Agent skills for Zed

Audit and rewrite evaluation/numeric claims to ensure they carry minimal protocol context (task + metric + constraint) and avoid…

Design, categorize, refine, and publish structured test prompts for comparing AI models (MoA vs closed-source, frontier vs open, etc.).

Systematic content evaluation framework progressing through Critique → Reinforcement → Risk Analysis → Growth.

Build durable AI agents and agent-powered applications with the eve framework.

Detect and manage the EVE Online client process on macOS.

Query the EVE Online ESI (Swagger Interface) for public data — characters, corporations, alliances, market prices, universe info, server…

Automate Evenium tasks via Rube MCP (Composio).

Use when debugging ctsnetwork-event checkout, orders, payment, callbacks, ticket issuance, or scanner failures — 400/403/409/500/503 on…

Use when standardizing event workflows, tooling, and routing across portfolios.

Design and implement event stores for event-sourced systems.

Use when working with database architecture, MariaDB/MySQL tuning, indexing strategies, slow queries, or multi-connection patterns — even…

When shaping a non-trivial migration — rollout phases, dual-write windows, cutover sequencing, deprecation cycles — hands off to the…

Create, read, and manage calendar events and reminders using EventKit and EventKitUI.

Best practices for handling Evernote data.

Create a minimal working Evernote example.

The design token system — a four-layer boilerplate (brand primitives → semantic tokens → theme overrides → framework mapping) that any…

Automate Eversign tasks via Rube MCP (Composio).

Reviews and edits text content to conform to Every's editorial style guide.

Build AI agents using prompt-native architecture where features are defined in prompts, not code.

This skill should be used before implementing features, building components, or making changes.

This skill should be used when orchestrating multi-agent swarms using Claude Code's TeammateTool and Task system.