0xtaoist

Research best practices via MCP Ref/Context7/WebSearch and create documentation (guide/manual/ADR/research). Single research, multiple output types.

Commit and push ALL changes (staged + unstaged + untracked) to the remote repository

Sync skills (symlinks) and MCP settings from Claude to Gemini CLI and Codex CLI

Probes CLI agents (Codex, Gemini) and writes docs/environment_state.json — agent availability config for Phase 0

Top orchestrator for complete doc system. Delegates to ln-110 coordinator (project docs) + ln-120-150 workers. Phase 3: global cleanup. Idempotent.

Meta-orchestrator: reads kanban board, lets user pick ONE Story, drives it through pipeline 300->310->400->500 via TeamCreate. Creates worktree isolation; coordinates workers + reports.

Coordinates project documentation creation. Gathers context once, detects project type, delegates to specialized workers (ln-111-115).

Creates 4 core project docs (requirements.md, architecture.md, tech_stack.md, patterns_catalog.md). ALWAYS created.

Render video content from React components using Remotion for The Forge puzzle replays and bout highlights.

Auto-configure Bankr Router + Forge SDK to compete in The Forge arena with cost-optimized LLM inference.

Seedance 2.0 video-generation prompting intelligence. Write, optimize, review, and split prompts for ByteDance Seedance 2.0 (quad-modal text+image+video+audio, 1080p, ~15s/clip). Use when crafting AI video prompts, building multi-shot or long-form sequences (e.g. 45s = 3x15s), enforcing character/scene consistency across clips, applying timeline prompting, choosing camera moves and lighting, using numbered @Image1/@Image2/@Video1/@Audio1 references (OpenArt), or splitting a script into a multi-prompt under a per-clip character budget (e.g. 2000 chars/clip). Topics: shot type, camera movement, lighting, color temperature, film-stock aesthetic, native audio, VFX brackets, character drift, prompt formula.