Skip to content
Back to skills

Hive Workers Skill

ASecurity

Execute tasks using hive mind orchestration with parallel agents, automatic code review, and documentation updates. Use for feature execution, epic completion, or complex multi-task work.

  • 10 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added May 26, 2026
ai-agentsgodocumentation

Works with

  • mcp

Security analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned May 27, 2026

npx -y skills add smith-horn/product-builder-starter --skill hive-workers-skill --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Hive Workers Skill?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Hive Workers Skill
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/smith-horn-hive-workers-skill/badge)](https://www.skillsdirectory.com/skills/smith-horn-hive-workers-skill)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: "Hive Workers"
version: "1.0.0"
description: "Execute tasks using hive mind orchestration with parallel agents, automatic code review, and documentation updates. Use for feature execution, epic completion, or complex multi-task work."
category: orchestration
tags:
  - hive-mind
  - orchestration
  - parallel-execution
  - multi-agent
author: Smith Horn
triggers:
  keywords:
    - execute with hive mind
    - run phase with hive mind
    - execute this epic
    - orchestrate these tasks
    - parallel execution with review
  explicit:
    - /hive-workers
composes:
  - governance
  - worktree-manager
  - linear
---

# Hive Workers Skill

Orchestrates complex task execution using ruflo hive mind with automatic code review and documentation updates.

## Quick Start

```
0. EXPLORE: Search codebase for existing implementations (MANDATORY)
1. Read the task or issue
2. Initialize hive mind: swarm_init({ topology: "hierarchical" })
3. Create todos: TodoWrite with all tasks
4. Execute in parallel where possible
5. Run code review with Task agent
6. Fix any "Must Fix" items
7. Run governance audit
8. Create ADR if architectural decision
9. Update project status
10. Generate sprint report
11. Cleanup: swarm_destroy, mark issues done
```

## Execution

When triggered, **immediately**:

1. Read `agent-prompt.md` from this skill's directory (`./agent-prompt.md`)
2. Spawn a single Task with `subagent_type: "general-purpose"` passing the agent-prompt content as the prompt
3. Include in the prompt: the user's request, current working directory, and any arguments passed
4. Wait for the agent to complete
5. Present the agent's summary to the user

## Sub-Documentation

| Document | Contents |
|----------|----------|
| [agent-prompt.md](agent-prompt.md) | Full execution workflow, phase details, checklists |
| [context-persistence.md](context-persistence.md) | Maintaining context across sessions for long-running tasks |
| [CHEATSHEET.md](CHEATSHEET.md) | Quick reference for common operations |
| [templates/](templates/) | Workflow templates for task execution |

## Related Skills

- [governance](../governance/SKILL.md) - Standards enforcement
- [worktree-manager](../worktree-manager/SKILL.md) - Parallel development

## Prerequisites

- ruflo configured (`claude mcp add ruflo -- npx ruflo@v3alpha mcp start`)
- Linear MCP (optional, for issue tracking)

For full execution details, see [agent-prompt.md](agent-prompt.md).

## Changelog

### v1.0.0 (2026-03)
- Initial public release
- 11-step hive mind execution workflow
- ruflo MCP integration (`swarm_init`, `agent_spawn`, `task_orchestrate`, `swarm_destroy`)
- Automatic governance audit after execution
- Context persistence across sessions (`context-persistence.md`)
- Workflow templates for common task types

Files in this skill

  • CHEATSHEET.md2.7 KB
  • SKILL.md2.7 KB
  • agent-prompt.md11.7 KB
  • context-persistence.md5.5 KB
  • templates/workflow-template.md1.9 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.