Skip to content
Automation
Skill

/construct-counterfactual

Construct the minimally or explicitly intervened counterfactual world required by the parent analysis.

From plugin
de-anthropocentric-research-engine
507200 skills

Claude Code

$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill construct-counterfactual --agent claude-code

SKILL.md

construct-counterfactual.SKILL.md
name: construct-counterfactual
description: "Construct the minimally or explicitly intervened counterfactual world required by the parent analysis."

construct-counterfactual

Purpose

Construct the minimally or explicitly intervened counterfactual world required by the parent analysis.

Input contract

required: [baseline_artifact, intervention_target, intervention_specification]
optional: [structural_model, invariants, outcome_query]
constraints: [alter only declared factors; preserve stated invariants]

Procedure

1. Freeze the baseline artifact and enumerate the target factor's dependencies. 2. Apply the intervention specification while holding declared invariants fixed. 3. Propagate direct and cascading effects through the structural model. 4. Compare queried outcomes and classify hold, weaken, flip, or indeterminate.

Output contract

produces: [counterfactual_world, changed_factors, cascading_effects, conclusion_status, consistency_check]
delta_fields: [findings, hypothesis_updates, uncertainties, open_questions]

Quality gates

  • The intervention is minimal or explicitly justified as non-minimal.
  • Every changed downstream variable has a propagation explanation.
  • Internal consistency and conclusion status are separately reported.

Parameterization

Caller supplies artifact schema, intervention grammar, invariants, propagation model, outcome query, and status vocabulary.

Failure and counterexamples

Reject worlds that silently alter non-target factors or violate declared structural constraints.

Provenance map

  • resolved: counterfactual-scenario-construction
Read more
@yogsoth-ai
Ships withde-anthropocentric-research-engine

A research skill graph for AI-native science. 271 markdown files. No runtime, no dependencies, no build step.

Stars on GitHub

Momentum

stars in total
507
Star history of yogsoth-ai/de-anthropocentric-research-engine on GitHub, a chart by star-history.com

More skills from other plugins.

agent-builder

agent-builder

Load immediately after an Agent intent, before the first agent_builder_* call. Governs how you create, configure, test, and…

n8n11d209k
@n8n-io@n8n-ioInstall Skill
browser-use

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…

@browser-use@browser-useInstall Skill
agent-browser

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…

@vercel-labs-2@vercel-labs-2Install Skill
add-anydoc

add-anydoc

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when…

@nanocoai@nanocoaiInstall Skill

Questions about construct-counterfactual.

Which coding agents can use construct-counterfactual?
construct-counterfactual installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.