8-Stage Verified Pipeline

1000+ Verified Skills.

Every skill goes through an 8-stage security verification pipeline before agents can use it.

994
Total Skills
792
Verified
784
Grade A
30
Categories

Popular Skills

Curated integrations used by thousands of agent workflows

How Verification Works

Every skill passes through 8 security stages before agents can use it

Ingest

Fetch & parse SKILL.md

pending

Schema

Validate structure

pending

Static

Code pattern scan

pending

Dataflow

Trace data paths

pending

LLM

AI consensus review

pending

Sandbox

Live execution test

pending

Provenance

Source verification

pending

Verdict

Grade assigned

pending
Verification Pipeline

Waiting to ingest skill...

Grade System

Every verified skill receives a grade based on its security posture

A

No Findings

All checks pass. No security findings. Safe for production agent workflows without restrictions.

B

Minor Findings

Minor findings detected. No security risk identified. Approved with informational notes for review.

C

Moderate Findings

Moderate findings present. Manual review recommended before use in sensitive agent workflows.

F

Critical Findings

Critical security findings. Blocked by default. Cannot be used until issues are resolved and re-verified.

Categories

Skills organized across every integration domain

Ready to Explore?

Browse the full registry of verified skills or contribute your own to the open-source ecosystem.