Hook Stack Evaluator
This skill analyzes code hooks and stack interactions to identify potential vulnerabilities or unexpected behavior for security assessment.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add hook-stack-evaluator npx -- -y @trustedskills/hook-stack-evaluator
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"hook-stack-evaluator": {
"command": "npx",
"args": [
"-y",
"@trustedskills/hook-stack-evaluator"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The Hook Stack Evaluator analyzes content hooks (headlines, opening lines, video intros, carousel openers) using The Hook Stack™ framework. It provides scoring and actionable refinement suggestions to improve hook effectiveness. The skill operates in either automatic or interactive modes, adapting its approach based on the user's intent and context.
When to use it
- To evaluate a headline or subhead for a newsletter.
- When seeking feedback on an opening line for content.
- To refine video introductions or carousel openers.
- In automated workflows where hooks need consistent evaluation and improvement.
- When needing assistance in crafting more compelling hooks through collaborative refinement.
Key capabilities
- Evaluates hooks against a 5-layer framework (The Hook Stack™).
- Provides scoring and actionable refinement suggestions.
- Operates in Automatic mode for automated workflows, generating improved alternatives if the score is below a threshold.
- Offers Interactive mode for collaborative refinement with user feedback ("Keep / Tweak / Trash?").
- Adapts to context signals to determine operational mode (Automatic or Interactive).
Example prompts
- "Evaluate this headline: 'The Future of AI'"
- "Run this opening line through the hook stack: 'In today's world...'"
- "Score my video intro."
- "Help me sharpen this hook for a LinkedIn post about marketing trends."
Tips & gotchas
- The skill adopts a direct and no-fluff communication style.
- Automatic mode skips audience/platform questions, relying on context or defaults.
- If the intent is unclear, the skill will default to Interactive Mode.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.