abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Formalize a research goal as an outcome, desired effect, and explicit constraints.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill formulate-top-goal --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/formulate-top-goalContext preview
The summary Claude sees to decide when to auto-load this skill.
Formalize a research goal as an outcome, desired effect, and explicit constraints.
name: formulate-top-goal description: "Formalize a research goal as an outcome, desired effect, and explicit constraints."
Formalize a research goal as an outcome, desired effect, and explicit constraints.
required: [research_intent] optional: [actor_profile, constraints, evidence_context] constraints: [goal wording must identify an observable outcome and relevant boundary conditions]
1. State the outcome that should change and the desired direction of change. 2. Identify scope, actors, resources, time, and non-negotiable constraints. 3. Separate goal content from proposed methods and assumptions. 4. Emit a testable top-goal statement with unresolved choices.
If the top goal has explicit success conditions but remains too broad to execute, consider `decompose-and-or-goal` as the next tactic.
produces: [top_goal, desired_effect, constraint_set, goal_assumptions, open_goal_questions] delta_fields: [findings, hypothesis_updates, assumption_updates, decisions, uncertainties, open_questions]
Do not accept "understand the topic" as a top goal without an outcome or decision target.
The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.
Repo: yogsoth-ai/de-anthropocentric-research-engine
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, outcome, timeframe, system…
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target, escalation depth,…
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.