New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Startup Pressure Test

by Kappaemme-git in Kappaemme-git/codex-startup-pressure-test-skill

Pressure-tests a startup idea with blunt, compact analysis of problem reality, competition, first customers and MVP, ending in a strong, weak or pivot verdict.

MITAuto-check passedBusiness, Finance & HR

Install Startup Pressure Test

skills CLI
$ npx skills add Kappaemme-git/codex-startup-pressure-test-skill --skill startup-pressure-test -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Kappaemme-git/codex-startup-pressure-test-skill startup-pressure-test --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Kappaemme-git/codex-startup-pressure-test-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/startup-pressure-test .claude/skills/startup-pressure-test && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
startup-pressure-test
GitHub stars
991
Token cost
~1.2k tokens
SKILL.md length
500 words
Files
3 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Pressure-tests a startup idea with blunt, compact analysis of problem reality, competition, first customers and MVP, ending in a strong, weak or pivot verdict.

  • Checking whether a startup idea solves a real, urgent problem before building
  • SKILL.md covers Overview, Language, First Move and Modes, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Mapping direct and indirect competitors and what it would cost customers to switch

What it does

If the idea is missing, the agent first asks for the idea, the target customer and what they should do or pay for; if it is provided, work starts at once. A mode is chosen from the request: pressure-test, problem-validation, competition-map, first-10-customers, mvp-plan, or full for a compact run of all of them, which is also the default when the request is unclear. A playbooks reference holds the detailed prompt templates and criteria for each mode.

Output is compact by design: a verdict of strong, weak or pivot required in at most three sentences, a six-row scorecard, and short capped sections on fatal flaws, problem reality, competition, first customers and MVP. The agent ranks dangerous flaws first, names the core assumption that must hold, treats current behavior as competition, rejects a claim of having none, and asks discovery questions about past behavior. Manual founder-led validation comes before automation, and replies follow the user's language.

When your agent uses it

  • Checking whether a startup idea solves a real, urgent problem before building
  • Mapping direct and indirect competitors and what it would cost customers to switch
  • Planning how to win the first 10 customers by hand
  • Defining the smallest MVP that tests the core assumption in two weeks
  • Getting a direct strong, weak or pivot verdict on an idea

Example prompts

  • “Pressure-test my idea: invoicing software for freelance translators who bill per word.”
  • “Who would I compete with if I built a meal-planning app for dialysis patients?”
  • “Plan the first 10 customers for my B2B tool that reconciles Shopify payouts.”
  • “Give me a two-week MVP plan for a Slack bot that summarizes support tickets.”

What it can do on your machine

Read from SKILL.md and the folder at commit 247b065. 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 (its code samples are markdown).

    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

Startup Pressure Test loads about 1.2k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 500 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 Kappaemme-git/codex-startup-pressure-test-skill at commit 247b065, republished under its MIT licence (© Kappaemme-git). 500 words, ~1,167 tokens.

Download SKILL.mdSave it as .claude/skills/startup-pressure-test/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
startup-pressure-test
description
Brutally evaluate and refine startup ideas with practical early-stage startup frameworks. Use when Codex is asked to pressure-test a startup idea, validate whether the problem is real, map competitors and current customer behavior, find the first 10 customers, define an MVP, create a 2-week launch plan, assess founder-market fit, or give a direct strong/weak/pivot verdict.

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:

text
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.

Read references/playbooks.md for the detailed prompt templates and criteria for each mode.

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:

markdown
**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.
Show full SKILL.md (218 more words)Show less

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, browse or state what must be verified.

Scoring

Use scores only when useful:

AreaScore
Pain intensity1-5
Buyer clarity1-5
Urgency1-5
Differentiation1-5
Speed to validate1-5
Founder advantage1-5

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.

Resources

  • references/playbooks.md: Mode-specific checklists and output details.

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

Files

SKILL.md and 2 other files (references) in startup-pressure-test of Kappaemme-git/codex-startup-pressure-test-skill.

  • SKILL.md
  • agents/openai.yaml
  • references/playbooks.md

Open the folder on GitHubat commit 247b065

Compare with similar skills

Startup Pressure Test next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Startup Pressure Test compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Startup Pressure Test this skillKappaemme-git/codex-startup-pressure-test-skill991—~1.2kAutomated safety check: PassMIT
Product Strategistdavila7/claude-code-templates32k3 repos~248Automated safety check: PassMIT
Anygen DocLeoYeAI/openclaw-master-skills2.2k—~4.3kAutomated safety check: PassMIT
Startup Designferdinandobons/startup-skill1.2k—~8.1kAutomated safety check: PassMIT
Market Research Analysismanojbajaj95/claude-gtm-plugin105—~2.6kAutomated safety check: PassMIT
7 Powers Analysisamplitude/builder-skills159—~1.1kAutomated safety check: PassNone

Similar skills

  • Product Strategist

    davila7/claude-code-templates

    Strategic product leadership toolkit for Head of Product including OKR cascade generation, market analysis, vision setting, and team scaling.

    32k GitHub starsUsed in 3 repos~248 tokens
    Business, Finance & HRAuto-check passed

  • Anygen Doc

    LeoYeAI/openclaw-master-skills

    Use this skill any time the user wants to create, draft, or generate a written document or report.

    2.2k GitHub stars~4.3k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed

  • Startup Design

    ferdinandobons/startup-skill

    Design, validate, and plan a startup from scratch. An agent skill from ferdinandobons/startup-skill.

    1.2k GitHub stars~8.1k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed

  • Market Research Analysis

    manojbajaj95/claude-gtm-plugin

    Comprehensive market research and analysis skill. An agent skill from manojbajaj95/claude-gtm-plugin.

    105 GitHub stars~2.6k tokensUpdated 20 days ago
    Marketing & SEOAuto-check passed

  • 7 Powers Analysis

    amplitude/builder-skills

    Analyzes a business, product or feature with Hamilton Helmer's 7 Powers framework to judge competitive advantage and how long it will last.

    159 GitHub stars~1.1k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed

  • Startup Analyst

    aiskillstore/marketplace

    Expert startup business analyst specializing in market sizing, financial modeling, competitive analysis, and strategic planning for early-stage companies.

    430 GitHub starsUsed in 10 repos~2.9k tokens
    Business, Finance & HRAuto-check passed

Categories

Questions about Startup Pressure Test

What does Startup Pressure Test do?

Pressure-tests a startup idea with blunt, compact analysis of problem reality, competition, first customers and MVP, ending in a strong, weak or pivot verdict. If the idea is missing, the agent first asks for the idea, the target customer and what they should do or pay for; if it is provided, work starts at once. A mode is chosen from the request: pressure-test, problem-validation, competition-map, first-10-customers, mvp-plan, or full for a compact run of all of them, which is also the default when the request is unclear.

When should I use Startup Pressure Test?

Startup Pressure Test fits situations like: checking whether a startup idea solves a real, urgent problem before building; mapping direct and indirect competitors and what it would cost customers to switch; planning how to win the first 10 customers by hand; defining the smallest MVP that tests the core assumption in two weeks.

How do I install Startup Pressure Test in Claude Code?

Run `npx skills add Kappaemme-git/codex-startup-pressure-test-skill --skill startup-pressure-test -a claude-code`. Or copy the skill folder (startup-pressure-test in Kappaemme-git/codex-startup-pressure-test-skill) into .claude/skills/startup-pressure-test in your project. Claude Code loads it when a task matches its description.

How do I install Startup Pressure Test in Codex?

Run `npx skills add Kappaemme-git/codex-startup-pressure-test-skill --skill startup-pressure-test -a codex`. Or copy the skill folder (startup-pressure-test in Kappaemme-git/codex-startup-pressure-test-skill) into .agents/skills/startup-pressure-test in your project. Codex loads it when a task matches its description.

Can I use Startup Pressure Test in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Kappaemme-git/codex-startup-pressure-test-skill --skill startup-pressure-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/startup-pressure-test, .gemini/skills/startup-pressure-test, .github/skills/startup-pressure-test and .opencode/skills/startup-pressure-test in your project.

What does Startup Pressure Test need to run?

SKILL.md names no scripts, command-line tools or credentials: Startup Pressure Test is instructions for the agent only.

Does Startup Pressure Test access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Startup Pressure Test safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Startup Pressure Test use?

Startup Pressure Test is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Startup Pressure Test use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Startup Pressure Test?

Skills that share tags, products or a category with Startup Pressure Test: Product Strategist (davila7/claude-code-templates, 32k stars), Anygen Doc (LeoYeAI/openclaw-master-skills, 2.2k stars), Startup Design (ferdinandobons/startup-skill, 1.2k stars) and Market Research Analysis (manojbajaj95/claude-gtm-plugin, 105 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Startup Pressure Test?

Kappaemme-git (a GitHub user) maintains it in Kappaemme-git/codex-startup-pressure-test-skill, which has 991 GitHub stars. The repository was last updated on May 3, 2026.

Source: Kappaemme-git/codex-startup-pressure-test-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.