abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Classify constraints as hard, soft, or assumption-like after explicit identification.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill classify-constraint --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill classify-constraint -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill classify-constraint -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill classify-constraint -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill classify-constraint -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill classify-constraint -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill classify-constraint -a windsurf -y
name: classify-constraint description: "Classify constraints as hard, soft, or assumption-like after explicit identification."
Classify each identified constraint as hard, soft, or assumption-like and make the consequence of that class explicit.
required: [constraint_candidates, evidence_register, decision_context] optional: [stakeholder_requirements, prior_constraint_ledger] constraints: [each candidate has a statement, scope, source, and consequence if violated]
1. Parse each candidate into condition, scope, source, and violation consequence. 2. Mark hard when violation is disqualifying and externally anchored; soft when tradeable; assumption-like when inferred and testable. 3. Record the evidence and counterevidence supporting the class. 4. Emit the classified ledger and tests or escalation required for uncertain classes.
produces: [constraint_ledger, classification_rationale, validation_actions] delta_fields: [findings, evidence_updates, assumption_updates, uncertainties, decisions]
Do not classify a preference as hard merely because it is strongly stated. Keep ambiguous constraints unresolved.
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…