Compile image, audio, and video generation into a complete deterministic ComfyUI batch that can execute without any LLM involvement after handoff.
Scanned 9/9/2026
Install to Claude Code
Skills Directorynpx -y skills add badgids/Story-Film-Skills --skill comfyui-offline-batch --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Comfyui Offline Batch?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/badgids-comfyui-offline-batch)More formats (shields.io, HTML) on the badges page.
---
name: comfyui-offline-batch
description: Compile image, audio, and video generation into a complete deterministic ComfyUI batch that can execute without any LLM involvement after handoff.
author: Alan Guice (Badgids)
license: Apache-2.0
---
# ComfyUI Offline Batch
Read `../../references/COMFYUI_OFFLINE_BATCH.md` and `comfyui`.
Before handing memory from a local LLM to ComfyUI, ensure the batch contains everything the runner needs:
- final API-format workflow JSON for every job
- stable source IDs and job IDs
- all final prompt/text values
- all seeds, sizes, durations, frame/audio parameters, model selections, and workflow inputs
- exact project input files plus deterministic upload/patch mappings
- job dependency edges
- output directories and expected output kinds
- timeout/retry policy that never changes creative inputs
- already-approved paid-route consent where applicable
Run live schema/model validation before arming the resource handoff. Missing nodes/models or unresolved placeholders are blockers while the LLM is still available.
The offline runner may retry the identical job for transient transport/server failures. It must stop and return control to the LLM for any semantic change, prompt rewrite, model substitution, missing creative decision, or continuity repair.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling
