hiclaw-multi-agent-collaboration
Set up and manage collaborative multi-agent teams using HiClaw, a Kubernetes-native platform with Matrix rooms for human-in-the-loop AI coordination
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-28 00:17
Agents & models
24,978 results
run-plan
Execute a multi-phase implementation plan by delegating each phase to sub-agents with fresh context windows. Use when the user invokes run-plan with a plan…
webmcp-agent
A skill for guiding AI Agents to interact with WebMCP web pages, triggered immediately after the AI Agent calls the browser (e.g., via chrome-devtools MCP or…
reasoning
This skill should be used when the user asks to "reason through", "think step by step", "analyze systematically", "debug with hypotheses", "root cause…
test-coverage
Measure and report test coverage across all test types
skill-creator
Create new skills or improve existing skills by clarifying intent, drafting SKILL.md instructions, organizing supporting resources, and doing lightweight…
opencode-ensemble
Use when coordinating OpenCode Ensemble teams, delegating independent coding work, reviewing teammate output, or running staged parallel waves. NOT for…
deliberative-analysis
Use when comparing non-trivial options or making a design/architecture/experiment/product/research/strategy decision with real tradeoffs, unclear criteria, or…
model-code-analyzer
Translate a human-approved main method and usable baseline into a minimal language-neutral implementation and experiment contract. Use after G2.5 and data…
terra-connections
Terra API device and provider connections. Use when connecting users to wearables (Fitbit, Garmin, Apple Health, Oura, WHOOP), managing user sessions, or…
media-toolkit
Use when an agent needs to upload, transcribe, segment, transform, matte, or inspect media from a local file or URL. Use this for transcription requests too:…
symphony
Use when an agent is given a Symphony work item ID, needs to load the item from the Symphony task client, do the target repo work, and update lifecycle state…
ai-orchestration-vercel-ai-sdk
Vercel AI SDK patterns - providers, text generation, streaming, structured output, tool calling, chat UI hooks, embeddings, and RAG
agnt-cli-builder
Build a whole_bot via the agntdev CLI (`agnt`). USE FOR: a one-time connect code in the prompt, a request to "build the bot" / "look at this project", an `agnt…
kadath
Run KADATH (Kernel for Agentic Darwinian Adaptation, Tooling, and Heredity), a Docker-based evolutionary kernel that turns a goal into a locked,…
mcp-server-sv-number
Drive the SV Number MCP server (`sv-number-mcp`), nine stdio tools that order a private phone number for one signup, read the SMS verification code straight…
notebooklm
Deep research and slide presentation generator using NotebookLM MCP. Performs deep research on topics, then generates professional slide presentations with…
prompt-maker
[Hyper] Use this skill when the user asks to create, refactor, optimize, or evaluate a reusable prompt, role/system/agent prompt, prompt template, prompt pack,…
plugin-creator
Create, validate, and publish Claude Code plugins and marketplaces. Use this skill when building plugins with commands, agents, hooks, MCP servers, or skills.
margin-management
Monitor the margin-living strategy from the live DB snapshot. Refreshes the local database first, then reads margin balance, interest costs, dividend coverage…
ui-skills
Opinionated constraints for building better interfaces with agents.
crank
Front door to the crank design pipeline — routes the ask to brainstorm, spec, or plan and runs that phase.
onboarding
Agent-driven onboarding guide for CircleCI. Walks a user through the full setup journey: account creation, organization selection or creation, GitHub App…
task-delegation
When a subtask should run on a different agent (Codex/Claude/Gemini) → delegate and track cross-agent execution.