mobilerun-docs
Mobilerun documentation reference. Use when users ask about Mobilerun setup, configuration, SDK usage, CLI commands, device setup, agents, architecture, app…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-10 00:15
Agents & models
26,026 results
mobilerun-assistant-mcp
Talk to the Mobilerun virtual assistant through the MCP assistant tool — create or resume a chat session, send a natural-language task, poll replies, answer…
project-memory-context-sync
Use this skill when adding, editing, or updating any Project Memory configuration files in this workspace — instruction files (.instructions.md), agent…
arena
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the…
figure-it-out
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales…
swarm
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
agent-info
Query the list of all agents (employees) available to the current user. Use when generating code that requires a real agentId, or when the user asks "which…
custom-agent
[AI & Tools] Use when creating, verifying, or enhancing Claude Code custom agent files.
grill
[Decision Support] Use when the user wants a plan, design, decision or idea stress-tested by interview before anything is written or built, or says "grill me".
project-skill-protocol
[Utilities] Use when a project adds, changes, lists or removes its OWN protocol rules layered over a framework skill (additive only). list | add | update |…
prompt-enhance
[Skill Management] Use when enhancing, compressing or expanding prompts, docs or skills. --op={compress|expand|enhance}.
start-workflow
[Skill Management] Use when starting a detected workflow, initializing workflow state, or activating a workflow sequence.
sync-skills-shared-protocols
[Skill Management] Use when shared protocol checklists change and need propagating across skills.
tech-stack-research
[Architecture] Use when a workflow step or the user asks for tech-stack research: alternatives, trade-offs and user-validated recommendations.
template-skill
[Category] Use when defining the standard skill description pattern.
workflow-end
[Process] Use when the active workflow has finished its steps or the user asks to close it: checks outcome evidence and owned changes, then closes the…
workflow-greenfield-init
[Workflow] Take a new product from idea through architecture, an approved plan and scaffolding to a reviewed, tested foundation; hand the first slice to…
workflow-planned-work
[Workflow] Turn an idea or existing canonical specs into a reviewed provisional spec or reviewed, readiness-checked, prioritized planned tasks and stories;…
seeing-as-agent
Debugging methodology for LLM tool calls — trace from the model's side first, use runtime evidence over code inference, and follow live request chains for…
elevenlabs-agents
Work with ElevenLabs Conversational AI agents - initiate calls, retrieve transcripts, manage phone numbers, and analyze agent conversations. Use when building…
operate-module
Answer questions about a deployed Duvo Module automation and change it safely, the way Ask Duvo does. Use when the user asks how an Automation is doing, what…
unsloth-training
Fine-tune LLMs with Unsloth using GRPO or SFT. Supports FP8, vision models, mobile deployment, Docker, packing, GGUF export, dataset preparation, synthetic…
ika-solana-pre-alpha
Guide for building on the Ika Solana devnet pre-alpha, a mock ika network. Use when creating dWallets or signing from a TypeScript app on Solana devnet, when…
grok-pi-herdr-orchestration
Use Herdr and shell scripts to create, drive, monitor, and stop grok-pi subagents, suitable for read-only code exploration, repository research, material organization, and long tasks that need visible terminal progress; use when the user mentions grok-pi, Herdr, Grok subagents, research agents, background agents, or asks to periodically check subagent progress.