channel or an inbox for anything new, notify the operator, post a comment or a reply, react to a message, find out whether a channel can do something, what a channel needs before it works, or who really sent a message and how sure that is. Also strips quoted replies, forwards, signatures and disclaimers from email bodies to get what the sender actually wrote. Triggers on “read issue”, “what did they actually write”, “strip the quoted reply”, “what’s new on”, “check the inbox”, “send me a notification”, “ping me when”, “post a comment”, “reply on the thread”, “react to”, “can telegram do”, “set up correspond”, “is this sender verified”. Every write is dry-run first and shown to the operator.
gh skill install thorwhalen/correspond correspond --agent claude-code
Source: correspond/data/skills/correspond (bundled with the pip package).
The bundled skills are also on disk after pip install correspond, under the package’s data/skills/ directory; link them into an agent without network access with skill link-skills <that directory>.
Instruction files#
Files agents read before working in this repository.
.claude/CLAUDE.md: read by Claude Code
Machine-readable documentation#
This site publishes the same documentation in forms that fit an agent’s context window:
llms.txt: an index of every page with a one-line description (llms.txt format)correspond.md: the whole documentation as one Markdown file<page>.html.md: a rendered Markdown twin of every page, advertised from each page’s<head>with<link rel="alternate" type="text/markdown">objects.inv: the Sphinx inventory: a symbol-to-URL index (sphobjinv convert plain objects.inv -)