Update to CellCog

{
  "description": "AI deep research powered by CellCog. Market research, competitive analysis, investment research, academic research, due diligence, literature reviews with citations, financial analysis, crypto research, news intelligence. Multi-source synthesis across hundreds of sources. #1 on DeepResearch Bench (October 2026).",
  "included_files": [],
  "name": "deep-research-cellcog",
  "skill_md_contents": "---\nname: deep-research-cellcog\ndescription: \"AI deep research powered by CellCog. Market research, competitive analysis, investment research, academic research, due diligence, literature reviews with citations, financial analysis, crypto research, news intelligence. Multi-source synthesis across hundreds of sources. #1 on DeepResearch Bench (October 2026).\"\n---\n# Deep Research - Powered by CellCog\n\n**#1 on DeepResearch Bench (October 2026).** Your AI research analyst for comprehensive, citation-backed research on any topic.\n\nLeaderboard: https://huggingface.co/spaces/muset-ai/DeepResearch-Bench-Leaderboard\n\n## How to Use\n\nUse the CellCog tools from this plugin's connector (`https://cellcog.ai/mcp`). The first time a tool runs, the user signs in with their CellCog account and clicks Approve.\n\n1. `cellcog_chat_create` with the brief as `prompt` (optionally `chat_mode` and `chat_tier`). It returns a chat id at once; the work runs in the background.\n2. Poll `cellcog_get_result` with that `chat_id` about once a minute. While it runs you get progress notes; when `complete` is true you get the final message and file links (valid 30 days), with previews of images and PDF pages.\n3. To iterate, `cellcog_chat_send` into the same chat. For files on the user's computer, open `cellcog_upload` and pass `upload:<upload_id>` in `attachments`; public https links can go in `attachments` directly.\n\nFor files, modes and tiers in depth, read the **cellcog** skill.\n\n---\n\n## What You Can Research\n\n### Competitive Analysis\n\nAnalyze companies against their competitors with structured insights:\n\n- **Company vs. Competitors**: \"Compare Stripe vs Square vs Adyen - market positioning, pricing, features, strengths/weaknesses\"\n- **SWOT Analysis**: \"Create a SWOT analysis for Shopify in the e-commerce platform market\"\n- **Market Positioning**: \"How does Notion position itself against Confluence, Coda, and Obsidian?\"\n- **Feature Comparison**: \"Compare the AI capabilities of Salesforce, HubSpot, and Zoho CRM\"\n\n### Market Research\n\nUnderstand markets, industries, and trends:\n\n- **Industry Analysis**: \"Analyze the electric vehicle market in Europe - size, growth, key players, trends\"\n- **Market Sizing**: \"What's the TAM/SAM/SOM for AI-powered customer service tools in North America?\"\n- **Trend Analysis**: \"What are the emerging trends in sustainable packaging for 2026?\"\n- **Customer Segments**: \"Identify and profile the key customer segments for premium pet food\"\n- **Regulatory Landscape**: \"Research FDA regulations for AI-powered medical devices\"\n\n### Stock & Investment Analysis\n\nFinancial research with data and analysis:\n\n- **Company Fundamentals**: \"Analyze NVIDIA's financials - revenue growth, margins, competitive moat\"\n- **Investment Thesis**: \"Build an investment thesis for Microsoft's AI strategy\"\n- **Sector Analysis**: \"Compare semiconductor stocks - NVDA, AMD, INTC, TSM\"\n- **Risk Assessment**: \"What are the key risks for Tesla investors in 2026?\"\n- **Earnings Analysis**: \"Summarize Apple's Q4 2025 earnings and forward guidance\"\n\n### Academic & Technical Research\n\nDeep dives with proper citations:\n\n- **Literature Review**: \"Research the current state of quantum error correction techniques\"\n- **Technology Deep Dive**: \"Explain transformer architectures and their evolution from attention mechanisms\"\n- **Scientific Topics**: \"What's the latest research on CRISPR gene editing for cancer treatment?\"\n- **Historical Analysis**: \"Research the history and impact of the Bretton Woods system\"\n\n### Due Diligence\n\nComprehensive research for decision-making:\n\n- **Startup Due Diligence**: \"Research [Company Name] - founding team, funding, product, market, competitors\"\n- **Vendor Evaluation**: \"Compare AWS, GCP, and Azure for enterprise AI/ML workloads\"\n- **Partnership Analysis**: \"Research potential risks and benefits of partnering with [Company]\"\n\n---\n\n## Research Output Formats\n\nCellCog can deliver research in multiple formats:\n\n| Format | Best For |\n|--------|----------|\n| **Interactive HTML Report** | Explorable dashboards with charts, expandable sections |\n| **PDF Report** | Shareable, printable professional documents |\n| **Markdown** | Integration into your docs/wikis |\n| **Plain Response** | Quick answers in chat |\n\nSpecify your preferred format in the prompt:\n- \"Create an interactive HTML report on...\"\n- \"Generate a PDF research report analyzing...\"\n- \"Give me a markdown summary of...\"\n\n---\n\n## Choosing Mode & Tier\n\n**Use `chat_mode=\"team\"` — this is exactly what Agent Team exists for.** Deep research is THE Team use case: multi-source synthesis, cross-validation, citation verification, multiple reasoning passes.\n\n| Scenario | Recommended |\n|----------|-------------|\n| Deep research, competitive analysis, market research | `chat_mode=\"team\"` (default tier `\"core\"`) |\n| High-stakes due diligence, institutional-grade analysis | `chat_mode=\"team\", chat_tier=\"max\"` (requires >=2,000 credits) |\n| Quick lookups, simple summaries | `chat_mode=\"agent\"` |\n\nLegacy names `\"agent team\"` / `\"agent team max\"` still work forever (they map to team core / team max).\n\n---\n\n## Research Quality Features\n\n### Citations (On Request)\n\n**Citations are NOT automatic.** CellCog focuses on delivering accurate, well-researched content by default.\n\nIf you need citations:\n- **Explicitly request them**: \"Include citations for all factual claims with source URLs\"\n- **Specify format**: \"Provide citations as footnotes\" or \"Include a references section at the end\"\n- **Indicate placement**: \"Citations inline\" vs \"Citations in appendix\"\n\nWithout explicit citation requests, CellCog prioritizes delivering accurate information efficiently.\n\n### Data Accuracy\nCellCog cross-references multiple sources for financial and statistical data, ensuring accuracy even without explicit citations.\n\n### Structured Analysis\nComplex research is organized with clear sections, executive summaries, and actionable insights.\n\n### Visual Elements\nResearch reports can include:\n- Charts and graphs\n- Comparison tables\n- Timeline visualizations\n- Market maps\n\n---\n\n## Example Research Prompts\n\n**Quick competitive intel:**\n> \"Compare Figma vs Sketch vs Adobe XD for enterprise UI design teams. Focus on collaboration features, pricing, and Figma's position after the Adobe acquisition failed.\"\n\n**Deep market research:**\n> \"Create a comprehensive market research report on the AI coding assistant market. Include market size, growth projections, key players (GitHub Copilot, Cursor, Codeium, etc.), pricing models, and enterprise adoption trends. Deliver as an interactive HTML report.\"\n\n**Investment analysis:**\n> \"Build an investment analysis for Palantir (PLTR). Cover business model, government vs commercial revenue mix, AI product strategy, valuation metrics, and key risks. Include relevant charts.\"\n\n**Academic deep dive:**\n> \"Research the current state of nuclear fusion energy. Cover recent breakthroughs (NIF, ITER, private companies like Commonwealth Fusion), technical challenges remaining, timeline to commercial viability, and investment landscape.\"\n\n---\n\n## Tips for Better Research\n\n1. **Be specific**: \"AI market\" is vague. \"Enterprise AI automation market in healthcare\" is better.\n\n2. **Specify timeframe**: \"Recent\" is ambiguous. \"2025-2026\" or \"last 6 months\" is clearer.\n\n3. **Define scope**: \"Compare everything about X and Y\" leads to bloat. \"Compare X and Y on pricing, features, and market positioning\" is focused.\n\n4. **Request structure**: \"Include executive summary, key findings, and recommendations\" helps organize output.\n\n5. **Mention output format**: \"Deliver as PDF\" or \"Create interactive HTML dashboard\" gets you the right format.\n"
}