AI skills, indexed with
visible audit evidence.

Search the live registry, inspect each record's verdict and available scanner evidence, and keep incomplete audits visibly separate from completed ones.

Registry stats loading…

How it works

1

Find what you need

Search the registry by what you're trying to do — security scanning, SEO checks, deployment, and more. Each record shows its current tier and verdict, including incomplete audits.

2

Look under the hood

Review the scanner findings, verdict reason, and available source evidence. The $29.99/mo plan unlocks detailed reports for audited skills.

3

Ship it

Inspect a single skill, or start from a free Blueprint — a curated manifest for assembling a complete agent workflow. Validate it in your own environment before production.

From the blog

Anthropic Just Shipped Claude Sonnet 5.5 At 70% Off Opus 5 With A Native Multi-Step Verification Loop. It Is The Direct Engineering Answer To The GPT-5.6 Sol Disaster. Here Is The Architecture, The Invoice Math, And The 3-Line Migration That Kills Your OpenAI Spend.

Twenty-six hours after the Bottleneck Labs GPT-5.6 Sol 48-hour business disaster hit Hacker News, Anthropic shipped Claude Sonnet 5.5 at $1.80/$9.00 per million tokens, 70% below Opus 5, with a new verify_steps API primitive that puts predicate-style multi-step agent verification on the wire as a first-class field. The four-way frontier pricing war is now a four-way verification war. Here is the architecture, the four rules that would have caught every failure mode in the Bottleneck transcript, three concrete invoice-math scenarios for the migration, and the three-line code swap that gets you 70% of the way.

Why teams use Mr. Technology

Most AI registries are basically link farms. We actually look at the code.

Real audits, not five-star reviews

Completed audits combine source, secret, dependency, static-analysis, and behavior signals where those checks are available. Pending and incomplete records stay visibly marked.

You can see what's inside

Scanner outputs, timestamps, source links, verdict reasons, and a plain-English summary are shown when that evidence exists.

Blueprints you can inspect and adapt

Tired of starting from a blank page? A Blueprint gives you a curated workflow manifest to inspect, adapt, and validate in your own environment.

Free access with one optional paid plan

Start free — browse the registry, read the blog, and copy blueprint manifests. Subscribe to the $29.99/mo plan when you need API access or detailed audit reports.

Featured technical guides

See all payloads →
New

OpenClaw assistant and operations skills.

Browse registry entries for assistant workflows, gateway operations, security review, and local automation. Check each record's evidence before installing it in your environment.

// ASSISTANT_READY

Free for everyone. One paid plan.

Browse the registry, read the blog, and copy blueprint manifests. Subscribe only for API access and detailed audit reports.

Free

No signup. Browse the registry, read the blog, and copy blueprint manifests.

$0
  • · Full registry browse
  • · Verdicts, tiers, and audit status
  • · Public API (paginated, up to 5,000 records/query)
  • · Free blueprint manifests
  • · Blog + pillar articles
One plan

API + audits

For teams shipping agent features in production. API key + detailed audit reports.

$29.99/mo
  • Detailed scanner findings and audit evidence
  • API key, higher rate limits
  • Premium API endpoint
  • Email support

Built for security teams and the developers they unblock.

Live registryRegistry loading…Updated 2026-08-04