Skill UI

This skill covers the implementation of Ed25519 digital signatures, a high-performance algorithm utilizing the Curve25519 structure. It details key pair generation, message signing, and signature verification. Ed25519 offers superior performance, determinism, and side-channel resistance compared to RSA and ECDSA. Use this skill for establishing robust authentication, ensuring data integrity, and securing system components like code or APIs.

A governance skill designed to secure AI agent tool calls using advanced authorization policies. It implements Cedar policies to control which tools agents can access and under what conditions. Key features include running in 'Shadow mode' for safe observation, 'Enforce mode' for strict blocking, and generating cryptographically signed Ed25519 receipts to provide an immutable, tamper-evident audit trail for every policy decision.

Mint and verify tamper-evident signed receipts for consequential AI agent actions such as deploy, delete, pay, or grant access. Supports EU AI Act Art. 12 record-keeping with Ed25519 and post-quantum signatures, verifiable offline from the receipt alone.

This skill executes comprehensive historical backtesting using the high-performance neural-trader engine. It supports features like walk-forward validation and captures key financial metrics (Sharpe, Drawdown). Critically, it signs the resulting artifact using Ed25519 cryptography, providing non-repudiable tamper evidence required for promoting research models to live trading systems.

Sign, verify, and track fix-marker regressions over time using a deterministic Ed25519 witness manifest. Works in any project — clone the toolkit, run init, register fixes, regen on each release.

Join and operate a signed agentbbs federation across hosts: pin peers, serve rooms, sync messages, and coordinate work claims using verified node identities.

A governance skill designed to secure AI agent tool calls using advanced authorization policies. It implements Cedar policies to control which tools agents can access and under what conditions. Key features include running in 'Shadow mode' for safe observation, 'Enforce mode' for strict blocking, and generating cryptographically signed Ed25519 receipts to provide an immutable, tamper-evident audit trail for every policy decision.

Send and receive cryptographically signed messages between AI agents via the AMP CLI. Initialize identities, send, read, reply, delete messages, set priority or type, and attach files, with local-first Ed25519-signed delivery.