gsd-set-profile
Switch model profile for GSD agents (quality/balanced/budget/inherit)
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,666 results
multi-agent-patterns
Design multi-agent systems with supervisor, peer-to-peer, and hierarchical architectures. Use for agent coordination, context isolation, and distributed…
vp-interaction-routing
Select the lowest-cost reliable interface for interacting with applications and services. Use before browser or desktop automation, especially when choosing…
vp-interaction-routing
Select the lowest-cost reliable interface for interacting with applications and services. Use before browser or desktop automation, especially when choosing…
agents-validator
Use when validating CLAUDE.md and AGENTS.md hierarchies across directories, checking that every CLAUDE.md contains @AGENTS.md on its own line, and content…
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
dynamic-agents
Orchestrate a large task across multiple agents with cost-aware model routing — session model for judgment-heavy work, Sonnet for mechanical work, Fable or…
screencast
Turn an agent-browser session into a polished product-demo video — fully local, free, no cloud upload. Records the browser to WebM while logging every action,…
claude-update
Update CLAUDE.md and skills when introducing new patterns or conventions. Triggers: "update claude", "update skills", "new pattern", "add convention".
app-builder
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack,…
template-skill
Replace with a clear description of what the skill does and when an agent should use it.
roast-my-agents-md
Brutally honest AGENTS.md/CLAUDE.md review backed by real A/B test evidence. Not just opinions — actual proof that your rules are dead weight. Roasts…
workflows
Write, run, and inspect persisted multi-agent DevSpace workflows, JavaScript scripts that compose subagent calls with agent, phase, parallel, and pipeline.
unity-game-grilling
Interrogate the user item by item regarding product, experience, architecture, visual, cost, licensing, and release trade-offs in Unity 6 games that cannot be eliminated by evidence or reasonable assumptions, and record versioned conclusions; used when the user explicitly requests interrogation, or when continuing to advance genuinely requires a user decision, not for factual queries or ordinary local implementation.
unity-game-workflow-control
The sole global workflow control plane for Unity game repositories; controls the executable state from requirements to release through six phases, A0-A6 risks, F0-F4 gates, implementation packages, and evidence manifests.
customize-yak
Adapts the YesYak process to a project or a person without editing any skill. It detects what the project already has, asks only what is missing, and after a…
session-retrospective-rules
Reviews the current piece of work, also when it spans several sessions. It finds what the user asked and whether it was done, the instructions the user…
unattended-run
Lets the feature-delivery-pipeline and its phase skills run from start to end without the user. The agent answers every checkpoint, interview round and "which…
wendy-device-enrollment
Expert guidance on enrolling WendyOS devices with pki-core and managing their certificate lifecycle. Use when developers mention: (1) device enrollment or…
graphiti-guide
Build real-time knowledge graphs for AI agents using Graphiti by Zep
agent-gen-image
Give agents image generation and editing abilities using `rawgenai` — create images from text, edit existing images, inpaint, and generate with reference…
claude
Enhanced CLI module for Claude Code, supporting third-party model providers and session management. Core Scenario: When the user wants to use Claude Code with…
deepseek
Integrate DeepSeek AI for high-performance text generation and specialized reasoning. Core Scenario: When the user wants to use DeepSeek's V3 or Reasoner…
llmf
Run local LLMs with zero dependencies using llamafile, supporting API servers, CLI chat, and model management. Core Scenario: When the user wants to run…