ComfyUI-AudioLoopHelper

Canonical first-pass when a ComfyUI-AudioLoopHelper workflow won't run or fails validation. Use when the user mentions "workflow won't run", "dependency cycle detected", "validation failed", "Failed to convert ... to INT", "control_after_generate", or describes a recent ComfyUI render that didn't get past prompt validation, or reports a loop/full-song render that is pathologically slow or re-encodes (text-encode / audio / keyframe) every iteration. Runs the canonical diagnosis (ComfyUI log tail, audit, DAG inspection, exec log review, launch-flag check for --cache-none) BEFORE any inline orjson scripting. Reference: docs/reference/debug_tools.md.

Structural diff of two ComfyUI workflow JSON files — node types, widget values, link topology, subgraph schemas — with noise filtered out (link IDs, node positions, ordering). Use when debugging "why does workflow A behave differently than B" or verifying a migration script produced the intended shape change.

Generate an LTX 2.3 prompt that makes a character speak SPECIFIC dialogue, formatted per the official LTX 2.3 prompt guide (short quoted segments with acting directions between, accent, acoustic environment). Use when the user wants to put words in a character's mouth for the AV inversion / one-pass / keyframe workflows (voice-cloned dubbing, dialogue replacement).

Scaffold a new scripts/apply_*.py workflow migration script from scripts/templates/, enforcing the project's idempotence + paired-audit-check convention. Use when adding a new fix that mutates example_workflows/*.json or stages an experimental variant.

Dispatch three parallel Explore agents to validate a structural refactor BEFORE writing changes. Use when the user proposes restructuring multiple CLAUDE.md / docs / agent / skill files (signal: ≥ 3 files, ≥ 2 different concerns), or when planning a curation pass on documentation. Cost ~30s of agent time; turns vague "compress this" into a concrete edit list and prevents premature subtree splits.

Analyze audio file for music video prompt scheduling. Picks the right analyzer (ffmpeg-only for quick energy/structure, librosa for BPM/key/F0/JSON-export-for-LLM), and outputs a prompt schedule template with timestamps. Also works on generated audio for diagnostic comparison.

Run the AudioLoopHelper test suite with correct uv groups, rootdir, and ComfyUI loader verification

Generate TimestampPromptSchedule variations from audio analysis and init_image. Follows i2v rules (present-progressive, describe changes only, singing together for multi-person, no dolly out). Outputs 3 variations (framing-only, energy-matched, lighting shifts).

Draft the next CHANGELOG.md section from commits since the last release. Reads current version from pyproject.toml and the most recent version header in CHANGELOG.md, then formats the delta in the repo's existing style (semver only, no dates, no major bumps without explicit permission). Prints the draft for user review. Does NOT write.

Aggregate the most recent sage trace (and optional matching exec log) into a per-prompt + attribution + gate-verdict report. Use after a ComfyUI generation when you want to know "where did time actually go" and "is mask kernel work justified."

Edit ComfyUI workflow JSON using WorkflowEditor utility. Use when modifying nodes, links, widget values, or subgraph internals in workflow files.