davidondrej

Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run every N minutes", "schedule a task", "run on a loop", "heartbeat". Covers external clocks (Claude Code, Codex, Pi) vs Hermes' built-in…

Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run…

Control the cmux macOS terminal app (CLI + socket API) — cmux workspaces, panes, surfaces, browser automation, notifications, settings, hooks. MUST be read before running any `cmux` command. Trigger ONLY when the user explicitly says "cmux" — a cmux pane,…

Launch new CLI coding agents through Corral Design 1, or correctly reopen existing agent sessions inside a Corral-active Herdr repository. Use when David asks to launch, spawn, batch-start, reopen, relaunch, or resume agents. New launches create Corral-owned…

Launch a Fable 5 Max 1M reviewer as a bb thread (default: /bb-subagents) to do a deep, neutral senior-developer review of the current work and report its findings back verbatim. Use when the user says "/fable-review", "fable review", or asks for Fable to…

Launch a GPT 5.6 Sol Max reviewer as a bb thread (default: /bb-subagents) to do a deep, neutral senior-developer review of the current work and report its findings back verbatim. Use when the user says "/gpt-review", "gpt review", or asks for GPT to review…

Operate and coordinate AI agents running inside Herdr in Ghostty. Use when the user says "Use the Herdr skill," mentions Herdr, or asks to inspect, message, wait for, or coordinate agents in a Herdr workspace. Herdr-specific; do not use for cmux or ordinary…

Score any AI model on the DeepSWE coding-agent benchmark via the OpenRouter API. Use when the user wants an independent, reproducible coding-agent eval — "run DeepSWE", "benchmark this model on DeepSWE", "score model X on the coding benchmark", "test a model…

Use before deploying Monorepo on a VPS or creating global agent links.

Use before committing, reviewing, or summarizing local changes in a shared repository.

Use before editing when a directory may have local AGENTS.md, CLAUDE.md, or adapter instructions.

Use when you need to understand repository structure, ownership boundaries, or where to make a change.

Use when making code or documentation changes in a workspace with multiple human or agent contributors.

Use when deciding how to validate a change with the smallest reliable local test or check.

Help David publish @davidondrej/autogit to npm as fast as possible. Use when David wants to publish/release to npm, hits a publish error (E404, EOTP, auth), or needs to re-auth npm. Contains David-specific context and known failures. Update this skill after…