AI skills, indexed with
visible evidence limits.

Search the live registry, inspect each record's source and scanner state, and keep incomplete scans 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 evidence tier and scan state.

2

Look under the hood

Review scanner findings, verdict reason, provenance state, and source evidence for free. Where qualified, non-standalone SKILL.md source snapshots include exact bytes, a pinned commit, and applicable license or notice evidence.

3

Adapt deliberately

Inspect a single skill, or start from a free Blueprint — a reference manifest for designing an agent workflow. Adapt and validate it in your own environment before production.

From the blog2026-08-05

Meta Shipped Muse Spark 1.2 and a Coding Agent — It's Good, It's Closed, and It's Still Not Opus 5

Meta released Muse Code and Muse Spark 1.2 today as a co-trained pair — terminal coding agent plus model, 1M-token context, $1.25/$4.25 per million tokens on the no-train tier. On Terminal-Bench 2.1 it lands at 82.9%, second only to Opus 5's 86.7%. On DeepSWE it's third. On the kernel-optimization case study it's fourth. Meta is now a real third option in the coding-agent wars. It's just not the top one.

Why teams use Mr. Technology

Most AI registries stop at links. We expose recorded evidence—and the gaps—record by record.

Recorded evidence, not five-star reviews

Completed scans combine source metadata, secret detection, dependency checks, and static-analysis findings where that evidence is 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 evidence. Paid human review.

Browse the registry and public API without an account. Commission a scoped one-time audit when automated evidence is not enough for a shipping decision.

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.

// SOURCE_REVIEW_FIRST

Free registry. Paid decisions.

Use public evidence at no charge. Buy a fixed-scope assessment when a human-reviewed release decision matters.

Free

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

$0
  • · Full registry browse
  • · Verdicts, tiers, evidence limits, and provenance
  • · Public API (paginated, up to 5,000 records/query)
  • · License-qualified SKILL.md source snapshots where available
  • · Free blueprint manifests
  • · Blog + pillar articles
One-time

Publisher Skill Audit

For one public or privately shared repository with up to ten skill folders.

$299
  • Provenance and dependency inventory
  • Gitleaks, Semgrep, and Trivy evidence
  • Human-reviewed PDF + JSON decision report
  • One remediation rescan within 30 days

Built for security teams and the developers they unblock.

Live registryRegistry loading…Snapshot date unavailable