manager-getting-started

Other Community

Repo stars 0
Author repo skills-registry

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Getting started with Manager — the 48-tool multi-AI orchestrator. Use when: delegating code tasks to Claude Code/Codex/Gemini, r…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “What Manager Is”, “Key Tools”, “Common Patterns”, “Anti-Patterns”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name manager-getting-started directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “What Manager Is / Key Tools / Common Patterns” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / shell-exec; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

What Manager Is

A single MCP server (manager.exe) with 48 tools for multi-AI orchestration. It routes tasks to Claude Code, Codex, Gemini CLI, and GPT, with parallel execution, workflow chaining, and learned routing patterns.

Category	Key Tools	What It Does
Task lifecycle	task_submit, task_status, task_output, task_poll, task_list	Submit, monitor, and retrieve AI task results
Routing	task_route, task_decompose, task_explain	Smart backend selection and task breakdown
Parallel	task_run_parallel	Concurrent multi-backend execution with dependencies
Workflows	workflow_run	Multi-step chains with retry and escalation
Templates	template_save, template_list, template_run	Reusable workflow patterns
Sessions	session_start, session_send, session_list	Interactive AI sessions
Direct access	codex_exec, codex_review, gemini_direct	Call specific backends directly
Analytics	get_analytics, run_analyzer	Execution stats and pattern analysis
Loaves	create_loaf, loaf_update, loaf_status, loaf_close	Multi-step tracked jobs
Notifications	notify	Desktop notifications for task events

Key Tools

I want to...	Use
Delegate a coding task	task_submit(backend="claude_code", prompt="...")
Let Manager pick the best AI	task_submit(auto_route=true, prompt="...")
Run tasks in parallel	task_run_parallel(steps=[...])
Chain steps with retry	workflow_run(steps=[...])
Save a reusable pattern	template_save(name="...", steps=[...])
Check what backend to use	task_route(prompt="...")
Start interactive session	session_start(backend="claude_code")
Get execution stats	get_analytics

Common Patterns

Quick delegation: manager:task_submit(backend="claude_code", prompt="Add error handling to src/main.rs", working_dir="C:/project")

Poll for completion: manager:task_poll(task_id="abc-123", timeout=60)

Parallel review: manager:task_run_parallel(steps=[ {id: "frontend", backend: "claude_code", prompt: "Review src/ui/", parallel_group: "review"}, {id: "backend", backend: "codex", prompt: "Review src/api/", parallel_group: "review"} ])

Anti-Patterns

Don't poll in a tight loop — use task_poll with a timeout instead of repeated task_status
Don't hardcode backends — use auto_route or task_route to let Manager learn which backend works best

Source: AIWander/manager — distributed by TomeVault.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: Other
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @tomevault-io · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: No requirement detected
Detected OS requirements: Unspecified
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Write / modify
Shell exec
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview manager-getting-started.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

## What Manager Is

A single MCP server (manager.exe) with 48 tools for multi-AI orchestration. It routes tasks to Claude Code, Codex, Gemini CLI, and GPT, with parallel execution, workflow chaining, and learned routing patterns.

| Category | Key Tools | What It Does |
|----------|-----------|-------------|
| Task lifecycle | task_submit, task_status, task_output, task_poll, task_list | Submit, monitor, and retrieve AI task results |
| Routing | task_route, task_decompose, task_explain | Smart backend selection and task breakdown |
| Parallel | task_run_parallel | Concurrent multi-backend execution with dependencies |
| Workflows | workflow_run | Multi-step chains with retry and escalation |
| Templates | template_save, template_list, template_run | Reusable workflow patterns |
| Sessions | session_start, session_send, session_list | Interactive AI sessions |
| Direct access | codex_exec, codex_review, gemini_direct | Call specific backends directly |
| Analytics | get_analytics, run_analyzer | Execution stats and pattern analysis |
| Loaves | create_loaf, loaf_update, loaf_status, loaf_close | Multi-step tracked jobs |
| Notifications | notify | Desktop notifications for task events |

## Key Tools

| I want to... | Use |
|--------------|-----|
| Delegate a coding task | task_submit(backend="claude_code", prompt="...") |
| Let Manager pick the best AI | task_submit(auto_route=true, prompt="...") |
| Run tasks in parallel | task_run_parallel(steps=[...]) |
| Chain steps with retry | workflow_run(steps=[...]) |
| Save a reusable pattern | template_save(name="...", steps=[...]) |
| Check what backend to use | task_route(prompt="...") |
| Start interactive session | session_start(backend="claude_code") |
| Get execution stats | get_analytics |

## Common Patterns

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> What Manager Is → Key Tools → Common Patterns → Anti-Patterns
terms    -> Quick delegation · Poll for completion · Parallel review · A single MCP server (manager.exe) with 48 tools for multi-AI orchestration. · | I want to... · --- > Source: [AIWander/manager](https://github.com/AIWander/manager) — distributed by [TomeVault](https://tomevault.io).
files/cmd -> src/main.rs · src/ui · src/api · AIWander/manager · github.com/AIWander/manager
body sha256 -> b23e07f832e3