Skill UI

Scans Solana and Anchor programs for six critical security vulnerabilities—arbitrary CPI, improper PDA validation, missing signer/ownership checks, sysvar spoofing, and instruction introspection issues—to support audits and pre-launch reviews.

A cultural pressure‑style skill that forces the assistant to repeatedly push past failures, think systemically, validate every change, and proactively hunt down related issues until end‑to‑end ownership is demonstrated.

Audits AI-assisted legal, compliance, governance, and institutional decisions before reliance to determine whether the responsible human or institution has enough access to evidence, reasoning, uncertainty, authority, and review path to genuinely own the decision rather than merely approve, sign, or transmit it.

Delegate bounded work to other AI agents while preserving context, file ownership, and progress checks. Covers agent selection, structured prompts, polling, remote VPS safety, and driving interactive CLIs.

Coordinate focused subagents on substantial work while maintaining non-overlapping ownership and integrating verified results. Ideal for large-scope tasks where parallel processing reduces elapsed time. Decompose tasks into distinct assignments, run scouts in parallel, assign distinct ownership, and synthesize outputs. Keep trivial work with the coordinator to avoid overhead.

Review supervisor, swarm, planner-worker and parallel agent workflows as distributed state machines: task ownership, shared state, branch joins, retries, cancellation, context handoffs, budgets, deadlocks and human escalation before rollout.

This skill monitors the progress, blockers, and task ownership of an AI team. It summarizes completed, active, and blocked work while distinguishing assertions from verified evidence. It surfaces decisions for the user and ensures budget reporting accuracy without claiming unverified execution.

This skill coordinates work across a RuFlo AI-agent swarm by discovering channels, reading signed updates, and checking claims. It helps manage multi-agent status, handoffs, ownership conflicts, and shared-work planning. Users must treat relay-sourced messages as untrusted and avoid irreversible actions unless explicitly requested. It ensures safe coordination without unauthorized state changes.