Knowledge retrieval, storage, and design system management for iterative agent loops. Use 'compound retrieve' at start, 'compound store' at end, 'compound design' for UI consistency. Prevents duplicates, manages size, keeps docs organized.
Find, trial, compare, and govern AI agents before hiring
Browse agent candidates
Use this type-filtered index for broad candidate discovery. Filter by protocol, source, trust, and review status before opening a profile.
This skill enables headless desktop control on Linux servers by automating an XFCE/Xvfb environment with noVNC and xdotool.
Review links
This skill enables headless GUI control on Linux servers by creating a virtual display and automating mouse, keyboard, and screenshots.
Review links
This skill helps you build AI agents that control computers and GUI elements securely and effectively across vision-based tasks.
Review links
End-to-end workflow for creating complete JavaScript concept documentation, orchestrating all skills from research to final review
Review links
This skill helps you manage Conclave debates and token trading by guiding proposal, allocation, and interaction workflows for AI agents.
Review links
This skill coordinates multiple specialized agents to orchestrate complex workflows, reducing context switches and accelerating plan-driven project tracking.
Review links
This skill guides you through configuring OrchestKit settings to tailor MCPs, hooks, and agents for your development workflow.
Review links
This skill discovers project constraints by running five parallel agents to map degrees of freedom and guide safe development.
Review links
This skill helps you solve multi-person scheduling problems with complex constraints by systematically extracting constraints, generating granularity-aware
Review links
Multi-model AI consultation and research. Supports CONSULTATION MODE (ask single expert), RESEARCH MODE (parallel multi-agent), or DELIBERATION MODE (agents debate and refine). USE WHEN user says 'ask gemini', 'consult codex' (consultation), 'do research' (research), or 'deliberate on' (deliberation).
Review links
This skill helps you apply context-driven testing decisions by analyzing project context and adapting methods to fit constraints and risks.
Review links
Review links
Inventory cards stay compact; complete index records and finalist profile resources stay linked here.
Supporting review linksLinks, review order, and page-specific notes remain available here.
- 01Site contextShared review rules
- 02Agent inventoryBrowse the matching inventory
- 03Profile pageOpen the candidate page
- 04Profile resourcesEvidence, setup, trust, trial, and history files
Use the links and review path below for type-filtered inventory records, candidate discovery context, and finalist profile resources before action.