AD vc-ai-infra-scout
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, price-capped paid endpoints (SELAT); pays per call in USDC from the user's own self-custody Circle wallet. Full run hard-capped at $0.40.
Deal-sourcing scout for VCs running an AI-infrastructure thesis — AI infra, crypto-AI/decentralized-AI, robotics/embodied-AI, agentic payments.
As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 85Steps. 8 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1323 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 573: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.