New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Patent Landscape Tools

by DrugClaw in DrugClaw/DrugClaw

Drug-patent landscape workflow guide for searching US patents via the PatentsView API, classifying pharmaceutical claim types (NCE, formulation, method-of-use, polymorph, combination, biologic…

Apache-2.0Auto-check passedLegal & Compliance

Install Patent Landscape Tools

skills CLI
$ npx skills add DrugClaw/DrugClaw --skill patent-landscape-tools -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install DrugClaw/DrugClaw patent-landscape-tools --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/DrugClaw/DrugClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'skills/science/patent(US)-landscape-tools' .claude/skills/patent-landscape-tools && rm -rf skills-src

Use ~/.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/

Facts

Skill name
patent-landscape-tools
GitHub stars
126
Token cost
~1.9k tokens
SKILL.md length
668 words
Files
2
Skills in repo
25
Repo updated
First seen
Licence
Apache-2.0

At a glance

Drug-patent landscape workflow guide for searching US patents via the PatentsView API, classifying pharmaceutical claim types (NCE, formulation, method-of-use, polymorph, combination, biologic…

  • Works in 6 steps: Always apply a pharmaceutical CPC filter… → Distinguish granted patents from… → Report the data source, query date, and… → …
  • The user asks about patent coverage
  • SKILL.md covers Working Rules, Environment Check, Bundled Assets and Patent Landscape Search, plus 7 more sections
  • Runs Python scripts from its folder; calls python3; reaches api.patentsview.org and api.fda.gov

What it does

Patent Landscape Tools is an agent skill from DrugClaw/DrugClaw. Drug-patent landscape workflow guide for searching US patents via the PatentsView API, classifying pharmaceutical claim types (NCE, formulation, method-of-use, polymorph, combination, biologic, process), grouping by patent family and assignee, estimating expiry timelines, and cross-referencing the FDA Orange Book for marketed-drug exclusivity windows. Use when the user asks about patent coverage, IP white-space, patent cliffs, or competitive filing activity around a drug, target, or compound class without asking…

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `template/patent(us)_landscape.py`).

It sits in Legal & Compliance, covering Intellectual property. The repository describes itself as: 💊 AI Research Assistant for Accelerated Drug Discovery. 🦞. The licence is Apache-2.0.

When your agent uses it

  • The user asks about patent coverage
  • Competitive filing activity around a drug
  • Compound class without asking for legal counsel

Example prompts

  • “/patent-landscape-tools”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Always apply a pharmaceutical CPC filter (A61K, A61P, or C07) to avoid non-drug noise.
  2. Distinguish granted patents from applications; PatentsView covers grants only.
  3. Report the data source, query date, and coverage limitation (US-only) in every output.
  4. Claim-type classification is heuristic from title and abstract keywords, not from reading claims.
  5. Expiry is estimated as filing date + 20 years; PTE, PTA, SPC, and terminal disclaimers are not computed.
  6. Do not present any output as freedom-to-operate analysis, legal advice, or infringement opinion.

What it can do on your machine

Read from SKILL.md and the folder at commit 960a6e0. 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

    Ships script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.patentsview.org
    • api.fda.gov

    Also links to:

    • patentsview.org
    • open.fda.gov
    • cooperativepatentclassification.org

    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

Patent Landscape Tools loads about 1.9k tokens when it runs. Until then it costs about 140 tokens; SKILL.md has 668 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~140
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 DrugClaw/DrugClaw at commit 960a6e0, republished under its Apache-2.0 licence (© DrugClaw). 668 words, ~1,882 tokens.

Download SKILL.mdSave it as .claude/skills/patent-landscape-tools/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
patent-landscape-tools
description
Drug-patent landscape workflow guide for searching US patents via the PatentsView API, classifying pharmaceutical claim types (NCE, formulation, method-of-use, polymorph, combination, biologic, process), grouping by patent family and assignee, estimating expiry timelines, and cross-referencing the FDA Orange Book for marketed-drug exclusivity windows. Use when the user asks about patent coverage, IP white-space, patent cliffs, or competitive filing activity around a drug, target, or compound class without asking for legal counsel.

Patent Landscape Tools

Use this skill for research-grade patent intelligence around drugs, targets, or mechanisms, not legal freedom-to-operate opinions.

Typical triggers:

  • search US patents related to a drug compound, target, or mechanism of action
  • classify pharmaceutical patents by claim type: NCE, formulation, method-of-use, polymorph, biologic, process
  • build a landscape summary showing filing trends, top assignees, and claim-type distribution
  • estimate patent expiry windows for one or more patent families
  • cross-reference the FDA Orange Book for a marketed drug's listed patents and exclusivity codes
  • identify IP white-space or under-patented mechanism classes before a new filing strategy

Working Rules

  1. Always apply a pharmaceutical CPC filter (A61K, A61P, or C07) to avoid non-drug noise.
  2. Distinguish granted patents from applications; PatentsView covers grants only.
  3. Report the data source, query date, and coverage limitation (US-only) in every output.
  4. Claim-type classification is heuristic from title and abstract keywords, not from reading claims.
  5. Expiry is estimated as filing date + 20 years; PTE, PTA, SPC, and terminal disclaimers are not computed.
  6. Do not present any output as freedom-to-operate analysis, legal advice, or infringement opinion.

Environment Check

bash
which python3 || true
python3 - <<'PY'
mods = ["requests"]
for name in mods:
    try:
        __import__(name)
        print(f"{name}: ok")
    except Exception as exc:
        print(f"{name}: missing ({exc})")
PY

If network access is unavailable, say so before claiming patent data was retrieved.

Bundled Assets

  • templates/patent_landscape.py

Use templates/patent_landscape.py for:

  • keyword + CPC-filtered patent search on PatentsView
  • automatic claim-type classification of each result
  • assignee ranking, filing-trend extraction, and family grouping
  • optional markdown landscape brief

Quick start:

bash
python3 templates/patent_landscape.py \
  --query "KRAS G12C inhibitor" \
  --cpc-filter A61K \
  --max-results 200 \
  --output patents/kras_g12c_landscape.csv \
  --summary patents/kras_g12c_summary.json \
  --brief patents/kras_g12c_brief.md

Broad landscape with date range:

bash
python3 templates/patent_landscape.py \
  --query "PD-1 antibody" \
  --cpc-filter A61K39 \
  --date-from 2015-01-01 \
  --max-results 500 \
  --output patents/pd1_ab_landscape.csv \
  --summary patents/pd1_ab_summary.json

Deliverables:

  • per-patent CSV with patent number, title, filing date, grant date, assignee, country, CPC, claim-type guess, estimated expiry year, and abstract snippet
  • summary JSON with total count, estimated family count, claim-type distribution, top assignees, country distribution, filing-year trend, and expiry window
  • optional markdown brief with tables and caveats

Expiry Timeline

Use templates/patent_landscape.py --mode expiry-timeline for:

  • patent expiry estimation sorted by earliest expiry
  • identification of upcoming patent cliffs for a compound or class
bash
python3 templates/patent_landscape.py \
  --query "semaglutide" \
  --mode expiry-timeline \
  --output patents/semaglutide_expiry.csv \
  --summary patents/semaglutide_expiry.json

Deliverables:

  • patent CSV sorted by estimated expiry year
  • summary JSON with total patents and timeline entry count

Orange Book Cross-Reference

Use --orange-book-query to add FDA Orange Book data for a marketed drug:

bash
python3 templates/patent_landscape.py \
  --query "semaglutide" \
  --mode expiry-timeline \
  --orange-book-query "semaglutide" \
  --output patents/semaglutide_expiry.csv \
  --summary patents/semaglutide_expiry.json

Orange Book entries include: brand name, generic name, NDA number, dosage form, route, and marketing status.

CPC Filter Reference

CPCScope
A61KPharmaceutical compositions (broadest drug filter)
A61K31Small-molecule active ingredients
A61K39Antibodies, vaccines, antigens
A61K47Excipients, carriers, formulation technology
A61PTherapeutic activity by indication
C07DHeterocyclic compounds (core scaffolds)
C07KPeptides and proteins
Show full SKILL.md (275 more words)Show less

Claim-Type Classification Heuristics

The template matches title + abstract keywords to assign one of:

  • NCE / composition-of-matter — compound, molecule, chemical entity, active ingredient
  • formulation — dosage form, tablet, capsule, nanoparticle, sustained release
  • method-of-use — method of treating, therapeutic use, for the treatment
  • polymorph / salt form — polymorph, crystal form, salt, co-crystal, hydrate
  • combination — combination, co-administration, synergistic
  • biologic — antibody, recombinant, fusion protein, monoclonal
  • diagnostic — biomarker, companion diagnostic, imaging agent
  • device / delivery — device, inhaler, auto-injector, applicator
  • process / manufacturing — synthesis, preparation, method of making

First match wins. Unmatched patents are labeled unclassified. This is not claim analysis.

Output Expectations

Good answers should mention:

  • the query terms, CPC filter, and date range applied
  • number of patent families and individual documents retrieved
  • claim-type distribution
  • top assignees with filing counts
  • filing trend by year
  • estimated expiry window for key families
  • Orange Book listings if queried
  • explicit caveat: US patents only, heuristic classification, not legal counsel
  • where the CSV, JSON, and optional brief were saved

For compound and regulatory lookups from ChEMBL, openFDA, ClinicalTrials.gov, activate pharma-db-tools. For target-level intelligence dossiers, activate target-intelligence-tools. For clinical-pipeline competitive analysis, activate competitive-intelligence-tools. For drug repurposing hypothesis generation, activate drug-repurposing-tools.

Reference

This skill queries the following public APIs:

  • USPTO PatentsView API — https://api.patentsview.org/patents/query — US granted-patent search with CPC, date, and full-text filters (patentsview.org/apis)
  • FDA openFDA drugsFDA API — https://api.fda.gov/drug/drugsfda.json — Orange Book product listings including brand/generic names, NDA numbers, dosage forms, and marketing status (open.fda.gov/apis/drug/drugsfda)
  • CPC classification scheme — Cooperative Patent Classification maintained by EPO and USPTO; A61K/A61P/C07 subclasses are used as pharmaceutical relevance filters (cooperativepatentclassification.org)
  • Claim-type classification heuristics are adapted from pharmaceutical IP landscape methodology described in: Dubey R, Maheshwari S. "Patent landscape analysis: A methodology for drug discovery." Drug Discovery Today, 2020.

© DrugClaw, Apache-2.0. 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 1 other file in skills/science/patent(US)-landscape-tools of DrugClaw/DrugClaw.

  • SKILL.md
  • template/patent(us)_landscape.py

Open the folder on GitHubat commit 960a6e0

Compare with similar skills

Patent Landscape Tools 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.

Patent Landscape Tools compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Patent Landscape Tools this skillDrugClaw/DrugClaw126—~1.9kAutomated safety check: PassApache-2.0
Paper to Chinese Patent DrafterYuan1z0825/nature-skills47k1 repos~1.1kAutomated safety check: PassApache-2.0
Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill1071 repos~959Automated safety check: PassNone
Patent Examinegfodor/legal-skills393—~4.8kAutomated safety check: PassGPL-3.0
Patent Auditgfodor/legal-skills393—~2.9kAutomated safety check: PassGPL-3.0
Replica BrandJakeschincariol/replica-skill1.4k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Paper to Chinese Patent Drafter

    Yuan1z0825/nature-skills

    Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.

    47k GitHub starsUsed in 1 repo~1.1k tokens
    Legal & ComplianceAuto-check passed

  • Paper To Cn Patent

    snipp-zha/Paper-to-patent-Skill

    Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts.

    107 GitHub starsUsed in 1 repo~959 tokens
    Legal & ComplianceAuto-check passed

  • Patent Examine

    gfodor/legal-skills

    Iteratively examine and revise a draft U.S. An agent skill from gfodor/legal-skills.

    393 GitHub stars~4.8k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

  • Patent Audit

    gfodor/legal-skills

    Audit a draft U.S. An agent skill from gfodor/legal-skills.

    393 GitHub stars~2.9k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

  • Replica Brand

    Jakeschincariol/replica-skill

    Names and rebrands an app clone so it is the user's own: name candidates with the trademark, domain, store and handle checks to run, a new palette checked for contrast, a logo brief, a voice guide…

    1.4k GitHub stars~1.1k tokensUpdated 8 days ago
    Legal & ComplianceAuto-check passed

  • Patent Workaround

    gfodor/legal-skills

    Adversarially pressure-test a draft or pending U.S. An agent skill from gfodor/legal-skills.

    393 GitHub stars~5.7k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

More from DrugClaw/DrugClaw

All 25 skills in this repo

  • Bio DB Tools

    DrugClaw/DrugClaw

    Query public biology databases and APIs including UniProt, RCSB PDB, AlphaFold DB, ClinVar, dbSNP, gnomAD, Ensembl, GEO, InterPro, KEGG, OpenTargets, Reactome, and STRING.

    126 GitHub stars~1.4k tokensUpdated 6 mo ago
    Auto-check passed

  • Grn Tools

    DrugClaw/DrugClaw

    Gene regulatory network workflow guide for transcriptomics and single-cell expression matrices using Arboreto, GRNBoost2, and GENIE3.

    126 GitHub stars~692 tokensUpdated 6 mo ago
    Auto-check passed

  • Knowledge Graph Tools

    DrugClaw/DrugClaw

    Drug-discovery knowledge-graph workflow guide for assembling drug-target-disease-pathway relationship graphs from OpenTargets GraphQL, ChEMBL REST, STRING PPI, and Reactome pathway APIs, then…

    126 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed

  • Literature Review Tools

    DrugClaw/DrugClaw

    Research-literature workflow guide for evidence-matrix assembly, citation-table normalization, structured review synthesis, and research-gap mapping.

    126 GitHub stars~923 tokensUpdated 6 mo ago
    Auto-check passed

  • Medical Data Tools

    DrugClaw/DrugClaw

    Medical data workflow guide for DICOM metadata inspection and basic de-identification, physiological signal analysis with NeuroKit2, and cohort-table profiling for clinical research datasets.

    126 GitHub stars~1.3k tokensUpdated 6 mo ago
    Auto-check passed

  • Omics Tools

    DrugClaw/DrugClaw

    Omics and single-cell workflow guide for AnnData, Scanpy-style dataset profiling, PyDESeq2-oriented count checks, pysam alignment inspection, and pyOpenMS mass-spectrometry summaries.

    126 GitHub stars~1.1k tokensUpdated 6 mo ago
    Auto-check passed

Categories

Questions about Patent Landscape Tools

What does Patent Landscape Tools do?

Drug-patent landscape workflow guide for searching US patents via the PatentsView API, classifying pharmaceutical claim types (NCE, formulation, method-of-use, polymorph, combination, biologic…. Patent Landscape Tools is an agent skill from DrugClaw/DrugClaw. Drug-patent landscape workflow guide for searching US patents via the PatentsView API, classifying pharmaceutical claim types (NCE, formulation, method-of-use, polymorph, combination, biologic, process), grouping by patent family and assignee, estimating expiry timelines, and cross-referencing the FDA Orange Book for marketed-drug exclusivity windows.

When should I use Patent Landscape Tools?

Patent Landscape Tools fits situations like: the user asks about patent coverage; competitive filing activity around a drug; compound class without asking for legal counsel.

How do I install Patent Landscape Tools in Claude Code?

Run `npx skills add DrugClaw/DrugClaw --skill patent-landscape-tools -a claude-code`. Or copy the skill folder (skills/science/patent(US)-landscape-tools in DrugClaw/DrugClaw) into .claude/skills/patent-landscape-tools in your project. Claude Code loads it when a task matches its description.

How do I install Patent Landscape Tools in Codex?

Run `npx skills add DrugClaw/DrugClaw --skill patent-landscape-tools -a codex`. Or copy the skill folder (skills/science/patent(US)-landscape-tools in DrugClaw/DrugClaw) into .agents/skills/patent-landscape-tools in your project. Codex loads it when a task matches its description.

Can I use Patent Landscape Tools 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 DrugClaw/DrugClaw --skill patent-landscape-tools -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/patent-landscape-tools, .gemini/skills/patent-landscape-tools, .github/skills/patent-landscape-tools and .opencode/skills/patent-landscape-tools in your project.

What does Patent Landscape Tools need to run?

Going by SKILL.md and its folder, Patent Landscape Tools needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Patent Landscape Tools access the network?

SKILL.md names 5 domains. In commands or code: api.patentsview.org and api.fda.gov; the agent is likely to contact these when it follows the instructions. As links in the text: patentsview.org, open.fda.gov and cooperativepatentclassification.org. This is read from the text; nothing was executed.

Is Patent Landscape Tools 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 Patent Landscape Tools use?

Patent Landscape Tools is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Patent Landscape Tools use?

About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Patent Landscape Tools?

Skills that share tags, products or a category with Patent Landscape Tools: Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 47k stars), Paper To Cn Patent (snipp-zha/Paper-to-patent-Skill, 107 stars), Patent Examine (gfodor/legal-skills, 393 stars) and Patent Audit (gfodor/legal-skills, 393 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Patent Landscape Tools?

DrugClaw (a GitHub organization) maintains it in DrugClaw/DrugClaw, which has 126 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on March 23, 2026.

Source: DrugClaw/DrugClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.