Release workflow for Untether — issue audit, version decisions, changelog drafting, pre-release validation, tagging, and post-release verification. Use when preparing a release or debugging release failures.
Raw Telegram Bot API patterns used by Untether. Covers httpx async HTTP client, inline keyboards, callback queries, long polling, rate limiting, outbox model, forum topics, voice transcription, and media group coalescing. NOT aiogram, python-telegram-bot, or grammY — Untether uses raw HTTP.
Untether overall architecture, event model, data flow, config system, engine backend registration, progress tracking, approval notifications, ephemeral cleanup, and key abstractions. Use when working on core infrastructure or understanding how the pieces fit together.
Prepare and ship a Untether release. Use when asked to cut a release, bump release versions, update changelog/spec/readme, tag v , or trigger the GitHub release workflow.
Telegram bridge for AI coding agents (Claude Code, Codex, OpenCode, Pi, Gemini CLI, Amp). Lets users control agents from their phone or any device — agents run on the user's machine while they're away from the terminal.
Claude Code instructions for littlebearapps/outlook-assistant, covering claude.md - outlook assistant, commands, authentication, architecture and safety controls.
Microsoft Outlook MCP server — 22 tools for email, calendar, contacts, and mailbox management. Runs locally from the @littlebearapps/outlook-assistant npm package. Needs 2 environment variables to run.
Generate high-quality public-facing repository documentation with a marketing edge. Creates READMEs that sell, changelogs that communicate value, roadmaps from GitHub milestones, and audits your docs completeness. Uses benefit-driven language, GEO-optimised structure, progressive disclosure, and the Banesullivan…
Checks documentation freshness and suggests PitchDocs commands to fix staleness. Launch when docs-awareness rule detects documentation moments, after version bumps, or before releases. Does NOT modify docs — only reports and suggests.
Codebase discovery and feature extraction for documentation generation. Scans project structure, extracts features with evidence, detects platform and audience, and produces a structured research packet for the docs-writer agent.
Orchestrates high-quality public-facing repository documentation generation. Coordinates docs-researcher (codebase discovery, feature extraction) and docs-reviewer (quality validation) agents in a pipeline, with the writing step in between. Use for README, CHANGELOG, ROADMAP, CONTRIBUTING, and full docs suite…
Guidance for setting up API reference documentation generators — TypeDoc, Sphinx, godoc, and rustdoc. Detects project language, recommends the right tool, and provides configuration templates. Use when a project needs automated API documentation from source code comments.
Generates user-friendly changelogs from git history using conventional commits. Writes entries in benefit language ("You can now..." not "Refactored internal..."). Follows Keep a Changelog format. Use when creating or updating CHANGELOG.md.
Orchestrates documentation updates after version bumps, feature additions, or periodic maintenance. Analyses git history since the last release, identifies which docs are affected, and delegates to existing skills (changelog, feature-benefits, docs-verify, llms-txt, user-guides) for selective refresh. Delegates AI…
Validates documentation quality and freshness — checks for broken links, stale content, llms.txt sync, image issues, heading hierarchy, and badge URLs. Runs locally or in CI. Use to catch documentation decay before it reaches users.