product-hunt-polish-review
Skill11 starsChanged 3 months agoMITView on GitHub
Use when reviewing an app for launch-readiness — Product Hunt polish, first impression, visual hierarchy, onboarding, empty states, screenshots, positioning, and the tiny details that make it feel premium.
In this repository39 other files it gives its agents.
- agent-starter-packSkill
- agent-state-machineSkill
- local-ai-ollamaSkill
- apple-hig-command-paletteSkill
- apple-hig-empty-statesSkill
- apple-hig-feedback-statusSkill
- apple-hig-inspectorsSkill
- apple-hig-macos-window-layoutSkill
- apple-hig-search-filteringSkill
- apple-hig-settingsSkill
- apple-hig-sf-symbolsSkill
- apple-hig-sidebarsSkill
- apple-hig-toolbarsSkill
- apple-hig-typographySkill
- blog-post-publishingSkill
- social-post-kitSkill
- color-principlesSkill
- kika-design-systemSkill
- emergency-switch-appSkill
- docs-updateSkill
- project-folder-cleanupSkill
- between-runs-auditSkill
- explain-new-projectSkill
- new-project-gateSkill
- old-project-auditSkill
- project-catch-upSkill
- project-workflowSkill
- project-worth-my-timeSkill
- butterfly-effectSkill
- spreadSkill
- tilSkill
- apple-app-intentsSkill
- macos-app-distribution-dmgSkill
- macos-clipboard-pasteboardSkill
- macos-global-shortcutsSkill
- macos-launch-at-loginSkill
- macos-menubar-swiftuiSkill
- macos-notificationsSkill
- macos-permissions-privacySkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use this skill when reviewing an app for launch-readiness, Product Hunt polish, first impression, visual quality, onboarding, screenshots, …
- Distinctive: line 22
Use when the user says:
- Distinctive: line 37
Do not use this skill for:
- Distinctive: line 132
Avoid empty dashboards unless it is an intentional first-run screen.
- Distinctive: line 134
Add captions only if needed.
- Distinctive: line 135
Keep screenshots visually consistent.
- Distinctive: line 139
Every empty state should sell the product gently.
- Distinctive: line 166
Avoid hype inside functional UI.
- Distinctive: line 167
Use verbs for actions.
- Distinctive: line 168
Avoid “magic” when explaining critical behavior.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Product Hunt Polish Review
Review an app for launch-readiness so it feels useful, clear, trustworthy, and polished in the first 30 seconds. Be direct and critical, prioritize clarity over decoration, and end with a concrete pre-launch checklist.
When to use
Use this skill when reviewing an app for launch-readiness, Product Hunt polish, first impression, visual quality, onboarding, screenshots, positioning, and tiny details that make the app feel premium.
Core rule
A launch-ready app must feel useful, clear, trustworthy, and polished in the first 30 seconds.When to use this skill
Use when the user says:
- Product Hunt worthy
- launch polish
- make it premium
- make it viral
- first impression
- final polish
- pixel perfect
- app store ready
- landing page polish
- screenshot review
When not to use this skill
Do not use this skill for:
- Deep architecture refactor
- Backend implementation
- Generic HIG review only
- Unfinished prototypes where core functionality does not work yet
Review dimensions
1. First impression
2. Core value clarity
3. Visual hierarchy
4. Onboarding
5. Empty states
6. Feedback/status
7. Performance feel
8. Trust/privacy
9. Screenshots
10. Launch copy30-second test
A new user should understand:
What is this?
Why do I need it?
What should I click first?
What happens after I click?
Can I trust it?If not, simplify.
First screen checklist
[ ] App name is clear
[ ] One-sentence value proposition exists
[ ] Primary action is obvious
[ ] No dense dashboard on first launch
[ ] Empty state helps user start
[ ] Visual style feels intentional
[ ] No broken or placeholder content
[ ] No confusing technical jargon for non-technical usersPremium UI checklist
[ ] Consistent spacing
[ ] Consistent typography
[ ] Consistent SF Symbols
[ ] Calm color system
[ ] Main content has breathing room
[ ] Few competing elements
[ ] Clear selected states
[ ] Clear hover/focus states
[ ] Loading/error/success states exist
[ ] Dark and light mode are both checkedProduct Hunt positioning
Good format:
[Product] helps [user] do [job] without [pain].Examples:
HubApp helps vibe coders run agent projects from one calm Mac workspace without losing track of tasks, skills, and active runs.
SkillPilot helps builders choose the right skills for each task without digging through folders.Screenshot checklist
For launch screenshots:
1. Hero screen showing main value
2. Command palette / fast workflow
3. Active run / status tracking
4. Skills/project organization
5. Settings/local AI/privacyRules:
- Use real-looking content.
- Avoid empty dashboards unless it is an intentional first-run screen.
- Show one clear story per screenshot.
- Add captions only if needed.
- Keep screenshots visually consistent.
Empty state polish
Every empty state should sell the product gently.
Example:
No Active Runs
The agent is not working on anything right now.
Start a task, open the queue, or run a saved skill.Trust and privacy checklist
Especially for AI/local apps:
[ ] Explain what stays local
[ ] Explain when cloud is used
[ ] Do not silently send private prompts to cloud
[ ] Show model/provider status
[ ] Show folder permissions clearly
[ ] Store secrets securely
[ ] Add export/delete data options if relevantMicrocopy rules
- Be direct.
- Avoid hype inside functional UI.
- Use verbs for actions.
- Avoid “magic” when explaining critical behavior.
- Make errors helpful.
- Make buttons specific.
Good buttons:
New Task
Run Skill
Open Queue
Generate Report
Connect OllamaBad buttons:
Go
Submit
Do Magic
ProceedLaunch readiness score
Rate each 1–5:
Clarity
Visual polish
Speed feel
Onboarding
Empty states
Error states
Trust/privacy
Screenshot quality
Positioning
Retention hookLaunch only when the average is 4+ and no category is below 3.
Common mistakes
Beautiful UI but unclear value
Too many features on first screen
No onboarding
No empty states
Fake progress
Placeholder content in screenshots
No trust/privacy explanation
Inconsistent icons/spacing
Product Hunt copy too vaguePrompt template
Drop this into any coding agent (Claude Code, Codex, Cursor, …) to apply the skill:
Use the product-hunt-polish-review skill to review this app for launch polish.
Goal:
Make the app feel premium, clear, useful, and launch-ready in the first 30 seconds.
Review:
- First impression
- Value proposition
- Primary action
- Visual hierarchy
- Empty states
- Feedback/status
- Onboarding
- Trust/privacy
- Screenshot readiness
- Microcopy
Rules:
- Be direct and critical.
- Identify what feels unfinished.
- Suggest concrete UI/content fixes.
- Do not add more features unless they improve first-time value.
- Prioritize clarity over decoration.
Output:
1. Launch readiness score / 10
2. Top 5 issues
3. Top 5 fixes
4. Screenshot plan
5. Product Hunt tagline options
6. Final pre-launch checklistDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

