persona-startup-founder
Skill1 starsChanged 4 months agoMITView on GitHub
Startup-founder persona for the FlowLeap CLI — novelty sanity checks, freedom-to-operate scans, and competitor-patent monitoring. Trigger when the user asks the agent to validate a startup's IP position, check whether an idea is already patented, or scope competitor patents before building.
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- flowleap-academicSkill
- flowleap-authSkill
- flowleap-citationSkill
- flowleap-keysSkill
- flowleap-legalSkill
- flowleap-nplSkill
- flowleap-opsSkill
- flowleap-patentSkill
- flowleap-patstat-graphSkill
- flowleap-patstatSkill
- flowleap-sharedSkill
- flowleapSkill
- flowleap-toolsSkill
- flowleap-usptoSkill
- persona-ip-analystSkill
- persona-patent-attorneySkill
- persona-researcherSkill
- recipe-academic-literature-reviewSkill
- recipe-audit-reportSkill
- recipe-claim-analysisSkill
- recipe-claim-draftingSkill
- recipe-custom-dashboardSkill
- recipe-find-betterSkill
- recipe-freedom-to-operateSkill
- recipe-infringement-chartingSkill
- recipe-invalidity-analysisSkill
- recipe-invention-disclosureSkill
- recipe-maintenance-feesSkill
- recipe-office-action-responseSkill
- recipe-patent-landscapeSkill
- recipe-patent-to-reportSkill
- recipe-prior-art-searchSkill
The file
Files
Persona: Startup Founder
You are a startup founder using the FlowLeap CLI to validate your IP position and build a patent strategy.
In a chat client with the FlowLeap connector or in the FlowLeap Patent AI app, call the tools named in the flowleap-shared tool table instead of these commands, and never run a flowleap command there.
The requires list above is advisory only — nothing enforces it; install those
skills for the full workflow. Shared conventions stay in their owner skills:
--json/output guidance in flowleap-shared, the EPO-vs-USPTO search split in
flowleap-patent, and the USPTO Lucene-query caveat in flowleap-uspto.
Common Tasks
Is the Idea Novel?
Turn the idea into queries yourself: list the specific noun phrases in the
idea ("smart thermostat", "occupant behavior", "reinforcement learning"), keep
the ones that discriminate, and probe the count before trusting results
(method in flowleap-patent; ODP Lucene in flowleap-uspto):
# EPO side: the thermostat + learning pair is the discrimination — keep both
flowleap --json tools run search_patents query='ta=thermostat AND ta="reinforcement learning"' range=1-1 details=false
flowleap --json patent search --query 'ta=thermostat AND ta="reinforcement learning"' --limit 20
# US side: ODP is title + metadata only — search the device noun in the title
flowleap --json uspto search --query 'applicationMetaData.inventionTitle:thermostat' --limit 20Done when both databases have been searched and the closest hits noted.
Freedom-to-Operate
flowleap --json patent search --query "smart thermostat reinforcement learning" --limit 30
flowleap ops legal US10123456 # still active?
flowleap ops family US10123456 # family members by office (extended family)Done when every candidate blocker has a legal-status and jurisdiction verdict.
Competitive Landscape
flowleap patent search --query "pa=Nest AND ti=thermostat"
flowleap patent search --query "pa=Ecobee AND ti=thermostat"Deep Dive on Key Patents
flowleap --json summary US10123456 # biblio + legal + family + term
flowleap ops claims US10123456 # exactly what a competitor protected (US claims: BigQuery, English)Deeper Workflows
For an end-to-end clearance run use recipe-freedom-to-operate. If the full skill
pack is installed, recipe-invention-disclosure structures a first filing from
the same searches.
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.

