Skip to content
Automation
Skill

/inventory-reference-items

Build a structured inventory of externally established reference items under a parent-specified schema, preserving applicability/status, key attributes, limitations, and provenance. Typical schemas include benchmark or known-solution/method family.

From plugin
de-anthropocentric-research-engine
512200 skills

Claude Code

$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill inventory-reference-items --agent claude-code

SKILL.md

inventory-reference-items.SKILL.md
name: inventory-reference-items
description: "Build a structured inventory of externally established reference items under a parent-specified schema, preserving applicability/status, key attributes, limitations, and provenance. Typical schemas include benchmark or known-solution/method family."

inventory-reference-items

Purpose

Build a structured inventory of externally established reference items under a caller-specified schema.

Input contract

required: [reference_items, item_schema, applicability_rules]
optional: [known_solutions, benchmarks, source_scope, status_vocabulary]
constraints: [preserve applicability, status, limitations, key attributes, and provenance for every item]

Procedure

1. Define the eligible reference universe and normalize item identifiers. 2. Extract schema fields, applicability, status, limitations, and provenance. 3. Deduplicate items without merging distinct benchmarks or methods. 4. Return the inventory with exclusions and unresolved provenance.

If reference items expose the metrics used for comparison, consider `decompose-evaluation-metric` as the next tactic.

Output contract

produces: [reference_inventory, applicability_map, limitation_register, provenance_index]
delta_fields: [findings, evidence_updates, uncertainties]

Quality gates

  • Every item has a stable identifier, source reference, applicability status, and limitation note.
  • Benchmark and known-solution inventories remain schema-distinct when their fields differ.
  • Missing fields are explicit; no benchmark or solution is inferred from a similar name.

Parameterization

The caller must provide item type, schema, eligible source scope, inclusion/status rules, canonical identifier policy, and required provenance fields.

Failure and counterexamples

Reject inventory entries with no provenance, mixed item types under one schema, or deduplication that removes a distinct reference item.

Provenance map

  • concept: knowledge-acquisition/benchmark-inventory
  • intermediate: Pass4/inventory-benchmarks
  • concept: creative-ideation/benchmark-inventory
  • intermediate: Pass4/inventory-known-solutions

Preserved source criteria ledger

No resolved v3 source node was present for these four entries; they remain explicitly marked concept/intermediate and are not replaced by a similarly named inventory.

Read more
@yogsoth-ai
Ships withde-anthropocentric-research-engine

A research skill graph for AI-native science. 271 markdown files. No runtime, no dependencies, no build step.

Stars on GitHub

Momentum

stars in total
512
Star history of yogsoth-ai/de-anthropocentric-research-engine on GitHub, a chart by star-history.com

More skills from other plugins.

agent-builder

agent-builder

Load immediately after an Agent intent, before the first agent_builder_* call. Governs how you create, configure, test, and…

n8n2w209k
@n8n-io@n8n-ioInstall Skill
browser-use

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…

@browser-use@browser-useInstall Skill
add-anydoc

add-anydoc

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when…

@nanocoai@nanocoaiInstall Skill

Questions about inventory-reference-items.

Which coding agents can use inventory-reference-items?
inventory-reference-items installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.