docs: improve AI agent discoverability of text, audio, and polish features#17
Merged
Merged
Conversation
…tures The capabilities command now guides agents through all four phases of professional editing (analyze, edit, audio polish, visual polish) instead of a flat step list that agents often stopped reading after trimming. Adds operation categories, a quality checklist, recipe examples for common patterns, and restructures the agent workflow into named phases. Co-authored-by: Cursor <cursoragent@cursor.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Restructures the
cutagent capabilitiesoutput and README to help AI agents discover and use all available features — especially audio polish (normalize, mix_audio), visual polish (text, animate, fade), and transitions — instead of stopping after basic trim/cut/concat.Why
AI agents using CutAgent tend to only discover and use trim/cut/concat operations, producing amateur-looking results. They miss text overlays, audio normalization, background music mixing, and transitions because these features are buried in a flat list that agents stop reading early. Professional video editing requires all four phases (analyze, edit, audio polish, visual polish), not just cutting.
How
cutagent capabilitiesoutput (cli.py):overviewtext at the top explicitly stating all four phases are neededoperation_categoriesgrouping operations into analysis, editing, audio_polish, and visual_polishquality_checklistwith 5 direct questions agents should ask before finishing (e.g., "Audio normalized?", "Titles added?")agent_workflowfrom a flat 12-step list to a 4-phase structure where audio and visual polish are clearly labeled as essential, not optionalrecipeswith 3 common patterns (interview cleanup, highlight reel, tutorial polish) that naturally combine text, audio, and transition operationsREADME.md:
cutagent capabilitiesthe explicit starting point for AI agentstextandanimateto the "Available operations" list in the EDL sectionChecklist
pytest) — 264 passedMade with Cursor