agentleFS
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/assess-prior-art-and-claims/SKILL.md

assess-prior-art-and-claims

Skill504 starsChanged 52 days agoApache-2.0View on GitHub

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

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Distinctive:

    Do not perform called SOP operations inline.

    line 22
  2. Very specific:

    If the retained claims expose absent feature combinations, consider map-patent-white-space as the next tactic.

    line 29
  3. Distinctive:

    Every claim element must map to a cited source or be marked unsupported.

    line 42
  4. Distinctive:

    Do not call a claim novel because no result was found.

    line 48

≈ “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

assess-prior-art-and-claims

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.

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.