About Mr. Technology

A curated AI skills registry.
Scanned, ranked, and explained.

Mr. Technology indexes the open AI agent skills ecosystem, runs a four-scanner evidence pipeline over every record, and curates the subset worth your time. The scanner output is published, not hidden.

What we curate

The agentic web has a quality problem. The open ecosystem has tens of thousands of “AI skill” repos. Most have not been tested. Most will not load cleanly. Some are malicious.

We don’t claim to certify anything. What we do is publish what the scanners found— source commit, scan timestamp, scanner verdict, and the explicit gaps where evidence does not exist. You decide what to ship.

The curated registry surfaces the records that are worth your evaluation time— skills that scanned cleanly, skills with documented licenses, skills whose source archive is reproducible. Everything else is in the broader index, marked with its evidence tier.

How the evidence is produced

1
Source archive and provenance
When source is available, the registry pins each record to a specific Git commit, source blob, and license. The scan output references the same commit so the audit can be re-run later.
2
Four scanners, fail-closed
gitleaks for secret patterns, Semgrep for unsafe execution and prompt-injection sinks, Trivy for known vulnerable dependencies in supported manifests, and SkillSpector for AI-skill-specific patterns. A scanner that cannot complete does not yield a passing verdict.
3
Verdict and evidence tier
CLEAN, FLAGGED, ERROR, QUARANTINE, or INCOMPLETE. The labels summarize stored scan output; they are not certification. INCOMPLETE is the honest answer when the scanner could not lock to one skill directory.
4
Curated subset
Records that scanned cleanly across all four scanners, with reproducible source, become candidates for the curated registry. The full index is still browsable.

What we index

We scan a defined set of files. Records that match these formats become candidates for the curated registry. Anything outside this set is not indexed and not curated.

Indexed formats
  • SKILL.md — Claude Skills Registry format
  • manifest.json, tools.json, server.json, mcp.json — MCP server format
  • package.json — Node.js dependencies (Trivy-scanned for known CVEs)
  • skill.yaml, SKILL.yaml, *.skill.md — YAML skill manifests
  • AGENTS.md, design.md, architecture.md, prompt.md, tool.md, README.md — agent-instruction files (when submitted through /submit-skill tagged as agent_docs)
Not in scope
  • Arbitrary README.md in repos without other indexed files — not promoted to a curated record on its own
  • Code files (*.py, *.ts) — security-scanned but not extracted as content
  • Plugin compositions / persona packages — not built (see scope)

What you get on the site

The Curated Registry

Skills that scanned cleanly and have reproducible source. The default view when you land on /registry.

The Full Index

Everything else, with evidence tiers. Browse, filter by verdict, see exactly what the scanner found and what it didn’t.

The Blog

Operator dispatches: what I learned shipping a skill that uses these scanners, what broke, what the registry showed me about the state of the open ecosystem.

The Blueprints

Free, inspectable workflow manifests. They are reference documents for candidate pipelines — not installers and not certification.

Why trust this

The scanner pipeline is open about its inputs and outputs. Every registry record carries a verdict, a scan timestamp, the source commit, and the four scanner states (gitleaks, semgrep, trivy, SkillSpector). When evidence is missing, the verdict says so. We do not average across incomplete data.

The pipeline is not a security certification. It is a reproduction layer — the same four scanners, run over the same source archive, will produce the same verdict. That is what makes the registry useful: you can re-run it on your own machine, against your own risk tolerance, and form your own judgment.

Free by default. Author support if you ship skills.

Free — no signup
Browse the curated registry, read the blog, copy blueprint manifests, query the public API. Validate every artifact in your own environment.
Author Support — from $299
For skill authors who want a deeper remediation review of their own repo. The same scanner evidence, plus a written analysis of what would change the verdict.

Built by

Editor: Rami Hollingsworth (editor@mr.technology), an AI Engineer and automation architect.

I built Mr. Technology as a dedicated hub for crafting the next generation of autonomous digital systems. Backed by a degree in Software Engineering and extensive experience in systems precision, my work focuses on advanced AI development, multi-agent frameworks, and automated workflows.

The scanners are real, the verdicts are reproducible, and the registry is published as-is. No certifications, no asterisks. If a record says CLEAN, it means the four scanners ran without finding anything they were configured to flag — nothing more.

For background, credentials, and prior work, see LinkedIn.

Get in touch