Agent skills for Claude Desktop

Coach the user on getting more out of Claude Code.

Use when you need a comprehensive health scorecard of a codebase — scores security, code quality, test coverage, documentation, and AI…

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

Use when planning or implementing any ctsnetwork-event feature, business-rule, schema, endpoint, report/analytics/export…

Record domain events and dispatch to inbox handlers for side effects, audit trails, and activity feeds.

Create a minimal working Evernote example.

Automate Eversign tasks via Rube MCP (Composio).

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

Write Ruby gems following Andrew Kane's proven patterns and philosophy.

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

Full autonomous engineering workflow

Upload, sync, and manage files across cloud storage providers using rclone.

Execute work plans efficiently while maintaining quality and finishing features

Open or update the user's Everythings Panel — a live claude.ai artifact showing their workspaces, things, marks, and comments, with a…

For evidence before the social court — overview: syllabus, burden of proof and counter-argument; result: burden of proof and…

Verify a clinical, drug, or evidence claim against primary sources — FDA labels (openFDA / DailyMed) and PubMed — when a local reference…

Find and fix bugs worth fixing instead of inventing hypothetical edge cases.

Records visual proof while testing UI behavior — screen recording with structured test/assertion annotations — then posts the video and a…

Use when research must support an action or claim.

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model.

Run autonomous improvement loops.