assess-prior-art-and-claims

SkillMonitoring & ops

Lets your agent assess patent claim novelty and prior art by breaking down claims and tracing patent families.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the assess-prior-art-and-claims skill

About this skill

Assess novelty/prior art and claim scope by decomposing claims, tracing relevant families, and checking status/provenance.

What this skill tells your AI

The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/assess-prior-art-and-claims/SKILL.md and read by ahel’s review.

Purpose

Assess novelty, prior art, claim scope, legal-status observations, and provenance without making unsupported legal conclusions.

Input contract

required: [claim_set, target_domain, jurisdiction_scope]
optional: [known_families, search_context, evidence_records]
constraints: [claim text and source provenance required, jurisdiction and observation date must be explicit]

Execution protocol

Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.

  1. You MUST load skill parse-patent-claim to parse independent and dependent claims and map elements to technical functions.
  2. You MUST load skill trace-patent-family to trace priority, family, continuation, and citation relationships.
  3. You MUST load skill assess-patent-claim-scope to assess breadth, limiting elements, overlap, and design-around vulnerability.
  4. You MUST load skill assess-patent-legal-status to classify observed status by jurisdiction and date.
  5. You MUST load skill verify-evidence-independence to check source independence before synthesizing novelty findings. If the retained claims expose absent feature combinations, consider map-patent-white-space as the next tactic.

Deviation: Skip status or independence checks only when the corresponding input is absent; record the omission as an open question. Do not infer legal status from an undated or single-source record.

Output contract

produces: [claim_element_map, prior_art_family_map, scope_assessment, legal_status_observations, novelty_findings]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]

Thresholds and quality gates

  • Every claim element must map to a cited source or be marked unsupported.
  • Any acquisition threshold must use a declared eligible family/source universe and relative coverage, not a fixed historical count.
  • Status observations require jurisdiction, observation date, source, and uncertainty.

Failure and counterexamples

Do not call a claim novel because no result was found; mark search coverage and unresolved elements. Do not collapse related family members into one record when claim scope or jurisdiction differs.

Provenance map

  • resolved: prior-art-search
  • resolved: knowledge-acquisition-claim-analysis
  • resolved: knowledge-acquisition-claim-decomposition
  • resolved: claim-parsing
  • resolved: legal-status-assessment

Preserved source criteria ledger

sourcesource linekindsource criterion
claim-analysis4435numeric/textualBudget 30 families / 30 claim / 20 web; HARD-GATE.

Context checkpoint / Delta notes

Append claim elements, family links, scope uncertainties, status observations, source-independence judgments, and unresolved search questions.

Signals

GitHub stars
501
Forks
41
Last commit
Sep 2026
Advanced
Catalog kind
skill
Key
assess-prior-art-and-claims
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine