idea-scoring
Skill8 starsChanged 3 months agoMITView on GitHub
Score and rank a shortlist of startup ideas to decide which one to build. Use when the user has several candidate ideas and asks "which idea should I pick," "how do I prioritise these," "how do I choose between ideas," or mentions scoring, ranking, or culling a list. This is the "Order & Cull" stage of the B.R.O.T.H. framework. For generating the shortlist, see founder-market-fit and trend-research. For picking the entry angle once an idea is chosen, see market-entry-strategies.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Latifox/find-me-saastheir own version, first seen Sep 6, 2026
- MaxKmet/idea-validation-agentstheir own version, first seen Apr 15, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- MaxKmet/idea-validation-agents★ 449same name
- Latifox/find-me-saas★ 10same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- cold-dmSkill
- content-sellingSkill
- discovery-callsSkill
- follow-up-sequencesSkill
- keyword-searchSkill
- profile-optimizationSkill
- prospecting-listsSkill
- context-engineeringSkill
- design-docSkill
- discussSkill
- grillingSkill
- llm-wikiSkill
- opencode-sessionsSkill
- playwright-cliSkill
- pr-descriptionSkill
- demand-first-validationSkill
- founder-market-fitSkill
- market-entry-strategiesSkill
- ship-v1Skill
- trend-researchSkill
- tiger-style-codingSkill
- voicenotesSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Before scoring, widen the field so you are choosing from the best options, not the first few.
- Distinctive: line 38
When ranking, weigh two different kinds of hard.
- Distinctive: line 51
Run a Deep Research expansion to widen and deepen the field.
- Distinctive: line 54
Commit to the top one or two.
- Distinctive: line 58
Do not skip the expansion and score only your first three ideas.
- Distinctive: line 59
Do not ignore "most interesting." An idea you find dull will die of neglect.
- Distinctive: line 60
Do not chase the highest market-size score alone.
- Distinctive: line 61
Do not keep everything. The output of this stage is a decision, not a longer list.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Idea Scoring (Order & Cull)
You help the user go from a long list of researched ideas down to the one worth building. Good techniques make finding ideas easy, sometimes too easy. This stage is the discipline that whittles the pile down to a single committed direction.
The scoring model
Score each candidate idea from 1 to 5 on four questions. Higher is better.
- Biggest market size? Is there enough demand and enough addressable spend to reach roughly $10k MRR?
- Lowest competition? Is the market proven but not saturated, with a visible gap to enter through? (Some competition is good; a crowded field with no gap is not.)
- Most interesting? Will you still care in 12 months? Boredom kills bootstrapped projects as reliably as no demand.
- Can I build it? Does it fit your skills and constraints, or can you realistically learn what's missing?
Total the four scores per idea. Rank the list. The top one or two graduate to strategy.
How to expand before you cull
Before scoring, widen the field so you are choosing from the best options, not the first few. Use Deep Research (or your LLM's equivalent) with the keywords and competitor list from earlier stages.
Prompt shape:
"Here are my target market, the problems, and a list of competitors: [paste]. Do deep research to expand this into a fuller set of opportunities. For each: estimate market size and demand signals, list direct and indirect competitors, note how saturated it is and where the gaps are, and flag how hard it would be to validate and to build. End with an opinionated view of the two or three biggest opportunities and why."
Expected outputs from that research:
- Deeper competitor analysis per direction
- An opinionated view of the biggest opportunities
Then you score the expanded set, not just your original hunches.
Validation difficulty vs execution difficulty
When ranking, weigh two different kinds of hard. An idea can be easy to validate but hard to build, or vice versa. The three archetypes:
| Entry type | Validation difficulty | Execution difficulty |
| Direct competitor (go at a proven market) | Easiest | Hardest (you must be genuinely better or cheaper) |
| Indirect competitor (adjacent market) | Medium | Medium |
| Growing trend (early mover) | Hardest (demand not yet proven) | Easiest, and first-mover advantage if you are right |
There is no free lunch: the easier something is to validate, the harder it usually is to execute against entrenched players, and vice versa. Pick the trade-off that matches your strengths, then confirm the specific angle in market-entry-strategies.
Workflow
- Gather surviving candidates from research.
- Run a Deep Research expansion to widen and deepen the field.
- Score every candidate 1 to 5 on market size, competition, interest, and buildability.
- Overlay the validation-vs-execution trade-off.
- Commit to the top one or two. Cull the rest without regret.
What NOT to do
- Do not skip the expansion and score only your first three ideas. You will miss better ones.
- Do not ignore "most interesting." An idea you find dull will die of neglect.
- Do not chase the highest market-size score alone. A huge market you cannot enter or cannot stand is worthless.
- Do not keep everything. The output of this stage is a decision, not a longer list.
Related skills
- founder-market-fit and trend-research - produce the candidates this stage ranks
- market-entry-strategies - choose the angle for the idea you commit to
- ship-v1 - build the winner
- demand-first-validation - the mindset check underlying every score
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.