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

Agent skill · Audited from source

viral-hook-creator

skill · ognjengt/founder-skillsMIT licenceAudited 31 Oct 2026 · source 90bc6f1424df

★ 652pushed 165 days ago
✓SAFEGrade B · 89/100 · 31 Oct 2026 · 90bc6f1
652repo stars · whole ognjengt/founder-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 90bc6f1424df and found no filesystem, network or shell access and no hard-coded secrets. What it does: Creates viral social media hooks using proven psychological patterns and trigger words. Use when user needs attention-grabbing openings for posts, threads, videos, or content.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “viral-hook-creator (ognjengt/founder-skills)”. Retrieved 31 Oct 2026. https://modelsatlas.com/skills/ognjengt/viral-hook-creator

Trust audit

Audit 0.4.1 · source read 31 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium2 low0 info

SAFE means nothing in the source contradicts what the skill says it does. 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, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS2
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (2)

LOWObfuscation / stealthreview.concealment · references/hook-patterns.md
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L2
"Coca Cola used this marketing strategy to secretly dopamine spike their users."
Why
The package instructs the agent to embed secret, hidden manipulation tactics into social content.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts
LOWPrompt injectionreview.misleading_scope · references/hook-patterns.md
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
"I cracked the marketing code Fortune 500 companies are gatekeeping."
Why
It encourages the agent to make unverifiable, false corporate claims to artificially boost engagement.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts

Audit 0.4.1 · source sha 90bc6f1424df · 31 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherognjengt GitHub userOwner of the repository this skill is read from
  • Source folderognjengt/founder-skills/skills/viral-hook-creatorThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict90bc6f1424dfA new audit runs when the source changes
  • Repository statusNot archivedLast push 165 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Creates viral social media hooks using proven psychological patterns and trigger words. Use when user needs attention-grabbing openings for posts, threads, videos, or content.

---
name: viral-hook-creator
description: Creates viral social media hooks using proven psychological patterns and trigger words. Use when user needs attention-grabbing openings for posts, threads, videos, or content.
---

# Viral Hook Creator

## Purpose
Generate 3-5 viral hook options using proven psychological patterns that create curiosity, provide value, and drive engagement. Hooks are optimized for social platforms (X/Twitter, LinkedIn, Instagram, TikTok).

---

## Execution Logic

**Check $ARGUMENTS first to determine execution mode:**

### If $ARGUMENTS is empty or not provided:
Respond with:
"viral-hook-creator loaded, proceed with additional instructions"

Then wait for the user to provide their requirements in the next message.

### If $ARGUMENTS contains content:
Proceed immediately to Task Execution (skip the "loaded" message).

---

## Task Execution

When user requirements are available (either from initial $ARGUMENTS or follow-up message):

### 1. MANDATORY: Read Reference Files FIRST
**BLOCKING REQUIREMENT - DO NOT SKIP THIS STEP**

Before doing ANYTHING else, you MUST use the Read tool to read BOTH reference files. This is non-negotiable:

```
Read: ./references/hook-patterns.md
Read: ./references/trigger_words.md
```

**What you will find:**
- **hook-patterns.md**: 18 proven hook patterns with templates, psychology explanations, and the Pattern Selection Matrix
- **trigger_words.md**: Four categories of viral trigger words (Insider, Helper, Thinker, Amplifiers)

**DO NOT PROCEED** to step 2 until you have read both files and have the patterns and trigger words loaded in context.

### 2. Check for Business Context (Optional)
Check if `FOUNDER_CONTEXT.md` exists in the project root.
- **If it exists:** Read it and use the business context to personalize your output (industry terminology, audience pain points, brand voice, authority metrics).
- **If it doesn't exist:** Proceed using defaults from the "Defaults & Assumptions" section.

### 3. Analyze Input
From the user's requirements, extract:
- Content topic/theme
- Target platform (X, LinkedIn, Instagram, TikTok, general)
- Goal (awareness, education, engagement, conversion)
- Target audience demographics and psychographics
- Available social proof (stats, achievements, research)

For any missing information, apply defaults from the **"Defaults & Assumptions"** section.

### 4. Generate Viral Hooks
Using the patterns and trigger words you read in Step 1, create hooks:

1. **Select patterns** from hook-patterns.md using the Pattern Selection Matrix (match user's goal + platform)
2. **Draft each hook** using the pattern template as your starting point
3. **Integrate 1-2 trigger words** from trigger_words.md into each hook as you write:
   - **Insider words** (secretly, revealed, hidden, uncovered, etc.) → exclusivity patterns
   - **Helper words** (losing, wasting, bleeding, stealing, etc.) → problem/urgency patterns
   - **Thinker words** (backwards, myth, counterintuitive, paradox, etc.) → contrarian patterns
   - **Amplifiers** (literally, every, zero, completely, etc.) → any pattern for intensity

4. **Follow all Writing Rules** (Core Rules, Pattern-Specific Rules, Platform-Specific Adaptations)
5. **Ensure differentiation** - each hook must use a unique pattern
6. **Verify natural integration** - trigger words should enhance, not distract

### 5. Format and Verify
- Structure output according to **Output Format** section
- Complete **Quality Checklist** self-verification
- Verify each hook contains trigger words from the reference file

---

## Writing Rules
Hard constraints. No interpretation.

### Core Rules
- Maximum 120 characters for X/Twitter hooks.
- Maximum 1-2 lines (40-60 characters) for video hooks.
- Lead with the most interesting element.
- Create a curiosity gap (promise value but withhold details).
- Use specific numbers when possible (not "many" but "17").
- Avoid clickbait that doesn't deliver.
- Use power words: steal, secret, mistake, never, proven, blueprint.
- No emojis unless platform-specific (Instagram/TikTok OK, LinkedIn/X avoid).
- No fluff or filler words.
- Active voice only.
- Present tense preferred.

### Pattern-Specific Rules
- For authority hooks: Lead with credible metric.
- For list hooks: Use odd numbers (7 > 6, 5 > 4).
- For story hooks: Start with unexpected outcome.
- For data hooks: Lead with surprising stat.
- For cautionary hooks: Lead with mistake/lesson.

### Platform-Specific Adaptations
- **X/Twitter**: Punchy, contrarian, data-driven, 120 char max.
- **LinkedIn**: Professional, achievement-oriented, thought leadership, 40-60 char first line.
- **Instagram**: Visual promise, lifestyle-oriented, aspirational, 125 char before "more" cutoff.
- **TikTok**: Fast-paced, relatable, trend-aware, 20-30 char on-screen text.
- **General**: Versatile, platform-agnostic.

---

## Output Format
Clean and simple. Just hooks with their pattern type as a headline.

```markdown
### [Pattern Name]
[Hook text]

### [Pattern Name]
[Hook text]

### [Pattern Name]
[Hook text]
```

**Example:**
```markdown
### Authority Credibility
I run a 23-person software agency. Here are 5 things I would never do again.

### Data-Driven Insight
I analyzed 1,000 LinkedIn posts. Here are the top 5 patterns that drove engagement.

### Contrarian
Everyone tells you to post daily. I posted 3x per week and got 10x more engagement.
```

---

## Defaults & Assumptions

Use these unless overridden.

- Number of hooks: 3
- Platform: X/Twitter (most restrictive character limit).
- Goal: Maximize engagement (likes, comments, shares).
- Audience: General business/entrepreneurship audience.
- Tone: Professional but conversational (matches most founders).
- Emotion: Curiosity (safest default for viral content).
- Format: Thread/post opener (not video hook).

---

## References

**These files MUST be read using the Read tool before generating any hooks (see Step 1 of Task Execution):**

| File | Purpose |
|------|---------|

Excerpt, first 6,000 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 90bc6f1

Download folder ↗
git clone https://github.com/ognjengt/founder-skills
git -C founder-skills checkout 90bc6f1424df

The author documents no install command, so this uses the repository directly. Our verdict covers commit 90bc6f1424df only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
CodexMentioned in its text, not testedSkills for Codex · About Codex
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 90bc6f1424df

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/ognjengt/viral-hook-creator/badge.svg)](https://modelsatlas.com/skills/ognjengt/viral-hook-creator/)

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: SAFE B](https://modelsatlas.com/skills/ognjengt/viral-hook-creator/badge.svg)](https://modelsatlas.com/skills/ognjengt/viral-hook-creator/)

Questions about viral-hook-creator

What does the viral-hook-creator skill do?
Claude skills for founders
Is viral-hook-creator safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can viral-hook-creator access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does viral-hook-creator work with?
Its documentation mentions codex. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (90bc6f1424df), 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.