/classification-navigation
IPC/CPC hierarchy drill-down and lateral expansion for patent discovery
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill classification-navigation --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/classification-navigation
Context preview
The summary Claude sees to decide when to auto-load this skill.
IPC/CPC hierarchy drill-down and lateral expansion for patent discovery
SKILL.md
classification-navigation.SKILL.mdname: classification-navigation
description: IPC/CPC hierarchy drill-down and lateral expansion for patent discovery
execution: tactic
dependencies:
sops:
- knowledge-acquisition-saturation-detection
- patent-categorization
- patent-query-formulation
Classification Navigation
Navigates the IPC/CPC patent classification hierarchy to discover patents through structured taxonomy traversal — drilling down into subclasses and expanding laterally to related classes.
Stages
1. Top-Level Classification Identification
- Determine relevant IPC/CPC sections and classes from seed patents or technology description
- Map the technology domain to classification entry points
- Identify primary and secondary classification codes
2. Subclass Drill-Down
- For each identified class, drill into subclass, main group, and subgroup levels
- Assess patent density at each level
- Identify the most specific relevant classification codes
3. Lateral Expansion to Related Classes
- From identified subclasses, explore sibling and cousin classes
- Follow "see also" and "related" cross-references in classification schemes
- Identify adjacent technology areas that may contain relevant patents
4. Cross-Reference Validation
- Verify that lateral expansion yields relevant results
- Check that discovered classes actually contain patents related to the target technology
- Prune irrelevant branches and confirm final classification scope
Available SOPs
| SOP | Role | |-----|------| | patent-query-formulation | Generate IPC/CPC-based search queries | | patent-categorization | Validate classification relevance of found patents | | saturation-detection | Determine when classification space is fully explored |
Execution Guidance
- Start broad (section/class level) and narrow down based on relevance
- IPC and CPC diverge at subgroup level — check both schemes
- Pay attention to classification reform dates — codes may have changed
- Cross-references in CPC scheme definitions reveal non-obvious connections
- A single invention often spans 3-5 classification codes — always check secondary classifications
Yield Report
Report to calling strategy after each execution:
- Classification codes explored (with depth level)
- New relevant codes discovered
- Patent count per classification code
- Coverage assessment (% of relevant classification space explored)
<!-- BEGIN available-tables (generated) -->
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | knowledge-acquisition-saturation-detection | Determine when additional searching yields diminishing returns. Analyzes the latest expansion batch against existing corpus to judge continue/near-saturation/saturated. Used by snowball and systematic-survey. | | patent-categorization | Classify patents by tech subdomain, application scenario, and value chain position | | patent-query-formulation | Construct keyword + IPC/CPC + assignee combination search strategies for patent databases |
<!-- END available-tables (generated) -->
Read more
name: classification-navigation description: IPC/CPC hierarchy drill-down and lateral expansion for patent discovery execution: tactic dependencies: sops: - knowledge-acquisition-saturation-detection - patent-categorization - patent-query-formulation
Classification Navigation
Navigates the IPC/CPC patent classification hierarchy to discover patents through structured taxonomy traversal — drilling down into subclasses and expanding laterally to related classes.
Stages
1. Top-Level Classification Identification
- Determine relevant IPC/CPC sections and classes from seed patents or technology description
- Map the technology domain to classification entry points
- Identify primary and secondary classification codes
2. Subclass Drill-Down
- For each identified class, drill into subclass, main group, and subgroup levels
- Assess patent density at each level
- Identify the most specific relevant classification codes
3. Lateral Expansion to Related Classes
- From identified subclasses, explore sibling and cousin classes
- Follow "see also" and "related" cross-references in classification schemes
- Identify adjacent technology areas that may contain relevant patents
4. Cross-Reference Validation
- Verify that lateral expansion yields relevant results
- Check that discovered classes actually contain patents related to the target technology
- Prune irrelevant branches and confirm final classification scope
Available SOPs
| SOP | Role | |-----|------| | patent-query-formulation | Generate IPC/CPC-based search queries | | patent-categorization | Validate classification relevance of found patents | | saturation-detection | Determine when classification space is fully explored |
Execution Guidance
- Start broad (section/class level) and narrow down based on relevance
- IPC and CPC diverge at subgroup level — check both schemes
- Pay attention to classification reform dates — codes may have changed
- Cross-references in CPC scheme definitions reveal non-obvious connections
- A single invention often spans 3-5 classification codes — always check secondary classifications
Yield Report
Report to calling strategy after each execution:
- Classification codes explored (with depth level)
- New relevant codes discovered
- Patent count per classification code
- Coverage assessment (% of relevant classification space explored)
<!-- BEGIN available-tables (generated) -->
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | knowledge-acquisition-saturation-detection | Determine when additional searching yields diminishing returns. Analyzes the latest expansion batch against existing corpus to judge continue/near-saturation/saturated. Used by snowball and systematic-survey. | | patent-categorization | Classify patents by tech subdomain, application scenario, and value chain position | | patent-query-formulation | Construct keyword + IPC/CPC + assignee combination search strategies for patent databases |
<!-- END available-tables (generated) -->
The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.
Repo: yogsoth-ai/de-anthropocentric-research-engine
Other skills on de-anthropocentric-research-engine.
- /formated-results
Closing skill for the research-executor, loaded as the last step of formated-specs. Summarize the design just produced into one research-result JSON fenced block in your reply. Do not execute the research.
Open skill - /formated-specs
Spec-slot skill for the research-executor. Emit the 4-layer DARE orchestration of the assigned topic as one research-graph JSON fenced block in your reply. Replaces the generic spec-writing step.
Open skill - /injection-fidelity
Loss-1 judge (codex role). Given one sample's de-identified dialogue and its PolicyCard, decide axis-by-axis whether the user-simulator enacted the card's per-axis pressure. Judge enactment of the card, never whether the research is good.
Open skill - /ladder-quality-order
Loss-2 judge (codex role). Over one topic's 6 shuffled research-design samples, pairwise-rank by quality using the D1–D5 standard. Emit the pairwise log; the harness computes the order and the ladder verdicts. Judge quality difference, never against academic standards.
Open skill - /optimization-loop
The optimizer brain for the ladder-foundry pretraining loop. Runs the two-level nested batch loop, delegates gating to gate_eval, attributes a failing batch to one weight (attribute-first), and recovers from disk after compaction. Control flow is fully scripted; only the
Open skill - /acu-nugget-recall
Tactic: Extract atomic units from one paper and score how much of a caller-supplied summary covers. Use for ACU-style binary or Nugget-style ternary recall checks; cannot run without a target summary.
Open skill

