by assafkip
A threat-intelligence approach to VC meetings. Six prompts, ~25 min per investor. Built with Claude Code.
# Add to your Claude Code skills
git clone https://github.com/assafkip/investor-reconGuides for using api integration skills like investor-recon.
Last scanned: 6/11/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-06-11T08:50:27.422Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}investor-recon is an open-source api integration skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by assafkip. A threat-intelligence approach to VC meetings. Six prompts, ~25 min per investor. Built with Claude Code. It has 0 GitHub stars.
Yes. investor-recon passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/assafkip/investor-recon" and add it to your Claude Code skills directory (see the Installation section above).
Yes. SkillsLLM lists many other API Integration skills you can browse and compare side by side. Open the API Integration category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh investor-recon against similar tools.
No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
A threat-intelligence approach to VC meetings. Runs in Claude Code, searches the fund's real material, and refuses to make things up.

Interactive version of this brief · claudedaddy.io
I spent 12 years doing threat intelligence. The job was simple to describe. Build a picture of an adversary before they ever know you are looking. Their patterns, their gaps, their next move.
A VC meeting is the same problem.
Most founders prep by rehearsing their pitch. That is backwards. The pitch is not where the decision happens. The fund builds a thesis about you before you walk in. The meeting is where they confirm it.
So stop rehearsing. Run recon.
This searches the real internet for the fund's material and cites every claim. If it cannot find something, it says "Not found." It never guesses the fund's deals, thesis, or check size from the name. A confident wrong brief walks you into the wrong room. That is worse than no brief.
This is why it runs in Claude Code, not a chat box. Claude Code can actually search and fetch. A plain chat guesses, and you cannot tell. The grounding is the product.
Easiest, no install. Open Claude Code, then copy the block in PASTE-THIS.md and paste it in. It asks you two questions and runs. Full setup steps (including the folder step Claude Code asks for) are in that file.
As a command. Install the plugin:
/plugin install github:assafkip/investor-recon
Then run /investor-recon in any Claude Code session.
See example-brief.md for what a finished brief looks like.
I build custom AI systems for founders and small teams. This repo is the free, lighter version of the work I do paid. If you want it wired into your actual raise, or a different operational problem an AI system should be handling, reach me at assaf@askconsulting.io.
MIT. See LICENSE.
I spent 12 years in threat intelligence watching teams find the same failure and fix it four times. The learning never stuck. I build tools that make it stick.
This is the free version. The paid kits live at claudedaddy.io.
Want this wired into your team's repo, or a heavier spec-and-review pipeline? That's the consulting. Book a call.