惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

腾讯CDC
博客园 - Franky
MyScale Blog
MyScale Blog
L
LangChain Blog
Martin Fowler
Martin Fowler
Recent Announcements
Recent Announcements
Stack Overflow Blog
Stack Overflow Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - 司徒正美
量子位
A
About on SuperTechFans
C
Check Point Blog
大猫的无限游戏
大猫的无限游戏
Last Week in AI
Last Week in AI
小众软件
小众软件
Apple Machine Learning Research
Apple Machine Learning Research
I
InfoQ
V
Visual Studio Blog
Vercel News
Vercel News
B
Blog
爱范儿
爱范儿
aimingoo的专栏
aimingoo的专栏
U
Unit 42

Show HN

Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code.
GitHub - assafkip/investor-recon: A threat-intelligence a...
Assafkip · 2026-06-12 · via Show HN

A threat-intelligence approach to VC meetings. Runs in Claude Code, searches the fund's real material, and refuses to make things up.

investor-recon in 25 seconds: walk in blind vs walk in with the brief

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.

The rule that matters

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.

What it produces

  • Thesis brief. What this fund actually backs, quoted from their own material, with links. Their words separated from your read of their deals.
  • Portfolio map. Where you fit, which portfolio company you collide with, the gap you fill.
  • Question set. The questions this partner will ask, from their cited thesis and your stage.
  • The hesitation. The single thing about your company that makes this specific fund pause.
  • The counter. How you answer it before they raise it.
  • Sources and gaps. Every link used, and an honest list of what it could not confirm.

Use it (two ways)

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.

Who built this

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.

License

MIT. See LICENSE.


Built by Assaf

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.