agentsclimarketplace

Apify pre seed investors

Skill johnisanerd/claude-skill-pre-seed-investors/apify-pre-seed-investors

Claude/agent skill: stage-filtered investor outreach lists with partner contacts and check sizes. Installs via npx skills add.

Install
npx -y skills add johnisanerd/claude-skill-pre-seed-investors --skill apify-pre-seed-investors

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 20 days oldThe repository was created 20 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Build a fundraising outreach list of pre seed investors with the Apify Startup Investors Data Scraper (johnvc/startup-investors-data-scraper). Filter a curated database of 10,469 firms by investment stage (Pre-Seed, Seed, Series A and beyond), industry focus, firm type, and country, and get investor firms with partner contacts, job titles, emails when available, LinkedIn URLs, and check sizes, ready to load into a CRM or outreach tool. Use when the user wants to find pre seed investors, seed investors, or early stage investors for a raise, build an investor outreach or lead list, find angel investors or VCs for a specific industry and stage, or ask who invests at pre-seed in their space. Research and outreach data only, no investment advice. Pay-per-firm billing, MCP-ready for Claude and other AI agents.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

6.6 KB, ~1.5k tokens by cl100k_base, as published. Nobody here has run it

Pre Seed Investors: Stage-Filtered Outreach Lists

Build an investor outreach list for a raise. Filter a curated database of 10,469 firms to the investors who actually invest at your stage and in your space, and get partner contacts with job titles, emails when available, and check sizes, ready for a CRM.

When to use this skill

  • The user is raising and wants to find pre seed investors, seed investors, or early stage investors.
  • They want an investor lead list scoped to an industry, stage, firm type, or country.
  • They want partner-level contacts (names, titles, LinkedIn, check sizes) for outreach.
  • They ask "who invests at pre-seed in fintech" or "make me a target list for my raise".

Not for: personalized investment advice or intro-making (this collects research and outreach data), city-level filtering (country only), or startup-side funding data.

What you get

One row per matching firm: firm_name, firm_description, firm_city, firm_country, firm_website, firm_linkedin_url, firm_stages, firm_aum, firm_focus, industry_names (plus crunchbase_url and social links when on file). With Include_Contacts true (the point of this workflow), each firm adds investor_contacts, empty when no contacts are on file: name, job_title, email when available, linkedin_url, and minimum, maximum, and target check sizes, the fields an outreach row needs.

Prerequisites

The Actor

Run it with the Apify CLI

Pre-seed investors in AI, with contacts:

apify actors call "johnvc/startup-investors-data-scraper" -i '{"Investment_Stages":["Pre-Seed"],"Focus_Areas":["Artificial Intelligence"],"Include_Contacts":true,"Max_Results":25}' \
  --json \
  --user-agent apify-awesome-skills/apify-pre-seed-investors \
  2>/dev/null

Early-stage bundle (pre-seed through Series A) among angels and VCs in the United States:

apify actors call "johnvc/startup-investors-data-scraper" -i '{"Investment_Stages":["Pre-Seed","Seed","Series A"],"Firm_Types":["Venture Capital Investor","Angel Investor"],"Countries":["United States"],"Include_Contacts":true,"Max_Results":30}' \
  --json \
  --user-agent apify-awesome-skills/apify-pre-seed-investors \
  2>/dev/null

Every call carries the three flags this repo expects: --json, --user-agent apify-awesome-skills/apify-pre-seed-investors, and 2>/dev/null.

Run it from Claude or another AI agent (MCP)

The Actor is MCP-ready. Add the hosted server URL:

https://mcp.apify.com/?tools=actors,docs,johnvc/startup-investors-data-scraper

Then ask, for example: "Find 25 pre-seed investors in climate tech with partner contacts and check sizes, and format them as an outreach sheet." MCP setup docs: https://docs.apify.com/platform/integrations/mcp

Workflow

  1. Scope the raise. Map the user's stage to Investment_Stages (a raise usually spans two: ["Pre-Seed","Seed"]), their space to Focus_Areas, and any geography to Countries (full English names).
  2. Pick firm types. Pre-seed lists usually want Firm_Types ["Venture Capital Investor","Angel Investor"] (exact enum strings); add accelerators or family offices when the user asks.
  3. Turn contacts on. Include_Contacts true is what makes this an outreach list rather than a market map.
  4. Bound and estimate. Max_Results 20 to 30 keeps the first pass around $2 to $3; confirm before bigger pulls. See references/gotchas.md.
  5. Run, then shape for outreach. Flatten investor_contacts to one row per contact (firm, name, title, email, LinkedIn, target check size). Flag rows without email for LinkedIn-first outreach.
  6. Qualify against check size. Filter out contacts whose minimum check exceeds the round, using the min, max, and target check fields.

Inputs

  • Investment_Stages (text list, Pre-Seed to IPO): the stage filter this workflow centers on
  • Focus_Areas (enum, about 48 industries) and Firm_Types (enum, 17)
  • Countries (full English names), Keyword (free text)
  • Include_Contacts (true for outreach), Max_Results (cost cap), Offset

Cost

Per firm plus per contact: a 25-firm pull with contacts lands around $2 to $3. Larger sweeps scale linearly; estimate and confirm first. Live prices and thresholds are in references/gotchas.md.

Honest limits

  • Emails are present only when available; some contacts are LinkedIn-only.
  • Country filter only; "investors in Boston" needs a US pull filtered client-side on firm_city.
  • The data supports outreach research; whether an investor is a fit is the founder's call, and this skill gives data, not investment advice.

Troubleshooting

  • Too few firms: widen Investment_Stages by one stage or drop Focus_Areas; stage tagging varies by firm.
  • No contacts on some firms: expected; not every firm carries contact rows. The firm's LinkedIn URL still supports manual lookup.
  • List feels generic: add Keyword (for example "developer tools") to narrow within an industry.

See references/gotchas.md for cost guardrails and error recovery, and references/actor-index.md for the Actor routing table.

Related company-data Actors

What ships with it: 2 files

3.6 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most mcp tooling skills give in ~1.5k tokens

Counted across 638 of the 750 authors here whose files we hold, read 2026-08-07

  • Create ten complex or independent read-only evaluation questionsin 69 of 638, across 15 files
  • Test servers using MCP Inspectorin 61 of 638, across 19 files
  • Provide actionable error messages with specific next stepsin 54 of 638, across 12 files
  • Prioritize comprehensive API coverage over specific workflows or workflow toolsin 54 of 638, across 12 files
  • Use TypeScript and Streamable HTTP for remote servers or clientsin 54 of 638, across 8 files
  • Define structured output schemas where possiblein 50 of 638, across 8 files
  • Use Zod or Pydantic for input schemasin 47 of 638, across 5 files
  • Fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
  • Load framework documentation using WebFetchin 45 of 638, across 3 files
  • Verify each evaluation answer independentlyin 45 of 638, across 3 files
  • Implement API client with authentication and paginationin 45 of 638, across 3 files
  • Define input schemas with validationin 27 of 638, across 9 files

Said here and by no other author read

  • map the raise to investment stages
  • select firm types by investor type
  • set include contacts to true
  • bound max results to estimate costs
  • confirm before running bigger pulls
  • flatten investor contacts to one row per contact

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.