pi-maestro-flow
Parallel multi-agent orchestration, planning, and persistent project knowledge
All Skills in This Repository (54)
Pure Emerald Level Indicatorsteam-frontend
Coordinate frontend delivery pipelines from requirements analysis through QA.
skill-iter-tune
Run execute-evaluate-improve loops on skill definitions and generated artifacts.
maestro-learn
Guide structured codebase learning through evidence gathering and pattern extraction.
team-adversarial-swarm
Coordinate adversarial ant-colony optimization workflows for multi-agent exploration and scoring.
maestro-spec
Record project constraints and standards from natural-language intent into structured spec entries.
maestro-knowledge
Route natural-language requests to Maestro knowledge lifecycle commands.
scholar-review
Parse reviewer comments and generate structured rebuttal and revision plans.
delegation-check
Validates delegation prompts against agent role definitions for conflicts and missing contracts.
team-swarm
Orchestrate multi-agent swarm exploration with pheromone-guided selection and deterministic update loops.
maestro-merge
Merge session worktree branches into main and synchronize run artifacts.
team-ux-improve
Diagnose and fix UI interaction failures in React and Vue codebases.
scholar-ideation
Formulate research topics into structured plans with literature gap analysis.
Frequently Asked Questions
FAQPage SchemaHow to install pi-maestro-flow?▼
Run `npx skills add catlog22/pi-maestro-flow --all -g -y` in your terminal to install the full skill set globally. Note the suite also requires Node.js 22.19+ and the Pi coding agent runtime.
What does pi-maestro-flow do?▼
It adds multi-agent orchestration to the Pi coding agent: parallel sub-agent dispatch with dependency graphs, plan-before-edit gates, long-running goal loops, and a persistent cross-session knowledge base.
How do I run multiple agents in parallel?▼
Use the teammate tool with a task list; each task can name its own agent role and model, and dependencies between tasks form a DAG that runs in parallel automatically.
Does it keep knowledge between sessions?▼
Yes. A built-in knowledge system stores specs, decisions, and reusable knowhow with semantic search, so future sessions recall prior decisions and conventions automatically.
Can non-coders use pi-maestro-flow?▼
Partially. You describe tasks in plain language and the system routes and executes them, but installing and running it requires a terminal and the Pi runtime, so basic command-line familiarity helps.
Related Repositories in Software Engineering
View All in Software Engineering→openclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core