AGENT SKILL

hivefiver_mcp_research_loop

Run iterative MCP-backed research with provider readiness checks, confidence scoring, contradiction control, and fallback governance.

License 许可
MIT
最近更新
2026-09-30
Stars
★ 9
Forks
0

01 前言 Front Matter

name
hivefiver_mcp_research_loop
description
Run iterative MCP-backed research with provider readiness checks, confidence scoring, contradiction control, and fallback governance.

02 资源文件 4

03 SKILL.md 正文

HiveFiver MCP Research Loop

Use this skill when planning or architecture decisions require evidence-backed research.

Workflow

  1. Run provider readiness check.
  2. Build query matrix by domain lane.
  3. Retrieve evidence in grounded order:
  • DeepWiki + Repomix (repository grounding)
  • Context7 (official semantics)
  • Tavily + Exa (external corroboration)
  1. Build contradiction register.
  2. Score confidence and emit setup TODOs.

Provider Contract

Required providers:

  • Context7
  • DeepWiki
  • Repomix
  • Tavily
  • Exa (MCP or provider-native)

If any provider is unavailable, continue but downgrade confidence.

Confidence Contract

  • full: corroborated, no critical gaps.
  • partial: usable with non-critical gaps.
  • low: critical gaps or unresolved contradictions.

Retry Contract

  • Validate contradictions up to 10 iterations.
  • At attempt 10, force explicit caveat block.

DeepWiki QA Translation

  • Use transformed context layers for control.
  • Keep output structure stable.
  • Treat TODO/task updates as first-class state.

References

  • references/provider-matrix.md

Template

  • templates/evidence-table.md

Scripts

  • scripts/check-mcp-readiness.mjs
  • scripts/score-confidence.sh

04 同仓库更多 Skills

LongLeo287
LongLeo287/OmniClaw

UI-UX Pro Max

Advanced UI/UX analysis and generation skills with data-driven patterns. Python scripts (core.py, search.py) for systematic UI pattern extraction, design system generation, and component search from curated data sources.

设计师数据分析师视觉设计Skill与智能体开发
★ 9
LongLeo287
LongLeo287/OmniClaw

shadcn-ui

Expert guidance for integrating and building applications with shadcn/ui components, including component discovery, installation, customization, and best practices.

设计师
★ 9
LongLeo287
LongLeo287/OmniClaw

zustand_store_ts

Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state/action separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.

前端开发
★ 9
LongLeo287
LongLeo287/OmniClaw

zustand

Zustand state management guide. Use when working with store code (src/store/**), implementing actions, managing state, or creating slices. Triggers on Zustand store development, state management questions, or action implementation.

★ 9
LongLeo287
LongLeo287/OmniClaw

youtube_summarizer

Automatically fetch YouTube video transcripts, generate structured summaries, and send full transcripts to messaging platforms. Detects YouTube URLs and provides metadata, key insights, and downloadable transcripts.

图像与多媒体Skill与智能体开发
★ 9
LongLeo287
LongLeo287/OmniClaw

youtube_clipper

YouTube 视频智能剪辑工具。下载视频和字幕,AI 分析生成精细章节(几分钟级别), 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频,并生成总结文案。 使用场景:当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词:视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video

★ 9