Esc

Type to search across all skills

Overview

SkillSafe is a secured registry for AI coding tool skills. It provides cryptographic integrity verification, dual-side scan report comparison, and content-addressed storage to ensure every skill you install is exactly what the publisher intended.

For AI tool integration, read the raw guide at /skill.md.

Quick Start

1. Install SkillSafe

Copy and send this message to your AI coding tool:

Install skillsafe from https://skillsafe.ai/skill.md

Your AI tool reads the skill definition, downloads the client, and sets up SkillSafe automatically. Works with Claude Code, Cursor, Windsurf, and any AI coding tool that supports skills.

2. Sign In & Save

skillsafe auth
skillsafe save ./my-skill --version 1.0.0
skillsafe share @myname/my-skill --version 1.0.0

Opens your browser to sign in with Google. Saves your skill privately, then shares it via a link. Email verification is required to share; saving is always available.

3. Install & Verify

skillsafe install @publisher/skill-name --tool claude

Downloads, re-scans independently, verifies the report against the publisher's, and installs only if the verdict is verified.

Authentication

All authenticated requests use a Bearer token:

Authorization: Bearer sk_your_api_key_here

API keys are hashed with SHA-256 before storage. The server never stores plaintext keys.

Key Limits

  • Free: 5 active keys
  • Paid: 20 keys
  • Enterprise: unlimited

Manage keys at /account/keys.

Saving & Sharing

Saving a Skill

Skills are saved privately by default. No email verification or scan report required.

POST /v1/skills/@{namespace}/{name}
Content-Type: multipart/form-data

Fields:
  archive      — .tar.gz of the skill directory
  scan_report  — JSON scan report (optional for save)
  metadata     — JSON with version, description, category, tags

Creating a Share Link

Sharing creates a link others can use to download and verify a saved version. Requires email verification and a scan report.

POST /v1/skills/@{namespace}/{name}/versions/{version}/share

Body (JSON):
  visibility   — "private" (link-only) or "public" (discoverable via search)
  expires_in   — "1d", "7d", "30d", or "never"

Size Limits

  • Max archive: 10 MB per version
  • Free: 10 MB total | Paid: 100 MB | Enterprise: 500 MB

Installing a Skill

GET /v1/skills/@{namespace}/{name}/download/{version}
Authorization: Bearer sk_...

After downloading, the consumer CLI extracts, re-scans, submits a report, and installs only on verified.

Verification Model

SkillSafe uses dual-side verification.

verified

Reports match. Safe to install.

divergent

Reports disagree. Review before installing.

critical

Tree hashes mismatch. Do not install.

Personal Vault

Encrypted backup with AES-256-GCM. Server stores only ciphertext.

PUT /v1/vault/{key}
Authorization: Bearer sk_...

API Reference

Base URL: https://api.skillsafe.ai

MethodPathAuth
GET/v1/accountYes
POST/v1/skills/@ns/nameYes
GET/v1/skills/@ns/nameNo
GET/v1/skills/searchNo
POST/v1/skills/@ns/name/starYes
POST/v1/skills/@ns/name/versions/{version}/shareYes
GET/v1/share/{shareId}No
GET/v1/share/{shareId}/downloadNo
DELETE/v1/share/{shareId}Yes
GET/v1/billing/portalYes

Security Model

  • Content-addressed storage: SHA-256 hashes
  • Tree hashes: Immutable per-version
  • Dual verification: Independent sharer + consumer scans
  • API key hashing: SHA-256 before storage
  • Vault encryption: AES-256-GCM, client-side

Report issues: security@skillsafe.ai