Subtitle Editor
Fix wrong words and bad timing on a caption track next to the video itself.
What it adds
A side-by-side editor pairing the video player with an editable, time-aligned list of caption cues.
What your agent is told to do
5
What your agent is told to do
5-
1
Build this on top of the caption tracks produced by Auto Captions rather than as a standalone tool. Editing a machine track is the main reason anyone opens this screen.
-
2
Show the cue list beside the player, keep the active cue highlighted as the video plays, and make clicking a cue seek the player to its start.
-
3
Let a cue be retimed by dragging its edges on a timeline and by typing exact timecodes. Dragging is faster; typing is the only way to be precise.
-
4
Reuse the app's existing Autosave and Unsaved Changes Guard rather than inventing a save model for this screen, and make undo work across both text edits and timing changes.
-
5
Do not build a full waveform video editor. This screen edits text and cue boundaries; trimming and re-encoding the media belong somewhere else.
Edge cases it handles
8
Edge cases it handles
8- Dragging a cue boundary must never produce a cue that overlaps its neighbour or ends before it starts. Clamp the drag at the adjacent boundary rather than accepting the value and failing on save.
- Warn when a cue's reading speed exceeds a comfortable characters-per-second threshold, since a technically valid cue can still be unreadable at playback speed.
- Unsaved edits must survive a tab close or reload. Autosave a draft revision of the track so an accidental navigation does not cost an hour of correction.
- Two people editing the same caption track at once must not silently overwrite each other. Either apply the app's existing record locking or merge per cue and surface the conflict.
- Seeking the player during editing must keep the highlighted cue and the playhead in agreement, including when the user scrubs backwards or edits a cue that is currently on screen.
- Splitting and merging cues are the two operations editors reach for constantly, and both must preserve total coverage of the timeline.
- Keyboard control matters more than the mouse here: play and pause, nudge timing, and move to the next cue must all be reachable without leaving the text field.
- Publishing an edited track must supersede the machine-generated one for viewers, not add a second identical language option to the player menu.
Definition of done
9
Definition of done
9- The cue list and the player stay synchronised in both directions during playback and scrubbing.
- Cue timings cannot be dragged into an overlap or a negative duration.
- Cues exceeding the reading speed threshold are flagged in the list.
- Edits autosave as a draft and survive a reload or tab close.
- Concurrent editing of one track is either prevented or surfaced as a conflict.
- Undo covers both text and timing changes.
- A published edited track replaces the machine-generated track in the player.
- The feature matches the existing design system.
- No existing functionality is broken.
Related features
Survey Builder
Survey Builder
Build a multi-question survey, send it out, and read all the answers in one place.
What it does
An authoring tool for multi-question surveys, a respondent flow, and a results view with export.
How it works
- 1 Ship a small, honest set of question types first: single choice, multiple choice, short text, long text, and a rating scale. That covers most real surveys. Defer matrix grids, file uploads, and calculated fields rather than half-building them.
- 2 Render the respondent flow with the app's existing Multi-Step Form and Conditional Form Fields, and reuse Form Field Shell for the inputs, so a survey looks and behaves like every other form in the product.
- 3 Give surveys the app's existing Draft and Publish States. Editing a live survey while responses are arriving is the main way survey data gets corrupted, so publishing must be a deliberate act with a clear boundary.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/survey-builder
Automation Builder
Automation Builder
Let customers wire a trigger, some conditions and an action so routine work runs itself.
What it does
A visual builder where a customer connects a trigger to conditions and actions, plus the runtime that executes it and a log of what happened.
How it works
- 1 Ship a fixed, curated set of triggers, conditions and actions drawn from what the app already does. A general-purpose scripting environment is not the minimum version, and offering one you cannot support is worse than offering ten steps that work.
- 2 Run automations through the app's existing background job system. If Background Job Dashboard or Scheduled Job Monitor exists, automation runs appear there rather than in a separate queue nobody watches.
- 3 Make the run log the centre of the feature, not an afterthought. A customer whose automation did nothing needs to see which run fired, what data entered each step, and where it stopped.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/automation-builder
Quiz Builder
Quiz Builder
Build a scored quiz with branching questions and a result page that reflects the answers.
What it does
An authoring tool for multi-question quizzes with scoring rules and answer-based branching, plus the taking experience and a result page.
How it works
- 1 Reuse the app's existing form machinery for the taking experience. If Multi-Step Form and Conditional Form Fields exist, the quiz runner is those features driven by the quiz definition, not a second form engine.
- 2 Support a small set of question types that actually score: single choice, multiple choice, and short text with an exact or pattern match. Free-text grading and media questions are a separate scope and should be deferred.
- 3 Give the author a way to see the quiz as a taker would, including a specific answer path, before it is published. A branching quiz cannot be checked by reading the editor.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/quiz-builder
How it works
-
1
Copy the link
Grab the Markdown instruction URL for this feature.
-
2
Give it to your AI
Paste it into Claude Code, Cursor, v0, Lovable — whatever you build with.
-
3
It inspects, then implements
Your agent reads your existing app first, then adds the feature to fit it.
Works with your stack
These instructions are written to adapt. They tell the agent to detect your framework, match your existing design system, and reuse what you already have — rather than assuming a particular stack.
Need it tighter than that? Customize the feature and tell it exactly what you're running.