orchestrator
Intelligent system orchestration for complex tasks using MCP and Pi Agent.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-02 00:09
Agents & models
25,485 results
senior-prompt-engineer
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement…
setup-agents-md
Generate a high-quality, repo-specific AGENTS.md file that tells AI agents how to work effectively in a repository. Reads the actual repo to extract commands,…
higgsfield-stack
Use when the user mentions the Higgsfield CLI (binaries `higgsfield` / `higgs` / `hf`, `higgsfield auth login`, `higgsfield generate create`, `higgsfield…
gitbutler-multi-agent
This skill should be used when coordinating multiple AI agents working concurrently, handling agent handoffs, transferring commits between agents, or when…
codex-async-followup
Schedule follow-ups in Codex App for long asynchronous waits when no independent work remains and no existing Goal covers the wait; resume work when the…
configure-mcp-server
Configure MCP (Model Context Protocol) servers for Claude Code and Claude Desktop. Covers mcptools setup, Hugging Face integration, WSL path handling, and…
write-claude-md
Create an effective CLAUDE.md file that provides project-specific instructions to AI coding assistants. Covers structure, common sections, do/don't patterns,…
multi-agent
Build multi-agent systems - orchestration, coordination, workflows, and distributed architectures
tizen-app-scaffold
Generates secure Tizen app projects (native/web/.NET) with privilege declarations, SMACK labels, and secure storage templates pre-configured.
avatar-keyframe-video
Create continuous keyframes from visual references of cosmic manifestation, giant projections of the same origin, or a character's power display, then use user-selected or available image-to-video tools to generate, review, and composite the action video in segments, without being tied to a finished-film platform. Suitable for the true body and the manifestation in the same frame, domain expansion, consolidation, and synchronized attacks; not responsible for adapting an entire novel or ordinary image carousels.
saizeriya-cli
Operate the saizeriya.js command-line interface on behalf of a user. Use when the user wants an AI agent to start or resume a Saizeriya mobile-ordering…
auditing-warehouse-source-coverage
Audit already-implemented Data warehouse import sources for endpoints, schemas, and tables the vendor's API offers but we never wired up. Use when asked…
remembering-conversations
Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
sharing-skills
Contribute skills back to upstream via branch and PR
testing-skills-with-subagents
RED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes
using-skills
Skills wiki intro - mandatory workflows, search tool, brainstorming triggers
shopify-dev-mcp
Routes Shopify Dev MCP lookups for surfaces the bundled Shopify skills don't cover. TRIGGER when: user needs docs or GraphQL for Storefront API, customer,…
internal-comms
A set of resources to help me write all kinds of internal communications using the formats the company prefers. Whenever asked to write some sort of internal communication (status report, leadership update, 3P update, company newsletter, FAQ, incident report, project update, etc.), Claude should use this skill.
strategy-ranking-sniper
Use when the user asks about SOL ranking sniper, Solana top token sniping, trending token bot, ranking-based auto-trading, 排行榜狙击, SOL sniper bot, momentum…
nav-compact
Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when…
nav-multi
DEPRECATED. Multi-Claude shell orchestration is superseded by native Claude Code Workflows. Auto-invokes on "run multi-agent workflow", "parallel agents for",…
sliced-dev
A vertical thin-slice step-by-step development process for medium-to-large coding tasks, supporting resuming dev-plans, cross-context recovery, subagent context isolation implementation, independent review-package, per-claim evidence closed loop / close-check, as well as high-risk changes such as requests contracts, routing, builds, and CI.
qveris
Search for and execute third-party API tools via the QVeris MCP server, then generate production code that calls the QVeris REST API for tasks like fetching…