vc-ai-infra-scout
Skill2 starsChanged 4 months agoMITView on GitHub
Deal-sourcing scout for VCs running an AI-infrastructure thesis — AI infra, crypto-AI/decentralized-AI, robotics/embodied-AI, agentic payments. Use when asked to \"scout AI infra startups\", \"find founders who haven't raised yet\", \"build a deal shortlist for my thesis\", or \"what pre-seed/seed rounds are being announced and what's the thesis behind them\". Fuses Hacker News, Product Hunt, web, Twitter/X, and LinkedIn signal via vetted paid endpoints (SELAT); pays per call in USDC from the user's own self-custody Circle wallet. Dry-run first to see live prices.
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- SELAT-AI/selat-skillstheir own version, first seen Oct 4, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- SELAT-AI/selat-skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 43
Every step is a real paid API call in USDC from the user's own Circle Agent Wallet (MPC self-custody — SELAT never holds keys or funds).
- Distinctive: line 50
Never ask for, paste, or handle a private key.
- Very specific: line 55
If selat isn't on PATH yet, install it — one npm package, no signup, no credentials:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
vc-ai-infra-scout
Source AI-infrastructure deals before the round. This skill runs a vetted multi-step pipeline that discovers emerging companies and founders from Hacker News, Product Hunt, the open web, Twitter/X, and LinkedIn, reads recent pre-seed/seed fundraising announcements, distills the live thesis of the funds leading those rounds, then enriches the top lead. You (the agent) do the judgment work around the paid data: dedupe across sources, rank by signal, flag teams that have not raised yet, and produce a shortlist with links plus a suggested outreach note.
The pipeline is a SELAT skill: a declarative, vetted recipe of paid API
calls (no API keys, no signups) settled in USDC across multiple payment rails
— direct Circle x402, routed MPP, and routed x402 on Base. The selat CLI
resolves the vetted endpoints, auto-detects each step's rail, and prints a
per-rail receipt summary.
Cost — read this first
- Every step is a real paid API call in USDC from the user's own Circle Agent Wallet (MPC self-custody — SELAT never holds keys or funds).
- Prices and spend limits live in the underlying SELAT skill, not here — the
live HTTP 402 quote from
selat skill verify/runis the price source of truth, so this wrapper doesn't restate dollar figures (they'd only drift). - Always dry-run first (Step 1 — free, no wallet), show the user the real quoted prices, and get their OK before any wallet setup or paid run.
- Never ask for, paste, or handle a private key. Wallet auth is handled by the CLI's Circle integration.
Step 0 — get the CLI (free, no account)
If selat isn't on PATH yet, install it — one npm package, no signup, no
credentials:
selat --version || npm install -g @selat-ai/selat-cli(macOS Skills UI users can also install it from this skill's dependency prompt.) Installing the CLI creates nothing money-related — no wallet, no account, no keys.
Step 1 — dry run first, before any wallet setup
Do this before creating a wallet or asking the user to fund anything.
The dry run probes every endpoint's live price and reachability for free — no
wallet, no funds, no account, no selat init:
selat skill install vc-ai-infra-scout
SELAT_ROUTER_URL=https://router.selat.ai \
selat skill verify ~/.config/selat/skills/vc-ai-infra-scout(verify takes the installed skill's directory — $XDG_CONFIG_HOME/selat/skills/<name>,
which defaults to the path above. The SELAT_ROUTER_URL prefix is only needed
before selat init has written config; it lets the routed steps quote their
price with zero setup.)
This prints each step's real quoted price and rail from the live 402 challenges — the actual cost of a run. Show the user these prices and get their OK before going anywhere near wallet setup. If they don't want to proceed, stop here; nothing has been spent and nothing has been created.
Step 2 — wallet setup (only after the user opts in)
selat init # creates the self-custody Circle Agent Wallet + config
selat fund # deposit USDC into Circle Gateway (user action)
selat doctor # verify wallet, router, and balance are readyselat init is safe to re-run — it detects an existing wallet and asks
before changing anything.
Step 3 — run
selat skill run vc-ai-infra-scout \
--thesis "humanoid robotics foundation models" \
--twitterQuery "humanoid robotics founder" \
--fundraisingQuery "robotics startup raised seed pre-seed 2026" \
--investorQuery "<lead funds surfaced by the fundraising steps>" \
--domain <top-lead-domain.com>| Param | Required | What it steers |
thesis | yes | Sub-thesis keyword for HN / Product Hunt / web discovery and the founder shortlist. |
twitterQuery | no | Twitter/X keyword search for founder buzz. |
fundraisingQuery | no | Keyword query for recent raise announcements (Twitter/X + LinkedIn). Put recency cues in the query itself. |
investorQuery | no | Twitter/X search for the funds leading those rounds — set it from the fundraising results, then re-run just that lens if needed. |
domain | no | The most promising company's domain, for the enrichment step. |
Each step returns raw JSON. Your job afterward: dedupe companies across sources, rank by traction/recency/founder signal, summarize the lead-fund tweets into the live thesis, explicitly flag promising teams with no announced round, and output a ranked shortlist with source links and a short outreach note for the top pick.
Why this is safe to install
- The skill is a declarative JSON manifest — no executable code. Installing it only ever writes data.
- Endpoints are https-only and pre-vetted; each publish is gated on a machine-checked live verification receipt.
- Spend limits are defined by the underlying SELAT skill and enforced by the runner, which surfaces the wallet's spending policy at every money moment.
- Funds stay in the user's own wallet. No API keys, no platform balance, no custodian.
Beyond this skill
SELAT is a general capability layer for paid agent actions. If the user's ask doesn't fit this skill:
selat search "<intent>" # FREE federated discovery + ranking
selat skill list --available # other vetted multi-step skillsDoes 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.

