abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Move from symptoms to causal structure using complementary root-cause representations and causal-validity checks.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill drill-root-causes --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill drill-root-causes -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill drill-root-causes -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill drill-root-causes -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill drill-root-causes -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill drill-root-causes -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill drill-root-causes -a windsurf -y
name: drill-root-causes description: "Move from symptoms to causal structure using complementary root-cause representations and causal-validity checks."
Move from symptoms to causal structure using complementary root-cause representations and validity checks.
required: [symptoms_or_undesirable_effects] optional: [evidence, system_boundary, known_causes] constraints: [each causal edge needs an evidence or assumption label]
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `drill-five-whys` to drill repeated whys. 2. You MUST load skill `decompose-ishikawa` to decompose six causal categories. 3. You MUST load skill `build-current-reality-tree` to build the current-reality tree. 4. You MUST load skill `validate-causal-link` to validate its causal links. If the root-cause chain depends on untested assumptions, consider `assumption-stress-test` as the next tactic. Deviation: use fewer representations only when the input explicitly limits scope; record omitted views and reason.
produces: [why_chain, ishikawa_map, current_reality_tree, root_cause_set] delta_fields: [findings, assumption_updates, uncertainties, decisions, open_questions]
Do not call a correlation a root cause, or stop at a label that cannot explain the observed effects.
Append symptom changes, causal edges, competing roots, and validation failures.
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…