iart-ai/freelance-motion-skills / skills/client-revisions
client-revisions
VerifiedThis skill should be used when the user asks to "stop scope creep", "limit revision rounds", "write SOW revision language", "the client keeps asking for changes", "how do I say this is out of scope", "translate vague feedback", "client said make it pop", or "write a change-order email". It provides revision-cap contract language, a consolidated-feedback request, a vague-feedback translator, and a polite out-of-scope email.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 0 B |
| SKILL.md | skill md | 11.2 KB |
| references/email-templates.md | markdown | 2.6 KB |
| references/feedback-translator.md | markdown | 2.7 KB |
| references/sow-clauses.md | markdown | 2.6 KB |
references/feedback-translator.md
View on GitHub# Feedback Translator (expanded)
Never touch the project file on a vague note. Convert it to a decidable choice and ask for a timestamp.
## Lookup table
| Client says | Likely axes | Ask back |
|---|---|---|
| "Make it pop" | colour / pace / scale / sound | "Saturation, faster cuts, bigger scale, or louder sound? Point me to a second that already pops." |
| "It feels off" | pace / colour / type / message | "Off in pacing, colour, type, or message — and which 2 seconds feel worst?" |
| "More premium" | easing / space / palette / type | "Slower easing, more breathing room, restrained palette, or refined type?" |
| "More dynamic" | camera / cuts / motion density | "More camera movement, faster cuts, or more elements moving?" |
| "I don't love it" | unknown — needs anchor | "What specifically? And a reference for what 'loving it' looks like?" |
| "Punch it up" | pace / colour / sound | "Pacing, colour, or sound? Show me a moment with the energy you want." |
| "Make it bigger" | scale / weight / contrast / time | "Bigger scale, bolder type, more contrast, or more screen time?" |
| "Something's missing" | scene / message / brand / energy | "A scene, a message, a brand element, or energy — and where?" |
| "Too busy" | element count / pace / colour | "Fewer elements at once, slower pace, or simpler palette?" |
| "Cheap-looking" | type / spacing / easing / colour | "Usually type choice, spacing, easing, or colour — which feels cheapest to you?" |
| "Not on brand" | colour / type / logo / tone | "Which — colour, type, logo usage, or overall tone?" |
| "Make it flow better" | transitions / pacing / continuity | "Smoother transitions, steadier pace, or stronger scene-to-scene continuity?" |
## The "problem, not fix" coaching note for clients
Share this once, early, to raise feedback quality:
> The most useful feedback names the problem, not the solution. "The
> intro drags" lets me fix it the right way; "make the intro faster"
> locks me into one fix that might not be the real issue. Tell me what
> feels wrong and where (a timestamp), and leave the how to me — you'll
> get a better result in fewer rounds.
## Three questions that decode almost any vague note
1. **Where?** — "Which timestamp or scene?"
2. **Which axis?** — colour, pace, type, scale, sound, or message?
3. **Compared to what?** — "Point to a reference, or a second in this video that already feels right."
---
Translate vague feedback into targeted changes and revision rounds stay bounded. Built by **[iart.ai](https://iart.ai/?utm_source=github&utm_medium=readme&utm_campaign=freelance-motion-skills&utm_content=skill_footer&utm_term=client-revisions)** — the AI motion agent for editable, on-brand motion graphics.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |