Idea Evaluator
sickn33/agentic-awesome-skills
Evaluates an idea by hosting a multi-turn debate between a Pro and Con agent, delivering a final verdict on whether it's worth pursuing.
Help users distinguish between deceptive tarpit ideas and high-potential opportunities by applying rigorous frameworks for market timing, business math, and user demand.
MITAuto-check passed
Install Evaluating Startup Ideas
$ npx skills add RefoundAI/lenny-skills --skill evaluating-startup-ideas -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install RefoundAI/lenny-skills evaluating-startup-ideas --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/evaluating-startup-ideas .claude/skills/evaluating-startup-ideas && rm -rf skills-srcUse ~/.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/
Install the "evaluating-startup-ideas" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/evaluating-startup-ideas into .claude/skills/evaluating-startup-ideas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-startup-ideas", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/RefoundAI/lenny-skills/tree/main/skills/evaluating-startup-ideasType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add RefoundAI/lenny-skills --skill evaluating-startup-ideas -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install RefoundAI/lenny-skills evaluating-startup-ideas --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/evaluating-startup-ideas .agents/skills/evaluating-startup-ideas && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "evaluating-startup-ideas" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/evaluating-startup-ideas into .agents/skills/evaluating-startup-ideas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-startup-ideas", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add RefoundAI/lenny-skills --skill evaluating-startup-ideas -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install RefoundAI/lenny-skills evaluating-startup-ideas --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/evaluating-startup-ideas .cursor/skills/evaluating-startup-ideas && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "evaluating-startup-ideas" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/evaluating-startup-ideas into .cursor/skills/evaluating-startup-ideas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-startup-ideas", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/RefoundAI/lenny-skills.git --path skills/evaluating-startup-ideas--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add RefoundAI/lenny-skills --skill evaluating-startup-ideas -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install RefoundAI/lenny-skills evaluating-startup-ideas --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/evaluating-startup-ideas .gemini/skills/evaluating-startup-ideas && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "evaluating-startup-ideas" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/evaluating-startup-ideas into .gemini/skills/evaluating-startup-ideas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-startup-ideas", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install RefoundAI/lenny-skills evaluating-startup-ideasInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add RefoundAI/lenny-skills --skill evaluating-startup-ideas -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/evaluating-startup-ideas .github/skills/evaluating-startup-ideas && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "evaluating-startup-ideas" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/evaluating-startup-ideas into .github/skills/evaluating-startup-ideas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-startup-ideas", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add RefoundAI/lenny-skills --skill evaluating-startup-ideas -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install RefoundAI/lenny-skills evaluating-startup-ideas --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/evaluating-startup-ideas .opencode/skills/evaluating-startup-ideas && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "evaluating-startup-ideas" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/evaluating-startup-ideas into .opencode/skills/evaluating-startup-ideas/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evaluating-startup-ideas", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
evaluating-startup-ideas- GitHub stars
- 1.4k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 979 words
- Files
- 3 (incl. references)
- Skills in repo
- 76
- Repo updated
- First seen
- Licence
- MIT
At a glance
Help users distinguish between deceptive tarpit ideas and high-potential opportunities by applying rigorous frameworks for market timing, business math, and user demand.
- Works in 4 steps: Assess Problem Urgency - Determine if… → Analyze Market Timing - Evaluate if… → Review Business Viability - Scrutinize… → …
- SKILL.md covers How to Help, Core Principles, Templates & Frameworks and Questions to Help Users, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Evaluating Startup Ideas is an agent skill from RefoundAI/lenny-skills. Help users distinguish between deceptive tarpit ideas and high-potential opportunities by applying rigorous frameworks for market timing, business math, and user demand.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/artifacts.md` and `references/guest-insights.md`).
The repository describes itself as: 86 product management skills from Lenny's Podcast for Claude Code and AI agents. Hiring, user research, strategy, shipping, and more. The licence is MIT.
Example prompts
- “/evaluating-startup-ideas”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Assess Problem Urgency - Determine if you are solving a hair-on-fire problem or an incremental convenience.
- Analyze Market Timing - Evaluate if there is a clear why now inflection point in technology, regulation, or behavior.
- Review Business Viability - Scrutinize the underlying math to ensure a path to $100M in annual revenue.
- Validate via Experiments - Guide the transition from brainstorming to manual testing before committing to code.
What it can do on your machine
Read from SKILL.md and the folder at commit 13598cc. 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
Evaluating Startup Ideas loads about 1.7k tokens when it runs, and up to ~35k if it reads all its reference files. Until then it costs about 49 tokens; SKILL.md has 979 words of instructions outside code blocks.
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 RefoundAI/lenny-skills at commit 13598cc, republished under its MIT licence (© RefoundAI). 979 words, ~1,688 tokens.
Download SKILL.mdSave it as
.claude/skills/evaluating-startup-ideas/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- evaluating-startup-ideas
- description
- Help users distinguish between deceptive tarpit ideas and high-potential opportunities by applying rigorous frameworks for market timing, business math, and user demand.
Evaluating Startup Ideas
Systematically validate problem-solution fit, market timing, and business viability before you build.
Help the user with evaluating startup ideas using insights from 21 guests and posts across Lenny's Podcast and Newsletter.
How to Help
- Assess Problem Urgency - Determine if you are solving a hair-on-fire problem or an incremental convenience.
- Analyze Market Timing - Evaluate if there is a clear why now inflection point in technology, regulation, or behavior.
- Review Business Viability - Scrutinize the underlying math to ensure a path to $100M in annual revenue.
- Validate via Experiments - Guide the transition from brainstorming to manual testing before committing to code.
Core Principles
Seek unglamorous niches
Andrew Wilkinson: "I think that's probably the most important thing in business is actually to find those niches where you can actually make real money because competition equals lower margin. The more competitors there are, the lower your prices have to be and the more competitive the business is ultimately."
Identify uncrowded industries like pest control or government software where lack of competition allows for higher margins and easier growth.
Prioritize autonomous outcomes
Bret Taylor: "First is, I think as you have these new technologies, rather than literally digitizing what came before, if you can create an entirely new experience, it answers the question for a new customer, why should I give this the time of day? And so, really disassembling the Lego set and reassembling into something new rather than just digitizing what was there before."
In the age of AI, the best opportunities lie in delivering autonomous results rather than just building productivity tools that require manual effort.
Wait for external turning points
Mike Maples Jr: "The three are inflections, insights and then the founder future fit. Business is never a fair fight. What inflections let the founder do is wage asymmetric warfare on the present."
Successful breakthroughs depend on identifying specific shifts in technology or behavior that allow a founder to challenge the status quo.
Validate demand before writing code
From "How to validate your B2B startup idea": "And then we got an email from an old Dropbox colleague who was like, ‘I hear you guys have become SOC 2 consultants. That’s super-weird. I thought you were going to do other things with your life. But also, can you come do this for my company?’ And that’s when it was like, no, but I’ll start writing code. That was the validation process for us."
Commit to building only after you have confirmed that users are willing to pay for or hire a manual version of your solution.
Look for polarizing signals
Sam Schillace: "And that bifurcation of love it, hate it, is really how you have an idea of whether you have impact in what you're building. If you get more of the bell curve of modern indifference and maybe mild like and mild dislike, that's an's an incremental product. That's not really disrupting anything."
True disruption is characterized by polarization where early users either love the product or hate it, rather than offering lukewarm acceptance.
Show full SKILL.md (470 more words)Show less
Templates & Frameworks
- Seven Patterns for Knowing When to Go All-In (How to validate your B2B startup idea) - Seven distinct patterns that convinced successful B2B founders to fully commit to their startup idea
- Five Strategies for Coming Up with a Consumer Startup Idea (How to kickstart and scale a consumer business) - A framework of five distinct strategies successful consumer founders used to generate their startup ideas, all rooted in 'paying attention'
- Three Signals of a Top 1% Startup (How to spot a top 1% startup early) - A three-part evaluation framework for identifying future generational companies early, derived from interviews with five people who repeatedly joined legendary
- Startup Evaluation Criteria (Priority-Ordered) (Lessons from 140+ angel investments) - Lenny's seven criteria for evaluating startups for angel investment, listed in priority order
- 'Why Now' Self-Assessment for Founders (Why now?) - Derived checklist for founders to evaluate their own 'why now' based on Lenny's research
- Three Questions to Test Venture-Scalability (Your startup idea probably isn’t venture-scale) - A self-assessment framework founders can use to determine if their idea qualifies for venture funding
- Schlep Blindness (Essential reading for product builders—part 2) - A mental model for recognizing that your unconscious mind filters out the most valuable startup ideas because they involve intimidating operational complexity.
- Three Ingredients of a Great B2B Startup Idea (How the most successful B2B startups came up with their original idea) - A framework for evaluating whether a B2B startup idea has the three essential ingredients to succeed
See references/artifacts.md for the full list with details.
Questions to Help Users
- "What is the specific inflection point that makes this idea viable today when it was not possible two years ago?"
- "Is the problem you are solving a hair-on-fire pain point that customers would beg to pay for?"
- "Have you spoken to at least 20 strangers who share this frustration to ensure the problem is widespread?"
- "Does the product provide a 10x better experience or a massive efficiency leap over current habits?"
- "Can you reach $100M in annual revenue based on the total number of reachable customers and your pricing model?"
- "Are you building for a demographic you belong to or understand intimately to gain an unfair insight?"
Common Mistakes to Flag
- Pursuing cool but crowded markets - High-competition industries like consumer social often have lower margins and higher failure rates than unglamorous niches.
- Trusting shallow positive feedback - Polite interest from friends or early testers can mask a lack of genuine willingness to pay or change habits.
- Ignoring the operational schlep - Founders often filter out the most valuable ideas because they involve intimidating operational complexities or non-coding work.
- Building solutions for made-up problems - Starting with a technology or a trend rather than a specific, painful problem leads to products that nobody actually needs.
Deep Dive
For all 48 sourced insights from 21 guests, see references/guest-insights.md
Related Skills
- Fundraising
- Founder Sales
© RefoundAI, 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 skills/evaluating-startup-ideas of RefoundAI/lenny-skills.
- SKILL.md
- references/artifacts.md
- references/guest-insights.md
Open the folder on GitHubat commit 13598cc
Compare with similar skills
Evaluating Startup Ideas 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Evaluating Startup Ideas this skillRefoundAI/lenny-skills | 1.4k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Idea Evaluatorsickn33/agentic-awesome-skills | 47k | 1 repos | ~930 | Automated safety check: Pass | MIT | |
| Idea Evaluator Prosickn33/agentic-awesome-skills | 47k | 1 repos | ~780 | Automated safety check: Pass | MIT | |
| Research Idea EvaluatorHKUSTDial/Supervisor-Skills | 8.5k | — | ~3.4k | Automated safety check: Pass | CC-BY-4.0 | |
| Arize Evaluatorgithub/awesome-copilot | 40k | 2 repos | ~8.1k | Automated safety check: Notes | MIT | |
| LLM Evaluationdavila7/claude-code-templates | 32k | 13 repos | ~3.5k | Automated safety check: Pass | MIT |
Similar skills
Idea Evaluator Pro
sickn33/agentic-awesome-skills
The Pro Agent persona for idea evaluation. An agent skill from sickn33/agentic-awesome-skills.
Research Idea Evaluator
HKUSTDial/Supervisor-Skills
Evaluates a draft research idea like a top-venue reviewer and advisor, scoring it on five dimensions, checking fit with your capacity and returning a clear verdict.
- Official
Arize Evaluator
github/awesome-copilot
Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and…
LLM Evaluation
davila7/claude-code-templates
Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.
Startup Idea Validator
mohitagw15856/pm-claude-skills
Pressure-test a startup idea the way a sharp investor or co-founder would — problem, market, wedge, moat, why-now, and the fastest cheap way to test it.
More from RefoundAI/lenny-skills
All 76 skills in this repoCustomer Interviews
RefoundAI/lenny-skills
Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.
Time Energy Management
RefoundAI/lenny-skills
Help users master their personal output by shifting from reactive scheduling to intentional energy management, internal trigger mastery, and proactive boundary setting.
User Onboarding Activation
RefoundAI/lenny-skills
Help users reach their first moment of core value by optimizing the first-run experience, removing friction, and aligning product design with psychological triggers.
Acquisition Channels
RefoundAI/lenny-skills
Help users identify unique distribution advantages and master the lifecycle of acquisition channels to build a sustainable engine for growth and retention.
AI Assisted Prototyping
RefoundAI/lenny-skills
Help users build functional product prototypes from natural language or visual mocks using AI coding tools.
AI Evals
RefoundAI/lenny-skills
Help users build robust infrastructure for measuring, monitoring, and iterating on AI product performance using human, code-based, and LLM-as-a-judge methodologies.
Questions about Evaluating Startup Ideas
What does Evaluating Startup Ideas do?
Help users distinguish between deceptive tarpit ideas and high-potential opportunities by applying rigorous frameworks for market timing, business math, and user demand. Evaluating Startup Ideas is an agent skill from RefoundAI/lenny-skills. Help users distinguish between deceptive tarpit ideas and high-potential opportunities by applying rigorous frameworks for market timing, business math, and user demand.
How do I install Evaluating Startup Ideas in Claude Code?
Run `npx skills add RefoundAI/lenny-skills --skill evaluating-startup-ideas -a claude-code`. Or copy the skill folder (skills/evaluating-startup-ideas in RefoundAI/lenny-skills) into .claude/skills/evaluating-startup-ideas in your project. Claude Code loads it when a task matches its description.
How do I install Evaluating Startup Ideas in Codex?
Run `npx skills add RefoundAI/lenny-skills --skill evaluating-startup-ideas -a codex`. Or copy the skill folder (skills/evaluating-startup-ideas in RefoundAI/lenny-skills) into .agents/skills/evaluating-startup-ideas in your project. Codex loads it when a task matches its description.
Can I use Evaluating Startup Ideas 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 RefoundAI/lenny-skills --skill evaluating-startup-ideas -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evaluating-startup-ideas, .gemini/skills/evaluating-startup-ideas, .github/skills/evaluating-startup-ideas and .opencode/skills/evaluating-startup-ideas in your project.
What does Evaluating Startup Ideas need to run?
SKILL.md names no scripts, command-line tools or credentials: Evaluating Startup Ideas is instructions for the agent only.
Does Evaluating Startup Ideas 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 Evaluating Startup Ideas 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 Evaluating Startup Ideas use?
Evaluating Startup Ideas 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 Evaluating Startup Ideas use?
About 1.7k tokens (SKILL.md is roughly 6.8k 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 33k tokens, read only when the agent opens those files.
What are the alternatives to Evaluating Startup Ideas?
Skills that share tags, products or a category with Evaluating Startup Ideas: Idea Evaluator (sickn33/agentic-awesome-skills, 47k stars), Idea Evaluator Pro (sickn33/agentic-awesome-skills, 47k stars), Research Idea Evaluator (HKUSTDial/Supervisor-Skills, 8.5k stars) and Arize Evaluator (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Evaluating Startup Ideas?
RefoundAI (a GitHub organization) maintains it in RefoundAI/lenny-skills, which has 1,377 GitHub stars. The repository holds 76 skills in this directory. The repository was last updated on July 16, 2026.
Source: RefoundAI/lenny-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.