Research

阅读助手 - 贴链接或粘贴文字，自动提炼4点：主旨/论据/行动/疑问，不用读全文。支持网页抓取和本地文本

Web search and content extraction powered by SkillBoss API Hub.

持续学习 Agent - 知识沉淀和经验固化框架。支持学习记录、快速索引、自我修复、经验→模型转化。包含完整模板、索引系统、SOP 流程。让 AI Agent 持续进化，每天进步一点点。

This skill should be used when the user asks to "analyze competitors", "competitor SEO", "who ranks for", "competitive analysis", "what are my competitors doing", "what are they doing differently", "why do they rank higher", or "spy on competitor SEO". Analyzes competitor SEO and GEO strategies including their ranking keywords, content approaches, backlink profiles, and AI citation patterns. Reveals opportunities to outperform competition. For content-focused gap analysis, see content-gap-ana...

You are a professional business analyst, skilled in writing various industry research reports, business insights, consulting analyses, company research reports, competitive analysis, user research, market analysis, and more.## General InstructionsYou must use references and sources to support your arguments, but all cited literature or materials must appear in logically relevant parts of the te...

Jarvis-Video-STT - 批量视频语音转文字工具。 基于Faster-Whisper，支持多进程并行、进度条、汇总报告。 **触发场景**： - 用户需要将视频中的语音转换为文字/字幕 - 批量处理多个视频 - 需要生成SRT字幕或纯文本 - 需要处理报告查看结果统计 **使用方式**： 1. 确认已安装依赖: pip install faster-whisper tqdm 2. 确认ffmpeg已安装 3. 执行命令或调用主脚本 **支持格式**：MP4, MKV, AVI, MOV **输出**： - .srt 文件：带时间戳的字幕格式 - .txt 文件：纯文本全文 - report.json：机器可读的汇总报告 - report.md：人类可读的汇总报告

Free DNS and email security analysis via IntoDNS.ai: DNSSEC, SPF, DKIM, DMARC, MTA-STS, BIMI, SMTP STARTTLS, FCrDNS, blacklists, sender requirements, report snapshots, and citation guidance.

信息调研报告自动化工作流。一键完成：多源搜索 → 深度挖掘 → 政府风格 DOCX 报告生成 → 邮件发送。

Use when improving an agent's own memory, skills, prompts, runtime rules, tool policies, AGENTS.md/agent.md files, or when adapting ideas from other agent projects into the current agent.

Complete grant intelligence system for individuals, nonprofits, startups, researchers, and small businesses. Trigger whenever someone needs to find grants, write grant applications, understand eligibility criteria, respond to reviewer feedback, or manage grant compliance. Also triggers on phrases like "find funding for", "apply for a grant", "write a grant proposal", "we need government funding", "what grants are available for", or any scenario where someone is seeking non-dilutive funding fr...

> **[SEO & GEO Skills Library](https://skills.sh/aaron-he-zhu/seo-geo-claude-skills)** · 20 skills for SEO + GEO · Install all: `npx skills add aaron-he-zhu/seo-geo-claude-skills` <details> <summary>Browse all 20 skills</summary> **Research** · [keyword-research](../keyword-research/) · **competitor-analysis** · [serp-analysis](../serp-analysis/) · [content-gap-analysis](../content-gap-analysis/) **Build** · [seo-content-writer](../../build/seo-content-writer/) · [geo-content-optimizer](../.....

Spawn and orchestrate multiple coordinated AI sub-agents to work in parallel on a single complex task. Use when: (1) a task is too large for one agent and should be decomposed into parallel subtasks, (2) you need multiple specialized agents researcher coder reviewer etc working together, (3) running agent councils or debates for decision-making, (4) parallel web research data processing or content generation across multiple workers, (5) any multi-agent orchestration pattern one-shot teams per...

Detect user frustration in prompts and translate charged/emotional language into clear, actionable instructions. Use when user messages contain vague anger ("this is garbage"), compressed expectations ("just fix it"), repeated complaints about the same issue, ALL CAPS, or emotional language that obscures what they actually need done. Critical for finite context windows where misinterpreting a frustrated prompt wastes tokens on the wrong task. Improves over time by logging frustration patterns...

LLM通用证据新鲜度判断技能。根据时间窗和证据时间信息，判断每条证据属于current/background/stale/undated/malformed哪一类。在搜索结果标准化之后、需要区分当前证据与背景证据时使用。触发条件：现实问题/新闻/政策/市场分析、需要降低"把旧材料当新材料"风险、时间敏感型任务。

Your AI think tank. Five domain-expert Fellows debate any idea, decision, or creative work. Three rounds. One verdict that's actually useful.

This skill enables AI agents to help users find, research, and book in-network doctors through Zocdoc.com. It surfaces real-time appointment availability, verified patient reviews, accepted insurance information, and detailed provider profiles sourced from Zocdoc.com, and directs users to Zocdoc.com to securely complete booking.

LLM通用证据清洗技能。将原始搜索结果、网页片段、OCR残片等原始材料清洗为可用证据，减少脏输入、伪实体、重复片段和错域材料对后续判断的污染。在搜索结果返回后、进入freshness判定或叙事生成前使用。触发条件：搜索结果质量差、证据量大但信噪比低、需要标准化证据格式。

You are the EmoCity Analyst � a friendly, plain-language guide to real-time facial signals, powered by EmoPulse. You help users read their current state � stress, mood, and how relaxed or guarded they look � using their camera. You explain what signals *suggest*, never what they *prove*.

Aggregates publicly available Embodied AI and Robotics news from curated sources (robotics media, arXiv, company blogs). Delivers structured briefings on humanoid robots, foundation models, hardware, deployments, and funding with direct links to original articles. Optional module surfaces hot GitHub open-source repos relevant to embodied AI (policies, sim, data, benchmarks).

> Read-only advisory skill for LLM inference energy decisions. > Evidence-first guidance powered by 360+ measured benchmark rows on RTX 4090D, RTX 5090, and A800. **Author**: Hongping Zhang ([@hongping-zh](https://github.com/hongping-zh)) **Version**: v3.0.8 **Skill URL**: https://clawhub.ai/hongping-zh/ecocompute **License**: MIT **Dataset**: [zenodo.org/records/18900289](https://zenodo.org/records/18900289) (collection window: 2025 Q1) ---

Resolve dual-perspective collaboration conflicts by classifying them into 5 types and applying targeted integration strategies. Use when two agents (or an agent and user) have different approaches to the same problem — e.g., qualitative vs. quantitative, strategic vs. tactical, creative vs. analytical. Provides conflict taxonomy, resolution strategies, and a 5-metric dashboard for validation.

Your personal research department. Multi-source synthesis that turns scattered information into actionable intelligence — not just summaries, but insights you can act on.

> 版本：6.0.0 > 描述：领域无关 | 配置驱动 | 数据源自适应 | 三层输出 ---

Deep Research Suite - One command to aggregate, analyze, and synthesize research from multiple sources. Search → Extract → Summarize → Report.