MCP App StoreMCP App Store
from agent-teams-playbook108
A cross-platform playbook for designing and running multi-agent teams: six-stage workflow, fallback chains, scenario decision trees, and quality gates for agent
This playbook codifies how to plan, discover, and run multi-agent teams across different runtimes (Claude Code, Codex, OpenClaw, Cursor). It provides a enforced six-stage workflow (planning, discovery, team design, parallel execution, quality gates, delivery), a three-step skill fallback chain, and scenario-based guidance for when to use simple prompts vs. full team orchestration. The document is prescriptive about transparency, downgrade paths, and verification steps so agents behave honestly about platform capabilities.
Use when a user requests multi-agent coordination, team orchestration, parallel processing, or when tasks would benefit from role-based parallelism (code review at scale, multi-angle research, large data processing). Also useful when mapping Claude Code concepts to platforms that lack identical primitives—this playbook specifies downgrade behavior.
Best for orchestrator-capable agents that can spawn subagents or manage parallel tasks (Claude Code, platform orchestrators, OpenClaw with workspace tasking). Agents that cannot spawn true subagents should follow the playbook's downgrade paths (main-thread staged execution).
This skill has not been reviewed by our automated audit pipeline yet.
ds-fix — data-science mid-analysis fixer
Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.
ArcKit Architecture Conformance
Run a systematic architecture conformance assessment that compares ADRs and principles against HLD/DLD artifacts to surface drift, violations, and technical deb
Make Scenario Creator
Assist with creating and validating 'make' scenario creator workflows for business automation: generate configurations, produce code, and recommend best practic
Ideogram Core Workflow — Edit, Remix, Upscale, Describe, Reframe
Image editing and image-to-image workflows for Ideogram: inpainting (Magic Fill), style remix, upscaling, image description, and reframing for new aspect ratios
Zero Tech Debt
Refactor features toward the intended architecture: remove legacy cruft and simplify code to reduce long-term operational cost.
SWE-AF — Autonomous Software Engineering Fleet
Orchestrates a coordinated multi-agent engineering workflow to plan, implement, test, and merge production-grade changes across single or multiple repositories.
Issue Triage & PR Review
Autonomously triage GitHub issues, submit fixes as PRs, and perform adversarial PR reviews to find security and quality problems.
Recursive Mode
Orchestrates recursive repository workflows: phased runs, locks, audits, and durable memory updates for long-running agentic tasks.