abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Construct an explicit set of scientifically relevant viewpoints, roles, worldviews, stakeholder positions, or epistemic lenses to apply to the same object.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-perspective-set --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-perspective-set -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-perspective-set -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-perspective-set -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-perspective-set -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-perspective-set -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-perspective-set -a windsurf -y
name: construct-perspective-set description: "Construct an explicit set of scientifically relevant viewpoints, roles, worldviews, stakeholder positions, or epistemic lenses to apply to the same object."
Construct an explicit set of relevant viewpoints or epistemic lenses for one object.
required: [target_object, perspective_basis, selection_goal] optional: [stakeholder_set, domain_roles, worldview_constraints] constraints: [each perspective must have a distinct warrant and scope]
1. Enumerate candidate roles, worldviews, and stakeholder positions. 2. Select a coverage-complete set and state inclusion rationale. 3. Record each lens's assumptions, objectives, and blind spots. 4. Return the set with mapping to the target object.
If the perspective set is sufficiently distinct and bounded, consider `rotate-perspective` as the next tactic.
produces: [perspective_set, selection_rationale, assumption_map, blind_spot_map] delta_fields: [findings, assumption_updates, uncertainties]
Caller supplies target schema, perspective taxonomy, minimum counts, relevance test, and overlap policy.
Reject decorative personas, duplicate lenses, or perspectives lacking a changed assumption or objective.
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…