ai

Review the uncommitted working tree. By default spawns codex /review and claude /code-review in two visible herdr tabs; with --codex-only, spawns only codex. Merges and de-duplicates findings in the main session, applies every fix except the net-negative ones via a fix tab (codex by default, claude via --fix-agent, or an existing tab via --fix-term) that then runs the project's tests and type-check — leaving all changes uncommitted. Use when invoked as /iso-review [--codex-only] [--claude-review-effort high|max] [--fix-agent codex|claude] [--fix-term TERM] [--kill-tabs], or asked to review-and-fix the current uncommitted changes.

Research-first prep for a new Italian YouTube video: derive topic(s), run Codex-agent deep research by default with source-credibility tiering and adversarial fact-verification (verified vs contested claims), offer 6 grounded Italian titles, create a NotebookLM notebook, and add reports plus only trustworthy (T1–T3) sources. Use when invoked as /social-new-notebooklm-project <topic | youtube-url...> [--bounded] [extra-source ...], or when asked to spin up a NotebookLM research notebook for a video. --bounded opts down to a smaller research pass. Does not generate NotebookLM artifacts.

One-shot launcher for a new Italian YouTube video. Spawns a single codex|claude tab (via iso-spawn) that runs the full chain inside itself — social-new-notebooklm-project (research → you pick the title) then social-notebooklm-artifacts (scaletta + 4 infographics). Fire-and-focus: async spawn with --focus, no kill; you own the tab. Use when invoked as /social-new-video <topic | youtube-url...> [--agent codex|claude] [--bounded] [--script-only | --images-only] [extra-source ...], or asked to spin up a whole new video (notebook + assets) in one go. Default agent codex. Pairs with social-new-notebooklm-project and social-notebooklm-artifacts (which it chains). Requires the iso-spawn skill + a herdr workspace.

Turn an existing NotebookLM notebook into video assets — a bulleted SCALETTA (focal-point talking points, NOT a verbatim script) AND a 2×2 matrix of 4 Italian infographics (simple+detailed × landscape+portrait). Content comes ENTIRELY from the notebook's sources (scaletta via notebooklm ask; image concepts derived from the notebook too) — you pass nothing, no persona. No citation numbers. By default produces long+short scaletta AND 4 PNGs, in Italian, under a chronological folder <YYYY-MM-DD> - <notebook-title>/ inside a base dir (default /Volumes/Crucial-4T/social, override with --out). Use when invoked as /social-notebooklm-artifacts [<notebook>] [--long | --short] [--script-only | --images-only] [--out <dir>], or asked to turn a NotebookLM project into a video script/scaletta and/or infographics. Agent-independent (Claude Code or Codex). Pairs with social-new-notebooklm-project (which builds the notebook).

Initialize AI defaults. Global steps run anywhere — install/verify caveman (ultra + shrink + statusline) and shrink any allowlisted MCP server that is present and stdio-launchable. Repo-scoped steps (graphify CLI install + /graphify wiring) run only inside a git repo. A gate decides which steps apply. Use when the user runs /iso-ai-init or asks to set up AI tooling.

Run a full development cycle — plan, then implement, then review — as one hands-off chain. Invoked as /iso-todo [--codex-only] [seed]. The parent session plans with iso-plan, spawns a codex implementation tab to run iso-write on a fresh feat/<slug> branch, keeps that tab alive, runs iso-review over the resulting uncommitted diff with reviewer tabs killed after recovery, and reuses the implementation tab for accepted fixes. With --codex-only, review skips Claude. Commits nothing. Use when the user runs /iso-todo, or asks to take an idea all the way from plan to implemented-and-reviewed without committing.

Spawn a codex or claude agent in its own herdr tab inside the SAME workspace where the skill runs, with full permissions and an optional auto-running prompt. Use when the user wants to spawn/open/launch a codex or claude tab/agent/panel in the current herdr workspace, dispatch a task to a sub-agent beside the current session, or says "spawn codex", "open a claude tab", "/iso-spawn", "launch an agent here".

Implement a written plan using TDD, without committing. Use when invoked as /iso-write <plan_path> [--no-branch | --branch=<name> | --worktree] or handed an implementation plan to build. Default creates a fresh branch from the plan filename; --no-branch implements on the current branch; --branch=<name> uses a named branch; --worktree runs in an isolated worktree. Delegates execution to superpowers executing-plans (red-green-refactor per task), stamps the plan done, and stops so the user reviews all changes before any commit. Agent-independent (Claude Code or Codex).

Set up a repo with IsaiaScope governance defaults — GitHub repo creation, prod/test/dev branch structure with protection, prod-gate CI, commitlint, version-bump hook, and /deploy-cascade command. Use when the user runs /iso-init-repo or asks to set up repo governance.

Planning-only chain. Runs brainstorming → grill-with-docs → (prototype, only when needed) → writing-plans in order, then renders a visual summary of the finished plan file. No state, no implementation. Use when the user runs /iso-plan, optionally with a seed idea as the argument.

Write or refine README files in the IsaiaScope house style — curated shieldcn (shadcn-styled) badges, context-aware layout (repo root/app · skill · lib/pkg), scannable prose — then commit only the README changes and push. Global, stack-agnostic (node, python, rust, go, docs-only, monorepo). Use when invoked as /iso-readme [path], or asked to write/refine/beautify a README in my style.