AI & Agents Agent Skills

Project-profile recalibration. Audits session calibration drift, presents per-cluster evidence for a user verdict, writes the updated…

Phase 2 architecture with parallel team workers: dual-stream arch + RefC development.

Provide provider capability awareness and route commands by answering what the current provider supports natively vs must emulate

Transforms vague UI ideas into detailed prompts optimized for Stitch -- enhances specificity, adds UI/UX keywords, injects design system…

Build Stitch-ready prompts from vague UI ideas (Path A) or from a Design Spec plus user request (Path B).

Style template format specification. Single markdown files that describe artistic direction.

Use when executing implementation plans with independent tasks in the current session

Governs, validates, and promotes AI agent skills through auditable multi-agent collaboration and shadow routing.

Parallel task orchestration CLI that dispatches work to AI workers (via Claude Code) in isolated git workspaces.

Multi-agent coordination patterns for OpenCode swarm workflows.

Initialize a multi-agent swarm with anti-drift configuration.

Agent skill for swarm-pr - invoke with $agent-swarm-pr

Orchestrates a multi-agent debate and decision-making framework to generate comprehensive implementation plans without executing code.

Gap surfacing before decisions. Raises procedural, consideration, assumption, and alternative gaps as questions when gaps go unnoticed…

Generate system definition file for ToolSmith with tested OS commands

Agent skill for orchestrator-task - invoke with $agent-orchestrator-task

Preset-driven team building — spawn coordinated multi-agent teams from battle-tested presets for full-stack, review, testing, TDD, and…

Launch Agent Team for feature implementation with review gates (coders + specialized reviewers + tech lead).

Send an interrupt signal to a working team agent.

Set up a complete agent team with file-based planning for complex multi-agent projects.

Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario analysis from each…