create-hive-issue
About
This Claude Skill creates detailed GitHub issues using a coordinated multi-worker approach with mprocs. It structures the process into scouting, analysis, and drafting phases, producing a thorough, multi-perspective issue write-up. The workflow is managed through a tasks.json configuration that tracks session status and assigns specific roles to different workers.
Quick Install
Claude Code
Recommended/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/create-hive-issueCopy and paste this command in Claude Code to install this skill
Documentation
Create Hive Issue
Overview
Use mprocs to coordinate multiple workers for a deep issue write-up.
Inputs
- Issue description
Workflow
- Verify
gitandmprocs. - Create
.hive/sessions/<session-id>andtasks.json. - Write queen and worker prompts (scout, analysis, draft).
- Launch mprocs and synthesize a final issue.
tasks.json Template
{
"session": "{SESSION_ID}",
"created": "{ISO_TIMESTAMP}",
"status": "active",
"thread_type": "Hive",
"task_type": "create-hive-issue",
"issue": {"description": "{ISSUE_DESC}"},
"tasks": [
{"id": "scout", "owner": "worker-1", "status": "pending"},
{"id": "analysis", "owner": "worker-2", "status": "pending"},
{"id": "draft", "owner": "worker-3", "status": "pending"}
]
}
Worker Prompt Outline
# Worker - Issue Scout
- Locate relevant files
- Summarize evidence
# Worker - Issue Analysis
- Identify scope and risks
# Worker - Issue Draft
- Write title and body
mprocs Launch
mprocs --config .hive/mprocs.yaml
Output
- Detailed GitHub issue with triage notes
GitHub Repository
Related Skills
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.
cloudflare-turnstile
MetaThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
