abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Generate a concrete executable attack/probe against a chosen threat surface.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill generate-attack-vector --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill generate-attack-vector -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill generate-attack-vector -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill generate-attack-vector -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill generate-attack-vector -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill generate-attack-vector -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill generate-attack-vector -a windsurf -y
name: generate-attack-vector description: "Generate a concrete executable attack/probe against a chosen threat surface."
Generate a concrete executable attack or probe against a chosen threat surface.
required: [threat_surface, target, attack_constraints] optional: [access_level, prior_findings] constraints: [attack must identify trigger, observable, and failure condition]
1. Select an exposed surface and attack objective. 2. Specify trigger, steps, observables, and failure interpretation. 3. Rank priority by information value and severity.
produces: [attack_vector, trigger, observable, failure_condition, priority] delta_fields: [findings, uncertainties, decisions]
Do not call a hypothetical weakness an attack result until executed.
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…