agentleFS
flowleap-aiflowleap-ai/flowleap-cli/skills/recipe-invention-disclosure/SKILL.md

recipe-invention-disclosure

Skill1 starsChanged 4 months agoMITView on GitHub

Prosecution recipe for turning an inventor conversation into a complete invention disclosure form (IDF) — structured technical capture, bar-date audit, novelty pre-check across patents and literature, landscape context, and a filing recommendation. Trigger when the user asks to document an invention, create an invention disclosure, or run a pre-filing novelty sanity check.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write the queries yourself from the Step 1 capture — the "key elements" list is your term extraction.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Recipe: Invention Disclosure (IDF)

Capture an invention completely enough that an attorney can draft from it.

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 steps stay the same.

Step 1: Structured Capture

Interview for these sections (push past marketing language to mechanisms):

  1. Problem — what fails today, and why existing approaches fall short
  2. Prior approaches — what the inventors know exists, including their own earlier work
  3. The inventive concept — the mechanism of the solution, not the benefit
  4. Key elements — minimum set needed for the invention to work
  5. Variations — alternative embodiments, ranges, materials, algorithms
  6. Evidence — prototypes, test data, figures
  7. People and dates — inventors and contribution; conception date; any public disclosure, sale, offer, or publication with dates (bar dates differ by jurisdiction — flag anything older than 12 months)

Step 2: Novelty Pre-Check

Write the queries yourself from the Step 1 capture — the "key elements" list is your term extraction. Keep the phrases that discriminate (the mechanism, not the benefit), probe the count, then search both offices (method in flowleap-patent; the disclosure never has to leave the machine to become a query):

flowleap --json tools run search_patents query='<self-written CQL>' range=1-1 details=false
flowleap --json patent search --query "<self-written CQL>" --limit 20
flowleap --json uspto search --query "<self-written ODP Lucene>" --limit 20   # title + metadata only

# Literature — inventors' own field publishes here first
flowleap --json academic search "<concept keywords>" --limit 15
flowleap --json npl "<concept keywords>" --limit 10

For anything close, pull claims and record how the invention differs:

flowleap --json ops claims <close-patent>

This is a sanity check, not a professional prior-art search — say so in the IDF.

Step 3: Landscape Context

flowleap --json analytics --keyword "<technology>" --date-from 2018-01-01

Filing trends and top assignees tell the reviewer whether this space is crowded, growing, or abandoned — context for the filing decision.

Step 4: Assemble the IDF

Sections: title; inventors + contributions; problem; prior approaches (including Step 2 findings with the differences recorded); detailed description of the inventive concept; key elements; variations; evidence; disclosure/bar-date audit; landscape summary.

Step 5: Recommendation

Close with one of: file now (novelty check clean, bar clock running), develop further (concept not yet enabled), or defensive publication (crowded space, low claim scope) — with the reasoning.

Output

A complete IDF document plus the raw novelty pre-check data (queries used, hits reviewed, differences noted) as an appendix.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.