ai-strategy-researcher
Skill0 starsChanged 7 months agoMITView on GitHub
Research and generate comprehensive AI business strategy reports as Word documents. Covers market signals, VC theses, vertical analysis, competitive landscape, unit economics, and operational playbooks. Use when the user wants AI market intelligence, strategy analysis, or business planning documents.
- Installs packages
In this repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-browserSkill
- presentationSkill
- time-skillSkill
- time-tokyoSkill
- weather-fetcherSkill
- weather-fetcher-tokyoSkill
- weather-svg-creatorSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 50
Always search these authoritative sources:
- Very specific: line 67
After research is complete, generate a Word document using python-docx:
- Very specific: line 86
Use Calibri font, Pt(11) body, colored headings
- Distinctive: line 90
All references include source name, article title, URL, and date
- Distinctive: line 107
Before delivering the document, verify:
- Distinctive: line 120
Always run parallel WebSearch calls where possible to minimize research time
- Distinctive: line 121
Prefer primary sources (VC blogs, company announcements) over news aggregators
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AI Strategy Researcher Skill
Research AI market signals and generate comprehensive business strategy documents as Word (.docx) files.
Task
Given a topic, vertical, or strategic question, conduct deep research across multiple sources and produce a professional Word document with full references.
Research Framework
Execute research in this order, running parallel searches where possible:
Phase 1: Market Signals (parallel searches)
- VC Theses — Search for latest investment theses from Sequoia, Emergence Capital, a16z, Bessemer, Y Combinator related to the topic
- Major Moves — Search for recent fundraises, acquisitions, JVs, and strategic partnerships (OpenAI, Anthropic, Google, Microsoft)
- Market Sizing — Search for TAM/SAM estimates from analyst reports, investor decks, and industry publications
Phase 2: Competitive Intelligence (parallel searches)
- Proof Points — Search for companies already winning in the space (ARR, valuation, growth metrics)
- Competitive Landscape — Map incumbents, startups, and model providers entering the space
- Failure Analysis — Search for companies that failed or pivoted, and why
Phase 3: Operational Intelligence (parallel searches)
- Unit Economics — Gross margins, revenue per employee, pricing models, COGS structure
- Go-to-Market — How successful companies acquired customers, partnership strategies
- Playbooks — Operational frameworks from VCs and successful founders
Phase 4: Framework Application
- Apply Sequoia's Copilot vs. Autopilot framework to the topic
- Apply Emergence Capital's Intelligence vs. Judgement framework to identify AI readiness
- Identify the Mirage PMF risk specific to this vertical/topic
- Define a North Star Metric appropriate to the vertical
Key Sources to Check
Always search these authoritative sources:
| Source | What to look for |
| Sequoia Capital blog | "Services: The New Software" thesis, vertical analysis |
| Emergence Capital | AI-Native Services Playbook, portfolio companies |
| Y Combinator | Request for Startups, batch companies in the space |
| Bessemer Venture Partners | Cloud/AI indices, pricing playbooks |
| a16z | Market maps, industry analyses |
| OpenAI blog | Deployment Company updates, Frontier Alliances |
| Anthropic blog | Enterprise JV updates, partner announcements |
| TechCrunch | Funding rounds, startup coverage |
| Fortune | Executive interviews, strategic analysis |
| Bloomberg | Financial data, deal structures |
Document Generation
After research is complete, generate a Word document using python-docx:
Required Sections
- Cover Page — Title, subtitle, date, source attribution
- Table of Contents — All sections and subsections
- Executive Summary — 5 key findings with market signals
- Market Signal Analysis — What just happened and why it matters
- Macro Thesis — VC frameworks applied to the topic
- Market Sizing & Vertical Analysis — TAM with tables
- Proof Points — Companies already winning with metrics
- Operational Playbook — How to build/execute
- Unit Economics — Margins, pricing, key metrics
- Competitive Moats — Defensibility framework
- Risk Analysis — Mirage PMF and failure modes
- Strategic Framework — Decision matrix for the user
- Competitive Landscape — Positioning map
- References & Sources — ALL URLs organized by category
Document Standards
- Use
Calibrifont,Pt(11)body, colored headings - Professional tables using
Light Grid Accent 1style - Block quotes for key insights (italic, indented)
- Bullet points with bold prefixes for scanability
- All references include source name, article title, URL, and date
- Minimum 30 referenced URLs across categories
File Output
- Save to project root as:
{topic-slug}-strategy-{month}{year}.docx - Example:
ai-native-insurance-strategy-may2026.docx - Clean up the Python generator script after document creation
Python Dependencies
The document generator requires python-docx. Install if needed:
pip install python-docxQuality Checklist
Before delivering the document, verify:
- All 13 sections present
- 15+ formatted tables with data
- 30+ referenced URLs with source attribution
- Copilot vs. Autopilot framework applied
- Intelligence vs. Judgement analysis included
- Mirage PMF risks identified
- North star metric defined
- Cover page with date and source attribution
- Professional formatting throughout
Notes
- Always run parallel WebSearch calls where possible to minimize research time
- Prefer primary sources (VC blogs, company announcements) over news aggregators
- Include both successful and failed companies for balanced analysis
- Convert all relative dates to absolute dates in the document
- The document should be investor-ready and presentable to stakeholders
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

