abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Identify relevant variables/factors and annotate functional roles.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-variables --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-variables -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-variables -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-variables -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-variables -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-variables -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-variables -a windsurf -y
name: identify-variables description: "Identify relevant variables/factors and annotate functional roles."
Identify relevant variables, factors, conditions, and assumptions and annotate their functional roles.
required: [artifact_or_system, target_claim_or_outcome] optional: [causal_claims, domain_schema, candidate_factors] constraints: [include explicit and implicit factors; each variable has a role, provenance, and suspected importance]
1. Parse the target claim or outcome and list quantities that could support, alter, or confound it. 2. Enumerate explicit and implicit variables, factors, conditions, and assumptions. 3. Classify functional roles such as causal variable, factor, design dimension, mediator, moderator, or confounder. 4. Attach provenance and suspected importance and return the structured variable list.
If variables and their roles are defined well enough to assert directional relations, consider `represent-mechanism-edge` as the next tactic.
produces: [variable_register, role_annotations, provenance_links, importance_notes] delta_fields: [findings, evidence_updates, uncertainties, open_questions]
The caller must provide the artifact/system description, target claim or outcome, optional causal claims, role ontology, domain vocabulary, and any candidate-factor list to reconcile.
Reject when a variable has no relation to the target outcome, a role is assigned without evidence, or a confounder is silently treated as a cause.
| source | physical line | kind | source criterion | |---|---:|---|---| | stress-test/factor-enumeration | 18 | structural | List all factors, conditions, and assumptions supporting the artifact conclusion, including explicit and implicit entries and suspected importance. |
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…