// Claude Plugins
founder-skills
Adversarial startup idea interrogation pipeline → BUILD / KILL / PIVOT verdict. Works with Claude Code, Codex, Cursor, Windsurf, Kiro, and OpenCode.
// Claude Plugins[ cli ][ claude ]#claude#ai-agents#claude-code#claude-plugin#codex#cursor-rules#founder#idea-validation#plugins$open-sourceupdated 16 days ago
Dormant
58/100
last commit 5 months ago
last release none
releases 0
open issues 0
Install with your AI
Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.
⚠ Unverified source (community-unclaimed, low activity) — reveal the prompt
⚠ Unverified source (community-unclaimed, low activity). Inspect the repo before letting your agent install it. Install and set up founder-skills (claude-plugin project) into my current project. Found on https://claudeers.com/founder-skills Repo: https://github.com/SanketSapkal/founder-skills Homepage/docs: — Detected install method: claude-plugin → /plugin install founder-skills@SanketSapkal/founder-skills Category: plugins. Platforms: cli. Read the repo's README for exact setup and env vars, then install it and wire it into my project. Claudeers Health Verdict: dormant; community-verified: false. Confirm the source before running anything.
// or install directly (claude-plugin)
⚠ Unverified / not recently updated — review before pasting a run-this config.
/plugin marketplace add SanketSapkal/founder-skills /plugin install founder-skills@SanketSapkal/founder-skills
// or clone · unverified · not recently updated
git clone https://github.com/SanketSapkal/founder-skills
// compatibility
| Platforms | cli |
|---|---|
| Operating systems | — |
| AI compatibility | claude |
| License | — |
| Pricing | open-source |
| Language | Shell |
founder-skills
Adversarial idea interrogation followed by structured business modeling — in one chained pipeline.
Every existing startup skills repo is generative: you bring an idea and it helps you fill it out. This repo starts by trying to kill the idea first, then builds out the survivors.
Existing repos: Interrogate OR Model
This repo: Interrogate THEN Model
The Key Differentiator
/verdict — a synthesis skill that reads all prior outputs and returns an explicit BUILD / KILL / PIVOT judgment with structured reasoning. No other skills repo has this.
Pipeline
[/problem-discovery] ──> [/problem-statement] ──> /pressure-test ──> /customer-archetype ──┬──> /founder-fit
(optional, if no ↑ ├──> /scope-mode ──> /startup-canvas ──> /unit-economics
specific idea yet) ⚠ run in fresh │ │
conversation ├──> /market-size ─────────┤
to avoid bias │ ├──> /regulatory-risk (regulated industries)
│ ├──> /battle-cards
│ └──> /assumption-map ──> /pretotype
└──────────────────────────────────────────────────────┘
↓
All outputs ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────> /verdict
/verdict (BUILD) ──┬───────────────────────────────> /build-brief → coding agent
├───────────────────────────────> /pitch-deck, /investor-lens, /elevator-pitch, /objection-map
└───────────────────────────────> /gtm-plan, /oneliner, /cold-outreach, /content-strategy
/verdict (KILL/PIVOT) ─────────────────────────────> /pivot-paths
⚠ Bias warning:
/problem-discoveryand/problem-statementhelp shape the problem — they are not adversarial. After running them, switch to a fresh Claude Code conversation before running/pressure-test. Otherwise the agent that just helped you frame the problem will be biased toward validating it, undercutting the adversarial review. This is a fundamental limit of LLM self-review, not a Claude-specific issue.
Every skill writes a structured output file to ./founder-outputs/. Downstream skills read those files. /verdict reads all of them.
Quick Start
- Install the plugin (see below)
- Open a project in Claude Code
- Say "I have an idea" or run
/pressure-test - Follow the pipeline — each skill recommends the next step
Installation
As a Claude Code plugin (recommended)
claude plugin add /path/to/founder-skills
Multi-platform install
The setup script auto-detects installed coding agents and installs the appropriate format for each:
git clone https://github.com/YOUR_USERNAME/founder-skills.git
cd founder-skills
./setup --auto # detect and install for all found agents
Or install for specific platforms:
./setup --claude global # Claude Code — symlink to ~/.claude/skills/
./setup --claude local # Claude Code — symlink to ./.claude/skills/
./setup --codex # Codex CLI — generate AGENTS.md
./setup --cursor # Cursor — generate .cursorrules
./setup --kiro # Kiro — copy SKILL.md to ~/.kiro/skills/
./setup --opencode # OpenCode — copy SKILL.md to .opencode/skills/
./setup --windsurf # Windsurf — generate .windsurf/rules/
./setup --all # install for every supported platform
Supported Platforms
| Platform | Format Generated | Install Location |
|---|---|---|
| Claude Code | SKILL.md (native) | ~/.claude/skills/ or .claude/skills/ |
| Codex CLI | AGENTS.md (plain markdown) | project root |
| Cursor | .cursorrules (markdown) | project root |
| Kiro | SKILL.md (copied) | ~/.kiro/skills/ |
| OpenCode | SKILL.md (copied) | .opencode/skills/ |
| Windsurf | .windsurf/rules/*.md | project root |
Skills Reference
| Skill | Purpose | Reads | Writes |
|---|---|---|---|
/problem-discovery | Surface candidate problems when no specific idea exists yet | — | problem-discovery-output.md |
/problem-statement | Polish a vague problem into a precise JTBD statement | problem-discovery (optional) | problem-statement-output.md |
/pressure-test | Adversarial interrogation — kill bad ideas early | problem-statement (optional) | pressure-test-output.md |
/customer-archetype | Force precise customer definition + buying committee mapping | pressure-test | customer-archetype-output.md |
/founder-fit | Assess founder-market fit and unfair advantage | pressure-test, archetype | founder-fit-output.md |
/scope-mode | Calibrate ambition: EXPAND / SELECTIVE / HOLD / REDUCE | pressure-test, archetype | scope-output.md |
/market-size | Bottom-up TAM / SAM / SOM | pressure-test, archetype | market-size-output.md |
/startup-canvas | Business model + value proposition | pressure-test, archetype, scope | startup-canvas-output.md |
/unit-economics | CAC / LTV / payback / gross margin — viability math | canvas, archetype, market-size, gtm-plan | unit-economics-output.md |
/regulatory-risk | Compliance exposure and licensing requirements | canvas, archetype, market-size | regulatory-risk-output.md |
/battle-cards | Competitive intelligence + switching costs + positioning | archetype, canvas | battle-cards-output.md |
/assumption-map | Surface and prioritize riskiest assumptions | canvas, market-size | assumption-map-output.md |
/pretotype | Design validation experiments | assumption-map | pretotype-output.md |
/verdict | BUILD / KILL / PIVOT synthesis | ALL outputs | verdict-output.md |
/pivot-paths | 3 concrete pivot directions | verdict + all outputs | pivot-paths-output.md |
/10x-why-now | Thiel's "why now" formalized | pressure-test, battle-cards | why-now-output.md |
/analogous-cos | Structurally similar companies in other markets | pressure-test, canvas | analogous-cos-output.md |
/build-brief | Structured handoff for coding agents | ALL outputs (BUILD verdict) | build-brief-output.md |
| Investment Pitch | |||
/pitch-deck | Sequoia narrative arc from all outputs | ALL outputs | pitch-deck-output.md |
/investor-lens | Score through seed angel, Series A, corporate VC lenses | verdict, canvas, market-size | investor-lens-output.md |
/elevator-pitch | 30-sec, 2-min, 10-min pitch versions | canvas, archetype, battle-cards | elevator-pitch-output.md |
/objection-map | 8-10 hardest investor questions with answers | verdict, assumption-map | objection-map-output.md |
| Sales & Marketing | |||
/gtm-plan | Bullseye framework — rank 19 channels, test top 3 | canvas, archetype | gtm-plan-output.md |
/oneliner | One-sentence value prop with scoring criteria | canvas, archetype, battle-cards | oneliner-output.md |
/cold-outreach | Personalized 3-email sequences from archetype | archetype, canvas | cold-outreach-output.md |
/content-strategy | 30-day content plan matched to archetype sources | archetype, canvas, battle-cards | content-strategy-output.md |
CLAUDE.md Snippet
Add this to your project's CLAUDE.md to give Claude pipeline awareness:
## Founder Skills Pipeline
This project uses the founder-skills pipeline for idea validation.
### Output Directory
All skill outputs are saved to `./founder-outputs/`. Each skill reads
prior outputs from this directory to build on earlier analysis.
### Pipeline Sequence
0a. `/problem-discovery` — (optional) Surface candidate problems if no idea yet
0b. `/problem-statement` — (optional) Polish a vague problem before pressure-testing
1. `/pressure-test` — Adversarial interrogation (run first if you have an idea)
2. `/customer-archetype` — Define the specific customer
3. `/founder-fit` — Assess founder-market fit
4. `/scope-mode` — Calibrate ambition level
5. `/market-size` — Bottom-up TAM/SAM/SOM
6. `/startup-canvas` — Business model + value proposition
7. `/unit-economics` — CAC / LTV / payback / gross margin
8. `/regulatory-risk` — Compliance exposure (regulated industries)
9. `/battle-cards` — Competitive intelligence
10. `/assumption-map` — Risk prioritization
11. `/pretotype` — Validation experiments
12. `/verdict` — BUILD / KILL / PIVOT judgment
> **Bias warning:** if you run `/problem-discovery` or `/problem-statement`, switch to a fresh Claude Code conversation before `/pressure-test` — otherwise the agent that helped frame the problem will be biased toward validating it.
Books Referenced
| Book | Author | Used By |
|---|---|---|
| The Mom Test | Rob Fitzpatrick | /pressure-test, /customer-archetype |
| Zero to One | Peter Thiel | /pressure-test, /scope-mode, /10x-why-now |
| Competing Against Luck | Clayton Christensen | /pressure-test, /customer-archetype, /startup-canvas |
| Lean Analytics | Croll & Yoskovitz | /market-size |
| The Lean Startup | Eric Ries | /startup-canvas, /pretotype, /scope-mode |
| Business Model Generation | Osterwalder | /startup-canvas |
| $100M Offers | Alex Hormozi | /startup-canvas |
| Continuous Discovery Habits | Teresa Torres | /assumption-map |
| Obviously Awesome | April Dunford | /battle-cards |
| Crossing the Chasm | Geoffrey Moore | /battle-cards, /10x-why-now |
| Pretotype It | Alberto Savoia | /pretotype |
| The Hard Thing About Hard Things | Ben Horowitz | /verdict |
| Shape Up | Basecamp | /build-brief |
| Inspired | Marty Cagan | /build-brief |
| Venture Deals | Feld & Mendelson | /investor-lens, /pitch-deck |
| The Fundraising Rules | Mark MacLeod | /objection-map |
| Traction | Weinberg & Mares | /gtm-plan |
| $100M Leads | Alex Hormozi | /gtm-plan, /cold-outreach, /content-strategy |
| Predictable Revenue | Ross & Tyler | /cold-outreach |
| Secrets of Sand Hill Road | Scott Kupor | /verdict |
// faq
What is founder-skills?
Adversarial startup idea interrogation pipeline → BUILD / KILL / PIVOT verdict. Works with Claude Code, Codex, Cursor, Windsurf, Kiro, and OpenCode.. It is open-source on GitHub.
Is founder-skills free to use?
founder-skills is open-source, so it is free to use.
What category does founder-skills belong to?
founder-skills is listed under plugins in the Claudeers registry of Claude-compatible tools.
5 views
★ 11 stars
unclaimed
updated 16 days ago
// embed badge
[](https://claudeers.com/founder-skills)
// retro hit counter
[](https://claudeers.com/founder-skills)
// reviews
// guestbook
0/500
// related in Claude Plugins
🔓A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
// pluginsmultica-ai/★ 215,548[ claude ]
🔓Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explainin…
// pluginsanthropics/⟨Python⟩★ 147,969[ claude ]
🔓"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
// pluginsHKUDS/⟨Python⟩★ 50,756◷ Apache-2.0[ claude ]
🔓financial-services — a Claude ecosystem project on GitHub.
// pluginsanthropics/⟨Python⟩★ 37,359◷ Apache-2.0[ claude ]