Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

product-hunt-launch

skill · magentosh/skillsLicence not declaredAudited 31 Oct 2026 · source 4599ef28a2a7

★ 793pushed 16 days ago
!CAUTIONGrade B · 89/100 · 3 findings · 4599ef2
793repo stars · whole magentosh/skills

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 4599ef28a2a7 and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 3 findings, 0 critical or high. What it does: Product Hunt launch optimization with specific specs, timing, and gallery strategy. Covers taglines, gallery images, maker comments, and launch day tactics. Use for: product launches, startup launches, side project…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “product-hunt-launch (magentosh/skills)”. Retrieved 31 Oct 2026. https://modelsatlas.com/skills/magentosh/product-hunt-launch

7 skills are called “product-hunt-launch”. You are viewing magentosh/skills.

and 2 more with this name.

Trust audit

Audit 0.4.1 · source read 31 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high2 medium1 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS1
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesWARN2
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass, no license.

Findings (3)

MEDIUMPrivilege escalation / persistencereview.unsafe_action · SKILL.md
F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L2
belt login

# Generate gallery hero image
belt app run falai/flux-dev-lora --input '{
Why
The skill instructs the agent to run interactive authentication commands without first verifying that the CLI tool is installed or the user has consented.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts
MEDIUMPrivilege escalation / persistencereview.unsafe_action · SKILL.md
F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L2
belt app run infsh/stitch-images --input '{
  "images": ["before-state.png", "after-state.png"],
Why
The skill directs the agent to generate and stitch images using specific relative file paths that may not exist in the current working directory.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts
LOWInventory / provenanceinv.no_license
F-13 Inventory / provenanceCWE-1104Layer L0
Why
no LICENSE file and no repo licence
Fix
add a licence

Audit 0.4.1 · source sha 4599ef28a2a7 · 31 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishermagentosh GitHub organizationOwner of the repository this skill is read from
  • Source foldermagentosh/skills/guides/product/product-hunt-launchThe exact folder we audited
  • LicenceNot declaredAs the repository states it
  • Commit pinned for this verdict4599ef28a2a7A new audit runs when the source changes
  • Repository statusNot archivedLast push 16 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Product Hunt launch optimization with specific specs, timing, and gallery strategy. Covers taglines, gallery images, maker comments, and launch day tactics. Use for: product launches, startup launches, side project…

---
name: product-hunt-launch
description: "Product Hunt launch optimization with specific specs, timing, and gallery strategy. Covers taglines, gallery images, maker comments, and launch day tactics. Use for: product launches, startup launches, side project launches, Product Hunt optimization. Triggers: product hunt, ph launch, product hunt launch, launch strategy, product launch, startup launch, product hunt tips, product hunt gallery, ph optimization, launch day, product hunt maker"
allowed-tools: Bash(belt *)
---

> **Install the belt CLI skill:** `npx skills add belt-sh/cli`

# Product Hunt Launch

Optimize your Product Hunt launch with research and visuals via [inference.sh](https://inference.sh) CLI.

## Quick Start

> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)

```bash
belt login

# Generate gallery hero image
belt app run falai/flux-dev-lora --input '{
  "prompt": "clean product showcase, modern SaaS dashboard interface on laptop screen, floating UI elements around it, soft gradient background from blue to purple, professional marketing hero shot, minimal clean design",
  "width": 1248,
  "height": 832
}'

# Research competitor launches
belt app run tavily/search-assistant --input '{
  "query": "Product Hunt top launches this week SaaS tools"
}'
```


## Listing Specifications

| Element | Spec | Notes |
|---------|------|-------|
| Product name | — | Keep it short, memorable |
| Tagline | **60 character limit** | No period at end |
| Description | First **260 chars** show in preview | Full description can be longer |
| Gallery images | Up to **8 images** | 1270 x 760 px recommended |
| Topics | **Max 3** | Pick the most specific ones |
| Makers | Tag all team members | They can engage in comments |
| Link | Product URL | Where upvoters go |

## Gallery Images

### The First Image Is Everything

The first gallery image shows in the feed, email digest, and social shares. It IS your first impression.

| Position | Content | Goal |
|----------|---------|------|
| **1 (Hero)** | Product in action, core value visible | Stop the scroll, communicate what it does |
| **2** | Key feature demonstration | Show the "aha moment" |
| **3** | Before/after or problem/solution | Show the transformation |
| **4** | Social proof or metrics | Build credibility |
| **5** | Technical differentiator or integrations | For evaluators |

### Dimensions

- Recommended: **1270 x 760 px** (16:9 ish)
- Minimum: 600px wide
- Supports GIF for animated demos

### Generating Gallery Images

```bash
# Image 1: Hero product shot
belt app run falai/flux-dev-lora --input '{
  "prompt": "modern SaaS product showcase, clean dashboard interface floating above gradient background, UI showing analytics charts and metrics, professional product marketing style, soft shadows, blue and white color scheme, wide format",
  "width": 1248,
  "height": 832
}'

# Image 2: Feature demo
belt app run falai/flux-dev-lora --input '{
  "prompt": "product feature showcase, split screen showing drag-and-drop interface on left and generated output on right, clean UI design, modern SaaS aesthetic, subtle grid background, professional marketing",
  "width": 1248,
  "height": 832
}'

# Image 3: Before/after
belt app run infsh/stitch-images --input '{
  "images": ["before-state.png", "after-state.png"],
  "direction": "horizontal"
}'

# Image 4: Social proof / metrics
belt app run falai/flux-dev-lora --input '{
  "prompt": "clean infographic style image showing upward growth metrics, large numbers and charts on dark background, professional data visualization, startup metrics dashboard style, modern minimal design",
  "width": 1248,
  "height": 832
}'
```

## Tagline

60 characters. No period. Must communicate what the product does AND why someone should care.

### Formulas That Work

| Formula | Example |
|---------|---------|
| [Action] for [audience] | "AI writing assistant for developers" |
| [Result] without [pain] | "Beautiful docs without the design skills" |
| [Tool] that [benefit] | "Analytics that explain themselves" |
| [Adjective] [category] | "Instant customer feedback surveys" |
| The [category] for [niche] | "The Figma for data visualization" |

### Examples

```
❌ "The best project management tool ever created" (superlative, 52 chars)
❌ "We help you manage projects better." (vague, has period, 37 chars)
❌ "AI-powered machine learning project management SaaS" (buzzword soup)

✅ "Ship docs in minutes, not days" (31 chars)
✅ "AI turns your data into stories" (32 chars)
✅ "The open-source Calendly alternative" (37 chars)
```

## Timing

### When to Launch

| Factor | Recommendation |
|--------|----------------|
| Day | **Tuesday, Wednesday, or Thursday** (highest traffic) |
| Time | **12:01 AM PT** (Pacific Time) — start of the PH day |
| Avoid | Weekends, holidays, major Apple/Google events |
| Duration | PH day = midnight PT to midnight PT |

### Why 12:01 AM PT

- Maximum time in the running for daily top spot
- Accumulate upvotes throughout the full day
- Morning email digest (US time) includes your product
- Allows engagement across all US time zones

## Maker Comment

Post within **5 minutes** of going live. This is your pitch.

### Structure

```
Hey Product Hunt! 👋

[1 sentence: what it is]

[2-3 sentences: why you built it / the problem you noticed]

[1-2 sentences: how it works / key differentiator]

[1 sentence: what's next / what you're looking for]

Would love to hear your thoughts — happy to answer any questions!
```

### Example

```
Hey Product Hunt!

DataFlow turns raw SQL queries into visual dashboards in seconds.

As a data engineer, I was frustrated spending more time formatting
reports than actually analyzing data. Every BI tool I tried required
a PhD in their configuration. So I built DataFlow — paste your SQL,
get a dashboard.

It auto-detects chart types, handles large datasets, and exports
to PDF/PNG with o

Excerpt, first 6,001 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 4599ef2

Download folder ↗
npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@web-search
npx skills add inference-sh/skills@prompt-engineering

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 4599ef28a2a7 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source 4599ef28a2a7

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/magentosh/product-hunt-launch/badge.svg)](https://modelsatlas.com/skills/magentosh/product-hunt-launch/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/magentosh/product-hunt-launch/badge.svg)](https://modelsatlas.com/skills/magentosh/product-hunt-launch/)

Questions about product-hunt-launch

What does the product-hunt-launch skill do?
inference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agents
Is product-hunt-launch safe to install?
With care. The audit graded it B (89/100) and found 3 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can product-hunt-launch access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (4599ef28a2a7), read on 2026-10-31. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.