abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Enumerate failure modes, trace cause-mode-effect chains, score risk, design mitigations, and re-evaluate residual risk.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill fmea-risk-analysis --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill fmea-risk-analysis -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill fmea-risk-analysis -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill fmea-risk-analysis -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill fmea-risk-analysis -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill fmea-risk-analysis -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill fmea-risk-analysis -a windsurf -y
name: fmea-risk-analysis description: "Enumerate failure modes, trace cause-mode-effect chains, score risk, design mitigations, and re-evaluate residual risk."
Enumerate failure modes, trace cause-mode-effect chains, score risk, design mitigations, and re-evaluate residual risk.
required: [system_or_process, functions, operating_conditions] optional: [failure_history, severity_scale, occurrence_scale, detectability_scale] constraints: [scales and scoring direction must be declared]
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `enumerate-failure-modes` to enumerate failure modes. You MUST load skill `build-failure-chain` to construct their propagation chains. 2. You MUST load skill `score-fmea-risk` to score severity, occurrence, detectability, and priority. 3. You MUST load skill `design-mitigation` to design mitigations. You MUST load skill `validate-mitigation-effect` to re-run the relevant test and validate the effect. If a failure chain requires explicit intervention counterfactuals, consider `counterfactual-causal-analysis` as the next tactic. Deviation: omit an unavailable score dimension only with an explicit unknown and no hidden imputation.
produces: [failure_mode_register, failure_chains, risk_scores, mitigation_plan, residual_risk_report] delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
Do not rank a failure mode without a cause/effect chain. Mark residual risk unknown when mitigation was not re-tested.
| source | source line | kind | source criterion | |---|---:|---|---| | v4 architecture | node desc | textual | Enumerate failure modes, score risk, mitigate, and re-evaluate residual risk. |
Append failure modes, chains, scores, mitigations, retest evidence, and residual uncertainties.
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…