Soft Screening Startup

What it does

When your agent uses it

• Include: evaluate this startup
• Screen this company
• Should I invest in X
• Is this a good investment

Example prompts

• “evaluate this startup”
• “screen this company”
• “should I invest in X”
• “/soft-screening-startup”

Requirements

• Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1EXTRACT COMPANY PROFILE
2. 2SCORE 8 DIMENSIONS
3. 3APPLY 4 INVESTOR LENSES
4. 4COMPUTE WEIGHTED OVERALL SCORE
5. 5DETERMINE VERDICT
6. 6WRITE INVESTMENT MEMO

What it can do on your machine

Read from SKILL.md and the folder at commit 616deb5. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Soft Screening Startup loads about 2.3k tokens when it runs. Until then it costs about 214 tokens; SKILL.md has 763 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~214

When it runs · the whole SKILL.md, loaded when a task matches

~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from davepoon/buildwithclaude at commit 616deb5, republished under its MIT licence (© davepoon). 763 words, ~2,334 tokens.

name

soft-screening-startup

description

Activate for ANY startup evaluation, investment screening, or company assessment. Triggers include: "evaluate this startup", "screen this company", "should I invest in X", "is this a good investment", "what do you think about this company", "review this startup", "score this company", "rate this pitch", "assess this founder", "quick take on X", "is X worth investing in", "pass or decline on X", "what's your verdict on X", "first look at this company", "quick screen on X", "what's your take on this founder", "is this fundable", "would a VC invest in this". Also triggers when a user pastes a company description, funding ask, or founder background and asks for an opinion. Works on claude.ai and Claude Code. For hard-mode deterministic scoring with Python audit trail, use /venture-capital-intelligence:hard-screening-startup.

Company:        [name or "unnamed"]
Sector:         [B2B SaaS / Consumer / Fintech / HealthTech / etc.]
Stage:          [Pre-Seed / Seed / Series A / Series B / etc.]
Geography:      [HQ + primary market]
Team:           [founders, backgrounds, relevant experience]
Product:        [what it does, how it works, what's unique]
Market:         [target customer, TAM claim if any]
Traction:       [revenue, users, growth rate, key customers]
Business Model: [how it makes money, pricing, unit economics if known]
Ask:            [fundraise amount, what it's for]
Missing:        [list any key info not provided]

Team            × 0.25   (most important — backs the jockey, not the horse)
Market          × 0.20   (venture requires big markets)
Product         × 0.15
Traction        × 0.15   (evidence beats argument)
Business Model  × 0.10
Competition     × 0.08
Financials      × 0.05
Risk Profile    × 0.02   (risk is last — every great company has risk)
─────────────────────────
Total           = 1.00

Weighted Score ≥ 7.5  AND  no single dimension below 4  →  PASS
Weighted Score 6.0–7.4  OR  one dimension below 4        →  CONDITIONAL PASS
Weighted Score < 6.0  OR  any dimension below 3           →  DECLINE

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
STARTUP SCREEN  ·  [Company Name]  ·  [Stage]  ·  [Sector]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

DIMENSION SCORES
  Team             [X]/10  [████████░░]  [1-sentence rationale]
  Market           [X]/10  [████████░░]  [1-sentence rationale]
  Product          [X]/10  [████████░░]  [1-sentence rationale]
  Traction         [X]/10  [████████░░]  [1-sentence rationale]
  Business Model   [X]/10  [████████░░]  [1-sentence rationale]
  Competition      [X]/10  [████████░░]  [1-sentence rationale]
  Financials       [X]/10  [████████░░]  [1-sentence rationale]
  Risk Profile     [X]/10  [████████░░]  [1-sentence rationale]

  WEIGHTED SCORE   [X.X]/10

INVESTOR LENSES
  Sequoia          [PASS / WATCH / PASS]    [1-line reason]
  YC               [PASS / WATCH / PASS]    [1-line reason]
  Tiger Global     [PASS / WATCH / PASS]    [1-line reason]
  Risk Mgmt        [MANAGEABLE / ELEVATED]  [1-line reason]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
VERDICT:  [PASS / CONDITIONAL PASS / DECLINE]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

[If CONDITIONAL PASS, list conditions:]
  Conditions:
  1. [specific condition]
  2. [specific condition]

INVESTMENT THESIS
[2–3 sentence bull case]

WHY NOW
[1–2 sentences on timing tailwind]

KEY RISKS
  1. [risk]
  2. [risk]
  3. [risk]

DD PRIORITIES
  1. [item to verify]
  2. [item to verify]
  3. [item to verify]

COMPARABLES
  [Company A] — [why this comp is relevant]
  [Company B] — [why this comp is relevant]

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
For deterministic Python-scored audit trail: /venture-capital-intelligence:hard-screening-startup
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

© davepoon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/venture-capital-intelligence/skills/soft-screening-startup of davepoon/buildwithclaude.

Open the folder on GitHubat commit 616deb5