技能检索
scalekit-agent-auth
Secure OAuth token management via Scalekit. Handles token storage, refresh, and retrieval for third-party services (Gmail, Slack, GitHub, etc.). Never stores tokens locally - always fetches fresh tokens from Scalekit.
vigil
AI agent safety guardrails for tool calls. Use when (1) you want to validate agent tool calls before execution, (2) building agents that run shell commands, file operations, or API calls, (3) adding a safety layer to any MCP server or agent framework, (4) auditing what your agents are doing. Catches destructive commands, SSRF, SQL injection, path traversal, data exfiltration, prompt injection, and credential leaks. Requires npm package vigil-agent-safety (12.3KB, under 2ms latency). Source: github.com/hexitlabs/vigil
fosmvvm-viewmodel-test-generator
Generate ViewModel tests with codable round-trip, versioning stability, and multi-locale translation verification.
cross-model-review
Adversarial plan review using two different AI models. Supports static mode (fixed roles) and alternating mode (models swap writer/reviewer each round, fully autonomous). Use when building features touching auth/payments/data models, or plans >1hr to implement. NOT for simple fixes, research tasks, or quick scripts.
azhua-skill-vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
arc-security-audit
Comprehensive security audit for an agent's full skill stack. Chains scanner, differ, trust-verifier, and health-monitor into a single assessment with prioritized findings and trust attestations.
arc-trust-verifier
Verify skill provenance and build trust scores for ClawHub skills. Checks publisher history, version consistency, dependency trust chains, and generates trust attestations.
self-review
Automatically review agent output quality before sending to user.
arb-injection
BYOCB ArbInjectionSkill: Scan EVM smart contracts for arbitrary call injection vulnerabilities. Monitor chains in real-time or scan specific addresses.