frankensteinCombine the best parts of multiple skills into one. Searches ClawHub, GitHub, skills.sh, skillsmp.com and other AI skill repos. Analyzes each safely, compares features, and builds a combined 'Frankenstein' skill with the best of each. Uses skill-auditor for security scanning and sandwrap for safe analysis. Use when: (1) Multiple skills exist for same purpose, (2) Want best-of-breed combination, (3) Building a comprehensive skill from fragments.
Install via ClawdBot CLI:
clawdbot install frankensteinDefault: Opus (or best available thinking model)
Frankenstein requires deep reasoning to:
Only use a smaller model if user explicitly requests it for cost reasons. The synthesis quality depends heavily on reasoning depth.
Create monster skills by combining the best parts of existing ones.
Frankenstein me an SEO audit skillSearch EVERY AI skills repository for matching skills:
1. ClawHub (primary)
clawhub search "[topic]" --registry "https://clawhub.ai"2. GitHub
Search: "[topic] AI skill" OR "[topic] claude skill" OR "[topic] agent skill"
Look for: SKILL.md, CLAUDE.md, or similar agent instruction files3. skills.sh
https://skills.sh/search?q=[topic]4. skillsmp.com (Skills Marketplace)
https://skillsmp.com/search/[topic]5. Other sources to check:
Gather all candidates before filtering. More sources = better Frankenstein.
Run each skill through skill-auditor. Skip any with HIGH risk scores.
For each skill found:
Analyze safe skills in sandwrap read-only mode.
For each safe skill, extract:
Build comparison matrix:
| Feature | skill-A | skill-B | skill-C | WINNER |
|---------|---------|---------|---------|--------|
| Feature 1 | Yes | No | Yes | A, C |
| Feature 2 | Basic | Advanced | None | B |
| Feature 3 | No | No | Yes | C |
Take the winning approach for each feature:
Use skill-creator to assemble the Frankenstein skill:
Run plan → test → improve loop until 3 stable passes:
Pass 1:
1. Read draft
2. Try to break it (find holes, contradictions, gaps)
3. Document issues
4. Fix them
Pass 2:
1. Read improved version
2. Actively try to find MORE issues
3. Fix any found
Pass 3+:
Continue until you genuinely try to improve
but can't find significant issuesWhat to look for each pass:
Document in VETTING-LOG.md:
Only proceed when:
Present the vetted skill for approval:
Creates a new skill with:
User: "Frankenstein me an SEO audit skill"
Frankenstein:
Searching ClawHub for "SEO audit"...
Found 5 skills:
1. seo-audit (coreyhaines31)
2. audit-website (squirrelscan)
3. seo-optimizer (local)
4. technical-seo (unknown)
5. seo-checker (unknown)
Security scanning...
✓ seo-audit: SAFE (8/10)
✓ audit-website: SAFE (7/10)
✓ seo-optimizer: SAFE (9/10)
✗ technical-seo: RISKY (4/10) - skipping
✗ seo-checker: RISKY (3/10) - skipping
Analyzing 3 safe skills...
Comparison:
| Feature | seo-audit | audit-website | seo-optimizer |
|----------------------|-----------|---------------|---------------|
| Methodology depth | ★★★★★ | ★★★ | ★★★★ |
| Automated rules | None | 230+ | 50+ |
| Auto-fix capability | No | No | Yes |
| CLI tool | No | squirrel | No |
| E-E-A-T coverage | Yes | Yes | Partial |
Recommended combination:
- Methodology: seo-audit (best framework)
- Rules engine: audit-website (230+ rules via squirrel CLI)
- Auto-fix: seo-optimizer (automated fixes)
- E-E-A-T: seo-audit (comprehensive)
Build this Frankenstein? [Yes/No]This skill uses:
When spawning analysis sub-agents, always use Opus (or best thinking model) unless user explicitly requests otherwise:
sessions_spawn(
task: "FRANKENSTEIN ANALYSIS: [topic]...",
model: "opus"
)Cheaper models miss nuances between skills and produce shallow combinations.
When a Frankenstein skill is built, it includes attribution:
## Sources
Built from best parts of:
- seo-audit by coreyhaines31 (methodology)
- audit-website by squirrelscan (rules engine)
- seo-optimizer (auto-fix)Generated Mar 1, 2026
A digital marketing agency wants to create a proprietary SEO audit tool by combining the best features from existing open-source skills. They use Frankenstein to analyze multiple SEO skills, merge advanced methodology with automated fixes, and build a unified tool for client audits, saving development time and ensuring high quality.
A large enterprise has multiple AI skills for customer support across different teams, leading to inconsistency. They employ Frankenstein to search for and combine the top skills, integrating the best response generation, ticket handling, and security features into a single, vetted skill for company-wide use.
A tech startup is building a new AI-powered analytics product but lacks resources. They use Frankenstein to gather and synthesize skills from various repositories, combining data visualization, predictive modeling, and reporting features into a cohesive skill, accelerating their MVP development.
An online education platform needs a skill to generate and optimize learning content. Frankenstein helps by analyzing multiple content creation skills, merging the best instructional design, accessibility checks, and engagement techniques into one skill, enhancing course quality and efficiency.
A healthcare organization seeks to improve compliance documentation by combining AI skills. Frankenstein searches for skills related to medical coding, privacy regulation, and report generation, synthesizing them into a secure, audited skill that ensures accuracy and regulatory adherence.
Offer Frankenstein as a service to businesses that need custom AI skills but lack expertise. Charge a fee for analyzing, combining, and vetting skills from public repositories, delivering tailored solutions with security scanning and documentation.
Create a marketplace where users can access pre-built Frankenstein skills or request custom combinations. Generate revenue through monthly subscriptions for premium skills, with tiers based on complexity and support, leveraging the vetting process for quality assurance.
Provide consulting services to help organizations integrate Frankenstein skills into their workflows. Revenue comes from hourly rates or retainer fees for ongoing support, training, and customization, targeting industries like marketing and tech.
💬 Integration Tip
Integrate Frankenstein early in the development cycle to leverage its security scanning and vetting loop, ensuring stable and high-quality skills from the start.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Perform a comprehensive read-only security audit of Clawdbot's own configuration. This is a knowledge-based skill that teaches Clawdbot to identify hardening opportunities across the system. Use when user asks to "run security check", "audit clawdbot", "check security hardening", or "what vulnerabilities does my Clawdbot have". This skill uses Clawdbot's internal capabilities and file system access to inspect configuration, detect misconfigurations, and recommend remediations. It is designed to be extensible - new checks can be added by updating this skill's knowledge.
Use when reviewing code for security vulnerabilities, implementing authentication flows, auditing OWASP Top 10, configuring CORS/CSP headers, handling secrets, input validation, SQL injection prevention, XSS protection, or any security-related code review.
Security check for ClawHub skills powered by Koi. Query the Clawdex API before installing any skill to verify it's safe.
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them. Security audit tool that detects data exfiltration, system modification attempts, backdoors, and obfuscation techniques.