abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Decompose a system into components/functions and record dependencies relevant to transformation.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-components --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-components -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-components -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-components -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-components -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-components -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-components -a windsurf -y
name: decompose-components description: "Decompose a system into components/functions and record dependencies relevant to transformation."
Decompose a system into components and functions, preserving dependencies relevant to transformation.
required: [system_or_design, decomposition_purpose] optional: [component_inventory, dependency_evidence] constraints: [components must have a function or interface and a parent relation]
1. Enumerate observable components and their functions. 2. Split compound components until each unit has a distinct transformation boundary. 3. Link dependencies, interfaces, and affected outcomes.
produces: [component_tree, function_map, dependency_map] delta_fields: [findings, assumption_updates, decisions]
Mark a component unresolved when its function or dependency cannot be evidenced; do not invent subcomponents.
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…