How do I install the Recipe Claim Drafting skill?

Run npx skillmds@latest add flowleap-ai/recipe-claim-drafting in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Recipe Claim Drafting safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Recipe Claim Drafting?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Recipe Claim Drafting free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Recipe Claim Drafting?

flowleap-ai (@flowleap-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Recipe Claim Drafting by flowleap-ai

Name: Recipe Claim Drafting
Author: flowleap-ai

Recipe Claim Drafting

Prosecution recipe for drafting patent claims grounded in prior art — search the closest art, study its claim language, decompose the invention into elements, iterate drafts through claim analysis, and check formal drafting rules against MPEP/EPO guidelines. Trigger when the user asks to draft or improve patent claims, write independent and dependent claims, or stress-test draft claims against known art and formal requirements.

flowleap-ai Updated Sep 17, 2026

File contents

Recipe: Claim Drafting

Draft claims that are novel over the closest art and formally sound.

Step 1: Find the Closest Art First

Claims drafted blind get rejected. Anchor on the art before writing:

Write the queries yourself, tuned precise — the goal is the closest few documents to read in full, so add a second discriminating ta term and probe the count down toward tens, not thousands (method in flowleap-patent):

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

Pull the claims of the 3-5 closest hits and study their language:

flowleap --json ops claims <closest-patent>
flowleap --json ops abstract <closest-patent>

Step 2: Element Inventory of the Invention

Write a one-paragraph invention summary, then decompose it yourself: list every element the invention needs to work (the mechanism, not the benefit), keep the language concrete, and note keywords and synonyms per element (the decomposition method is in recipe-claim-analysis, Step 4).

Sort the elements: which are old (in the closest art), which are the point of novelty. The independent claim needs the old elements for operability plus at least one novel element for allowance.

Step 3: Draft the Claim Set

Independent claim: preamble (technical field) + transition (comprising) + minimum element set that is both operable and novel
Dependent claims: one fallback feature each, ordered by commercial value — these are the amendment reservoir for prosecution
Draft method + apparatus (and CRM where relevant) parallel sets

Step 4: Check Formal Drafting Rules

# EPO clarity/support requirements
flowleap --json legal search "claim clarity conciseness support Article 84" --jurisdiction epo --comprehensive

# US definiteness and functional-language rules
flowleap --json legal search "claim definiteness functional language means plus function" --jurisdiction uspto --comprehensive

Check each claim against the found rules: antecedent basis, single-sentence form, no result-only language without structure, support in the description.

Step 5: Iterate Against the Art

For each draft independent claim, write a search from its novel element the same way as Step 1 — the novel element's phrase is the discriminating term:

flowleap --json patent search --query "<CQL written from the novel element>" --limit 10

If the searches surface art reading on the draft, narrow the novel element and repeat. Stop when the closest surfaced art clearly lacks an element.

Output

Closest-art table (reference, claim 1 language, what it lacks)
Element inventory split into old vs. novel
Full claim set (independent + dependents) with a support map into the description
Formal-rules checklist with legal citations per rule

---name: recipe-claim-draftingdescription: Prosecution recipe for drafting patent claims grounded in prior art — search the closest art, study its claim language, decompose the invention into elements, iterate drafts through claim analysis, and check formal drafting rules against MPEP/EPO guidelines. Trigger when the user asks to draft or improve patent claims, write independent and dependent claims, or stress-test draft claims against known art and formal requirements.---# Recipe: Claim DraftingDraft claims that are novel over the closest art and formally sound.## Step 1: Find the Closest Art FirstClaims drafted blind get rejected. Anchor on the art before writing:Write the queries yourself, tuned precise — the goal is the closest fewdocuments to read in full, so add a second discriminating `ta` term and probethe count down toward tens, not thousands (method in `flowleap-patent`):```bashflowleap --json tools run search_patents query='<self-written CQL>' range=1-1 details=falseflowleap --json patent search --query "<self-written CQL>" --limit 20flowleap --json uspto search --query "<self-written ODP Lucene>" --limit 20 # title + metadata only```Pull the claims of the 3-5 closest hits and study their language:```bashflowleap --json ops claims <closest-patent>flowleap --json ops abstract <closest-patent>```## Step 2: Element Inventory of the InventionWrite a one-paragraph invention summary, then decompose it yourself: listevery element the invention needs to work (the mechanism, not the benefit),keep the language concrete, and note keywords and synonyms per element (thedecomposition method is in `recipe-claim-analysis`, Step 4).Sort the elements: which are old (in the closest art), which are the point ofnovelty. The independent claim needs the old elements for operability plus atleast one novel element for allowance.## Step 3: Draft the Claim Set- **Independent claim**: preamble (technical field) + transition (`comprising`) + minimum element set that is both operable and novel- **Dependent claims**: one fallback feature each, ordered by commercial value — these are the amendment reservoir for prosecution- Draft method + apparatus (and CRM where relevant) parallel sets## Step 4: Check Formal Drafting Rules```bash# EPO clarity/support requirementsflowleap --json legal search "claim clarity conciseness support Article 84" --jurisdiction epo --comprehensive# US definiteness and functional-language rulesflowleap --json legal search "claim definiteness functional language means plus function" --jurisdiction uspto --comprehensive```Check each claim against the found rules: antecedent basis, single-sentenceform, no result-only language without structure, support in the description.## Step 5: Iterate Against the ArtFor each draft independent claim, write a search from its novel element thesame way as Step 1 — the novel element's phrase is the discriminating term:```bashflowleap --json patent search --query "<CQL written from the novel element>" --limit 10```If the searches surface art reading on the draft, narrow the novelelement and repeat. Stop when the closest surfaced art clearly lacks anelement.## Output- Closest-art table (reference, claim 1 language, what it lacks)- Element inventory split into old vs. novel- Full claim set (independent + dependents) with a support map into the description- Formal-rules checklist with legal citations per rule

Frequently asked questions