Skills for startup founders by lool ventures.
A Claude Cowork plugin that gives founders four AI-powered coaching agents: market sizing, pitch deck review, financial model review, and IC simulation. Each agent follows a structured, script-backed workflow to produce analysis that holds up under investor scrutiny.
Builds credible TAM/SAM/SOM analysis — the kind that earns investor trust rather than raising eyebrows.
What it does:
- Calculates TAM/SAM/SOM using top-down, bottom-up, or both approaches
- Validates market claims against external sources (analyst reports, government data, industry stats)
- Stress-tests assumptions with sensitivity analysis and confidence-based range widening
- Runs a 22-item self-check against common market sizing pitfalls
- Assembles a final report with cross-artifact consistency validation
What to provide: A pitch deck, financial model, market data, or just describe the business (product, target customer, geography, pricing). The agent will research external sources to validate and build the estimate.
What you get back: A structured report with TAM/SAM/SOM figures (top-down and/or bottom-up), sensitivity ranges showing best/worst case, a scored self-check against common pitfalls, and coaching commentary on what will hold up in diligence.
Example prompts:
- "Here's the deck for Acme Corp -- can you validate their market sizing?"
- "We're looking at a fintech startup in the payments space targeting SMBs in Europe. What's the market look like?"
- "What happens to the market sizing if the customer count is 30% lower than estimated?"
Full workflow details:
founder-skills/skills/market-sizing/SKILL.md
Reviews pitch decks against 2026 investor best practices, calibrated by stage (pre-seed, seed, Series A).
What it does:
- Scores 35 criteria across 7 categories (pass/fail/warn/not_applicable)
- Detects fundraising stage and applies stage-specific expectations
- Reviews each slide from the investor's perspective with specific, actionable feedback
- Grounds every recommendation in a named best-practice principle
- Assembles a scored report with overall deck readiness assessment
What to provide: A pitch deck in any format — PDF, PowerPoint, markdown, or text descriptions of your slides.
What you get back: A slide-by-slide review from the investor's perspective, a scored checklist (35 criteria across 7 categories), an overall readiness rating (strong/solid/needs work/major revision), and coaching on the highest-leverage changes to make before sending.
Example prompts:
- "Here's our seed deck -- can you review it?"
- "Is this deck ready to send to investors? We're raising a pre-seed round."
- "I have 10 slides: Slide 1 is our company intro with the tagline 'AI-powered compliance for fintechs'..."
Full workflow details:
founder-skills/skills/deck-review/SKILL.md
Simulates a realistic VC Investment Committee discussion with three partner archetypes debating a startup's merits, concerns, and deal terms -- scored across 28 dimensions.
What it does:
- Simulates three distinct partner perspectives: The Visionary (markets/timing), The Operator (execution/GTM), The Analyst (unit economics/financials)
- Runs partner assessments independently via sub-agents for genuine diversity of perspective
- Scores 28 dimensions across 7 categories (team, market, product, business model, financials, risk, fund fit)
- Checks portfolio conflicts against the fund's existing investments
- Supports fund-specific mode with WebSearch-backed fund research
- Imports prior market-sizing and deck-review artifacts for grounded analysis
What to provide: A pitch deck, financial model, data room contents, or a verbal description of the business. Optionally, name a specific fund to simulate (e.g. "How would Sequoia evaluate us?"). Works best after running market sizing and/or deck review first — those artifacts are imported automatically.
What you get back: A simulated IC debate with three distinct partner voices, a conviction score across 28 dimensions, a consensus verdict (invest/more diligence/pass/hard pass), portfolio conflict analysis, and coaching on exactly what to prepare before a real IC meeting.
Example prompts:
- "Simulate an IC discussion for our startup"
- "How would Sequoia's partners discuss our company?"
- "I just did market sizing and a deck review -- now simulate the IC"
Full workflow details:
founder-skills/skills/ic-sim/SKILL.md
Reviews startup financial models for investor readiness — validating structure, unit economics, runway, and metrics against stage-appropriate standards.
What it does:
- Scores 46 criteria across 7 categories with profile-based auto-gating by stage, geography, and sector
- Computes and benchmarks 11 unit economics metrics against stage-appropriate targets
- Stress-tests runway under base, slow-growth, and crisis scenarios with decision-point analysis
- Supports Excel (.xlsx), CSV, Google Sheets exports, pitch decks, and conversational input
- Assembles a final report with cross-artifact consistency validation
What to provide: A financial model in any format — Excel spreadsheet, CSV, Google Sheets export, financial slides from a deck, or just describe the numbers in conversation. The agent adapts its analysis depth to the format provided.
What you get back: A scored checklist (46 criteria across 7 categories), benchmarked unit economics with ratings, multi-scenario runway projections with cash-out dates and decision points, an overall readiness rating (strong/solid/needs work/major revision), and coaching on the highest-leverage improvements.
Example prompts:
- "Review my financial model" (with an Excel file attached)
- "Here are our projections from the deck -- can you validate the unit economics?"
- "We're burning $80K/mo with $1.2M in the bank, growing 15% MoM. How does our runway look?"
Full workflow details:
founder-skills/skills/financial-model-review/SKILL.md
- Open Customize in the sidebar
- Click + on the Personal Plugins list
- Choose Browse Plugins
- Switch to the Personal tab
- Click the + button
- Choose Add marketplace from GitHub
- Enter
lool-ventures/founder-skills - Sync, then Install
claude plugin marketplace add lool-ventures/founder-skills
claude plugin install founder-skills@lool-founder-skills
Once installed, the agents activate automatically when you ask about market sizing, deck review, financial model review, or IC simulation. No additional configuration required.
Manus adopted the Agent Skills standard in January 2026 and can read SKILL.md files and execute bundled scripts. The founder-skills Python scripts are already portable (pure CLI, JSON in/out), but the workflow instructions in our SKILL.md files are currently Claude-native (sub-agent orchestration, plugin hooks, path resolution). We plan to add Manus-compatible skill wrappers once the platform's skill discovery and marketplace layer stabilizes.
OpenAI has adopted the skills standard originally introduced by Anthropic, and skills now work across ChatGPT, Codex CLI, and the OpenAI API. The ecosystem is converging quickly but the plugin/marketplace layer is still a moving target. Once the dust settles, we plan to add first-class support for ChatGPT and Codex as well.
Requires Python 3.12+ and uv. Quick start:
git clone https://github.com/lool-ventures/founder-skills.git
cd founder-skills
uv sync --extra dev # install dependencies + dev tools
uv run pytest # run testsSee CONTRIBUTING.md for the full development workflow.
Plugin not updating after a new release? As of Feb 2026 (Claude Desktop for Mac v1.1.3963), the plugin cache does not always refresh when a marketplace is updated. This is a known platform issue. To force an update:
- Enable auto-update:
/plugin> Marketplaces > selectlool-founder-skills> "Enable auto-update" - If that doesn't work, clear the cache and reinstall:
Then restart Claude Code/Cowork and reinstall the plugin.
rm -rf ~/.claude/plugins/cache/lool-founder-skills
In Cowork, if the plugin shows stale data after updating, you may need to fully remove and re-add the marketplace from the Plugins sidebar.
This plugin runs entirely inside your local Claude session. No data is collected, transmitted, or shared with lool ventures.
We welcome contributions — new skills, improvements to existing ones, and bug fixes. See CONTRIBUTING.md to get started and DESIGN.md for the principles behind how skills are built.
- Bug reports and feature requests — GitHub Issues
- Questions and discussion — GitHub Discussions
- Security vulnerabilities — Report privately (see SECURITY.md)
- About lool ventures — lool.vc