My AI Agents Home
This repository also configures its own agents. See what dotai tells them →
Skill Claude CodeCodex
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Skill Claude CodeCodex
Run Gemini CLI headlessly or resume a prior CLI session. Use for requested Gemini prompts, model choices, or session lookup.
Skill Claude CodeCodex
Select and apply workflow skills when the user asks how to use this skill collection or an active workflow needs routing.
Skill Claude CodeCodex
Check completion claims against current evidence when asked to audit verification or when an active workflow requires this gate.
Skill Claude CodeCodex
Verify a claim with fresh local evidence. restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE. Use this skill when the user asks to verify a claim or say verify this, prove it works, or did this fix it.
Skill Claude CodeCodex
Fetch web pages and convert them to clean Markdown using markdown.new. Use when user wants to fetch a URL as markdown, convert HTML to markdown, or extract clean text from websites.
Skill Claude CodeCodex
Write an implementation plan from an established design when a plan or engineering handoff is requested.
Skill Codex
Coordinate a long-lived software product through delegated agents, persistent initiatives, worktrees, pull requests, reviews, releases, and learned context. Use when one coordinator should remain responsive while workers execute substantial multi-PR or multi-repository work. Do not use for a one-off task that should…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: