abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Design an intervention that prevents, detects, responds to, removes, or relaxes a failure mode/constraint; state residual risk and validation evidence.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill design-mitigation --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill design-mitigation -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill design-mitigation -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill design-mitigation -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill design-mitigation -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill design-mitigation -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill design-mitigation -a windsurf -y
name: design-mitigation description: "Design an intervention that prevents, detects, responds to, removes, or relaxes a failure mode/constraint; state residual risk and validation evidence."
Design an intervention that prevents, detects, responds to, removes, or relaxes a failure mode.
required: [failure_mode, causal_mechanism, resource_limits] optional: [existing_controls, timeline, acceptance_criteria] constraints: [residual risk and validation evidence must be explicit]
1. Classify the failure and locate controllable causal points. 2. Generate prevention, detection, response, removal, and relaxation options. 3. Sequence selected actions with resources and validation tests. 4. Estimate residual risk and define escalation conditions.
If the mitigation has an explicit mechanism and measurable target, consider `validate-mitigation-effect` as the next tactic.
produces: [mitigation_plan, validation_tests, residual_risk, success_criteria] delta_fields: [decisions, findings, uncertainties]
Caller supplies failure taxonomy, causal graph, intervention classes, resource schema, timeline, and risk scale.
Reject vague actions, controls that do not touch the mechanism, or plans without residual-risk accounting.
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…