abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Recursively decompose a goal into an AND/OR DAG whose leaves are executable or testable subgoals.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-and-or-goal --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-and-or-goal -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-and-or-goal -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-and-or-goal -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-and-or-goal -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-and-or-goal -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-and-or-goal -a windsurf -y
name: decompose-and-or-goal description: "Recursively decompose a goal into an AND/OR DAG whose leaves are executable or testable subgoals."
Recursively decompose a goal into an AND/OR DAG whose leaves are executable or testable subgoals.
required: [top_goal, constraints] optional: [actor_profile, obstacle_report, existing_subgoals] constraints: [branch semantics, dependencies, and leaf criteria must be explicit]
1. Split the goal into necessary AND conditions and alternative OR paths. 2. Recurse until each leaf has an observable result or executable action. 3. Attach actors, dependencies, constraints, and unresolved feasibility to each branch. 4. Preserve shared subgoals as DAG nodes rather than duplicating them.
If the AND/OR decomposition is complete enough to test necessity and coverage, consider `validate-goal-tree` as the next tactic.
produces: [goal_dag, branch_semantics, executable_leaves, dependency_edges, feasibility_questions] delta_fields: [findings, hypothesis_updates, uncertainties, open_questions]
Do not split prose into labels without changing testability, and do not treat alternatives as simultaneous requirements.
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…