abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Construct an acyclic is-a/part-of/instance-of hierarchy with explicit roots, depth, and transitivity constraints.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-hierarchy --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-hierarchy -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-hierarchy -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-hierarchy -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-hierarchy -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-hierarchy -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-hierarchy -a windsurf -y
name: construct-hierarchy description: "Construct an acyclic is-a/part-of/instance-of hierarchy with explicit roots, depth, and transitivity constraints."
Construct an acyclic is-a/part-of/instance-of hierarchy with explicit roots, depth, and transitivity constraints.
required: [entity_set, relation_assertions, hierarchy_scope] optional: [root_policy, multiple_inheritance_policy, depth_limit] constraints: [relations use declared types; cycles are invalid]
1. Normalize entity identifiers and relation types. 2. Insert high-confidence edges and infer only declared transitive edges. 3. Detect cycles, orphan nodes, missing intermediate levels, and root violations. 4. Repair or quarantine invalid edges, then emit roots, depth, and edge rationale.
If the hierarchy is complete enough to test for cycles, orphans, and incompatible parentage, consider `audit-structure-consistency` as the next tactic.
produces: [hierarchy_graph, roots, depth_report, cycle_report, edge_rationales] delta_fields: [findings, evidence_updates, uncertainties]
Caller supplies entity schema, relation ontology, root and multiple-inheritance policies, transitivity rules, and depth limit.
Reject an edge that creates a cycle or conflates is-a with part-of.
| source | criterion | |---|---| | hierarchy-construction | Acyclic always; cycles are logical errors. | | hierarchy-construction | Multiple inheritance is allowed. | | hierarchy-construction | Depth <=5 unless explicitly justified. |
A research skill graph for AI-native science. 271 markdown files. No runtime, no dependencies, no build step.
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context,…
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target,…
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…