AI & Agents Agent Skills

Diverga Dashboard - Live configuration status and feature overview. 24 specialized agents across 9 categories for social science research.

Tailoring AI behavior for specific professional domains.

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy…

Agent that simulates Elon Musk with high-fidelity psychological and communicational depth.

Improve prompts with design specs and UI/UX vocabulary.

Transforms vague UI ideas into polished, Stitch-optimized prompts.

Use when generating the unified enhancement report from aggregated findings.

Use when reviewing SKILL.md files for structure and trigger quality.

Environment diagnostics — check providers, auth, config, hooks, scheduler, and more

How the AI communicates mistakes, uncertainty, and limitations gracefully.

When and how AI should escalate to humans, refuse, or ask for clarification.

Set or report the reproducibility mode governing how AIWG workflows execute, from standard to fully auditable

Create Claude Code skills with best practices, structure, validation, and testing.

Alias for $council --mode=debate (adversarial named-persona debate).

Use this plugin when the user wants to create, improve, validate, publish, or submit an OpenDesign plugin using the plugin spec, examples…

Coordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated implementation.

Analyze images — segment objects, detect, run OCR, describe, and answer visual questions via fal.ai vision models.

Generate workflow JSON files for chaining AI models

Dispatch the same query to multiple subagents in parallel across chunks in a manifest and aggregate results with source provenance

Create new skills, modify and improve existing skills, and measure skill performance.

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule"…