pi-orchestration
Orchestrate multiple AI models (GLM, MiniMax, etc.) as workers using Pi Coding Agent with Claude as coordinator.
What this skill does
# Pi Orchestration
Use Claude as an orchestrator to spawn and coordinate multiple AI model workers (GLM, MiniMax, etc.) via Pi Coding Agent.
## Supported Providers
| Provider | Model | Status |
|----------|-------|--------|
| **GLM** | glm-4.7 | ✅ Working |
| **MiniMax** | MiniMax-M2.1 | ✅ Working |
| OpenAI | gpt-4o, etc. | ✅ Working |
| Anthropic | claude-* | ✅ Working |
## Setup
### 1. GLM (Zhipu AI)
Get API key from [open.bigmodel.cn](https://open.bigmodel.cn/)
```bash
export GLM_API_KEY="your-glm-api-key"
```
### 2. MiniMax
Get API key from [api.minimax.chat](https://api.minimax.chat/)
```bash
export MINIMAX_API_KEY="your-minimax-api-key"
export MINIMAX_GROUP_ID="your-group-id" # Required for MiniMax
```
## Usage
### Direct Commands
```bash
# GLM-4.7
pi --provider glm --model glm-4.7 -p "Your task"
# MiniMax M2.1
pi --provider minimax --model MiniMax-M2.1 -p "Your task"
# Test connectivity
pi --provider glm --model glm-4.7 -p "Say hello"
```
### Orchestration Patterns
Claude (Opus) can spawn these as background workers:
#### Background Worker
```bash
bash workdir:/tmp/task background:true command:"pi --provider glm --model glm-4.7 -p 'Build feature X'"
```
#### Parallel Army (tmux)
```bash
# Create worker sessions
tmux new-session -d -s worker-1
tmux new-session -d -s worker-2
# Dispatch tasks
tmux send-keys -t worker-1 "pi --provider glm --model glm-4.7 -p 'Task 1'" Enter
tmux send-keys -t worker-2 "pi --provider minimax --model MiniMax-M2.1 -p 'Task 2'" Enter
# Check progress
tmux capture-pane -t worker-1 -p
tmux capture-pane -t worker-2 -p
```
#### Map-Reduce Pattern
```bash
# Map: Distribute subtasks to workers
for i in 1 2 3; do
tmux send-keys -t worker-$i "pi --provider glm --model glm-4.7 -p 'Process chunk $i'" Enter
done
# Reduce: Collect and combine results
for i in 1 2 3; do
tmux capture-pane -t worker-$i -p >> /tmp/results.txt
done
```
## Orchestration Script
```bash
# Quick orchestration helper
uv run {baseDir}/scripts/orchestrate.py spawn --provider glm --model glm-4.7 --task "Build a REST API"
uv run {baseDir}/scripts/orchestrate.py status
uv run {baseDir}/scripts/orchestrate.py collect
```
## Best Practices
1. **Task Decomposition**: Break large tasks into independent subtasks
2. **Model Selection**: Use GLM for Chinese content, MiniMax for creative tasks
3. **Error Handling**: Check worker status before collecting results
4. **Resource Management**: Clean up tmux sessions after completion
## Example: Parallel Code Review
```bash
# Claude orchestrates 3 workers to review different files
tmux send-keys -t worker-1 "pi --provider glm -p 'Review auth.py for security issues'" Enter
tmux send-keys -t worker-2 "pi --provider minimax -p 'Review api.py for performance'" Enter
tmux send-keys -t worker-3 "pi --provider glm -p 'Review db.py for SQL injection'" Enter
# Wait and collect
sleep 30
for i in 1 2 3; do
echo "=== Worker $i ===" >> review.md
tmux capture-pane -t worker-$i -p >> review.md
done
```
## Notes
- Pi Coding Agent must be installed: `npm install -g @anthropic/pi-coding-agent`
- GLM and MiniMax have generous free tiers
- Claude acts as coordinator, workers do the heavy lifting
- Combine with process tool for background task management
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.