abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Turn a research direction into an AND/OR goal DAG with testable leaves, dependency structure, and feasibility annotations.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-research-goal --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-research-goal -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-research-goal -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-research-goal -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-research-goal -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-research-goal -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill decompose-research-goal -a windsurf -y
name: decompose-research-goal description: "Turn a research direction into an AND/OR goal DAG with testable leaves, dependency structure, and feasibility annotations."
Turn a research direction into an AND/OR goal DAG with testable leaves, dependencies, and feasibility annotations.
required: [research_direction, constraints] optional: [actor_profile, obstacle_report, timeline, north_star] constraints: [goal wording, constraints, and source context must be explicit]
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `formulate-top-goal` to formalize the top goal and desired effect. 2. You MUST load skill `decompose-and-or-goal` to recursively construct AND/OR branches and executable leaves. 3. You MUST load skill `validate-goal-tree` to check leaf specificity, testability, coverage, and dependency consistency. 4. You MUST load skill `assess-goal-feasibility` to annotate feasibility and alternatives. 5. You MUST load skill `map-dependencies` to map the goal dependencies. You MUST load skill `crystallize-north-star` to compress the result into a North Star.
Deviation: Omit feasibility annotations when no actor, resource, or timeline constraints are supplied; mark the tree provisional rather than inventing constraints. Re-run only the affected branch after a decision changes its parent goal.
produces: [goal_tree_dag, executable_leaves, dependency_map, feasibility_annotations, research_north_star] delta_fields: [findings, hypothesis_updates, decisions, uncertainties, open_questions]
Reject trees with circular dependencies, vague leaves, or branches that cannot be tied to the declared direction. Do not treat a polished sentence as evidence that decomposition is complete.
| source | source line | kind | source criterion | |---|---:|---|---| | none retained | - | - | No source numeric/textual criterion retained after normalization. |
Append the goal DAG, leaf validation, feasibility annotations, dependency changes, and unresolved validation questions.
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…