agentleFS
Sign inStart free
HelloRuruHelloRuru/claude-teams-go/skill/SKILL.md

skill

Skill1 starsChanged 8 months agoMITView on GitHub

Run multi-agent team workflows using your existing Claude Code subscription. No extra tools, no extra cost -- just Markdown blueprints and Claude Code Hooks. One command dispatches a team of specialized agents that research, draft, assemble, review, and polish your deliverable through a structured pipeline. The Conductor breaks down the requirement and dispatches Task Agents. Two Assemblers then create competing drafts -- one emotional, one structural. The Judge merges the best of both versions and runs a quality checklist. The…

62 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ai-slop-cleaner, ralplan and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Jurel89Skill

    ai-slop-cleaner

    Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

    Also in 5 projects that use this

  • ibahgatSkill

    ralplan

    Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.

    Also in 5 projects that use this

  • ibahgatSkill

    hud

    Control omi visual HUD profile and keep status output readable in normal, compact, or hidden mode.

    Also in 5 projects that use this

  • Jurel89Skill

    ultraqa

    QA cycling loop — build/lint/test, fix, retry up to 5 cycles

    Also in 3 projects that use this

  • LucasCooperBeySkill

    visual-verdict

    Structured visual QA verdict for screenshot-to-reference comparisons. Returns JSON scores driving edit iterations. Use after any UI implementation to verify visual fidelity.

    Also in 3 projects that use this

  • Yeachan-HeoSkill

    ultragoal

    Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 45 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run multi-agent team workflows using your existing Claude Code subscription.

    line 5
  2. Very specific:

    Run /teams to launch a blueprint workflow.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 45 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Claude Teams Go

What It Does

Run multi-agent team workflows using your existing Claude Code subscription. No extra tools, no extra cost -- just Markdown blueprints and Claude Code Hooks. One command dispatches a team of specialized agents that research, draft, assemble, review, and polish your deliverable through a structured pipeline.

Core Concept

User Request
    |
Conductor (Claude Code main agent)
    |-- clarifies requirements
    |-- selects blueprint
    |-- dispatches Task Agents
    v
Task Agents (parallel subagents)
    |
    v
Assembler A (Empath) + Assembler B (Architect)  [parallel]
    |
    v
Judge (Checker) -- merge + quality checklist
    |
    v
Polisher -- refine + deliver
    |
    v
User <-> Polisher negotiation

The Conductor breaks down the requirement and dispatches Task Agents. Two Assemblers then create competing drafts -- one emotional, one structural. The Judge merges the best of both versions and runs a quality checklist. The Polisher applies final refinements and delivers to the user.

File Structure

roles/              Resident role personas (Empath, Architect, Judge, Polisher)
blueprints/         Workflow definitions -- each blueprint = one team configuration
  _template.md      Blank blueprint for creating new ones
hooks/              teams-router.js -- detects blueprint triggers on user input
commands/           Slash commands (/teams, /blueprint, /roles) in EN and ZH

Quick Start

  1. Copy roles/ and blueprints/ into your project root.
  2. Install the hook: copy hooks/teams-router.js to .claude/hooks/.
  3. Copy commands/ to .claude/commands/.
  4. Run /teams to launch a blueprint workflow.

That's it. No dependencies to install.

Commands

CommandAliasWhat It Does
/teams/組隊Launch a blueprint workflow
/blueprint/規劃List, create, or edit blueprints
/roles/角色設定View or modify resident role personas

Blueprint Format

Each blueprint is a Markdown file with these sections:

SectionPurpose
MetaName, trigger words, one-line description
AgentsTask Agent table -- roles and memory references (tasks assigned at runtime)
FlowExecution order: parallel, then stages
Roles MemoryOptional memory file injection for resident roles
ChecklistQuality gates the Judge must verify before passing
On FailRetry behavior when the Judge rejects a deliverable

See blueprints/_template.md for the full template.

Memory Integration

Works standalone, but pairs with claude-memory-engine for richer context.

ConditionBehavior
Memory engine installedReads blueprint memory fields; injects memory into subagent prompts
Memory engine not installedSkips injection; subagents rely on blueprint task descriptions alone

Resident Roles

Four permanent roles that stay consistent across every workflow:

RoleCodenameFocus
Assembler AEmpathEmotional resonance, storytelling, rhythm -- finds the warmest angle
Assembler BArchitectStructure, keyword placement, evidence -- builds the most persuasive frame
CheckerJudgeMerges both versions, decides the empath/architect ratio, runs quality checklist
PolisherPolisherFinal refinement, AI-trace removal, and sole point of contact with the user

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free