| name | hermes-startup-pressure-test |
| description | Use when pressure-testing a startup idea, validating real customer pain, mapping competition/current behavior, finding the first 10 customers, defining a 2-week MVP, assessing founder-market fit, or giving a direct strong/weak/pivot verdict. |
| version | 1.0.0 |
| author | Hermes Agent; adapted from Francesco Mistero |
| license | MIT |
| metadata | {"hermes":{"tags":["startup","validation","mvp","founder","pressure-test","yc"],"related_skills":["ideation","writing-plans"]}} |
Startup Pressure Test
Overview
Use this skill to pressure-test a startup idea before the user wastes time building the wrong thing. Be direct, specific, and practical. Use a Paul Graham-style early startup lens: real users, painful problems, current behavior, manual traction, and the smallest test that proves or kills the idea.
Language
Match the user's language. If the user writes in Italian, answer in Italian. If the user writes in English, answer in English. Keep common startup terms in English when clearer: ICP, MVP, PMF, early adopter, switching cost, wedge.
First Move
If the idea is missing, ask for it first. Keep the question short:
Send me the startup idea, target customer, and what you want them to do/pay for.
If the idea is already provided, start immediately.
Modes
Choose the mode from the user request. If unclear, use full.
pressure-test: find fatal flaws and give a verdict.problem-validation: test whether the pain is real and urgent.competition-map: map current behavior, direct competitors, indirect competitors, and switching cost.first-10-customers: create a manual plan to find and convert the first 10 customers.mvp-plan: define the smallest MVP that tests the core assumption in 2 weeks.full: run a compact version of all modes.
Use references/playbooks.md for the detailed prompt templates and criteria for each mode when the user asks for a specific mode, deep report, or more detail.
Default Output
Default to compact output. Most users need a sharp diagnosis they can scan in 30 seconds, not a long essay. Include the score table by default.
Use this shape:
**Verdict**
Strong / Weak / Pivot required
2-3 direct sentences.
**Scorecard**
| Area | Score | Read |
|---|---:|---|
| Pain intensity | 3/5 | ... |
| Buyer clarity | 2/5 | ... |
| Urgency | 3/5 | ... |
| Differentiation | 2/5 | ... |
| Speed to validate | 4/5 | ... |
| Founder advantage | 3/5 | ... |
**Core Assumption**
One sentence.
**Fatal Flaws**
| Risk | Severity | Why It Matters | Fast Test |
|---|---|---|---|
| ... | High | ... | ... |
**Problem Reality**
- Pain: ...
- Early adopter: ...
- Vitamin or painkiller: ...
**Competition**
- Current behavior: ...
- Real enemy: ...
- Differentiation needed: ...
**First 10 Customers**
1. ...
2. ...
3. ...
**MVP**
- Build:
- Cut:
- 2-week test:
Default limits:
- Scorecard: always include 6 rows.
- Verdict: max 3 sentences.
- Fatal flaws: max 3 rows.
- Problem reality: max 3 bullets.
- Competition: max 3 bullets.
- First 10 customers: max 3 actions.
- MVP: max 3 bullets.
- Do not include outreach templates, discovery questions, or weekly plans unless the user asks for more detail.
Rules
- Be specific to the idea; never give generic startup advice.
- Rank dangerous flaws first.
- Identify the core assumption that must be true for the business to work.
- Treat current behavior as competition.
- Treat "we have no competition" as false by default.
- Test real behavior, not compliments or hypothetical intent.
- Discovery questions must ask about past behavior.
- Prefer manual founder-led validation before automation.
- First customers must be found manually before ads, growth hacks, or scale.
- Cut features that do not test the riskiest assumption.
- MVP must test the single riskiest assumption, not become a mini-product.
- If the idea is weak, say so directly and explain the pivot path.
- Do not invent fake market data. If market facts matter and are current/uncertain, use available web/search tools or clearly state what must be verified.
Scoring
Use scores only when useful:
| Area | Score |
|---|
| Pain intensity | 1-5 |
| Buyer clarity | 1-5 |
| Urgency | 1-5 |
| Differentiation | 1-5 |
| Speed to validate | 1-5 |
| Founder advantage | 1-5 |
Scores must be tied to evidence from the idea, not vibes.
Deep Mode
If the user asks for deep, full report, brutal, be extremely honest, or give me more detail, expand each section with:
- assumptions to validate
- disconfirming evidence to look for
- customer discovery questions
- outreach messages
- 2-week milestones
- pivot options
Still keep the writing direct and structured.
Hermes Usage
Invoke this skill by name when the user asks to pressure-test or validate a startup idea:
/skill hermes-startup-pressure-test
Then send the idea, target customer, and what the customer should do or pay for. In regular chat, load this skill whenever the user asks for startup idea validation, MVP narrowing, first-customer planning, or a strong/weak/pivot verdict.
Attribution
Adapted for Hermes from the MIT-licensed Codex startup-pressure-test skill by Francesco Mistero. Original package/repository references discovered from hnrydev/startup-pressure-test-skill and codex-startup-pressure-test-skill.
Resources
references/playbooks.md: Mode-specific checklists and output details.
