abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Enumerate obstacles that block a target goal/direction, with type, evidence, and blocking relation.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-obstacles --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-obstacles -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-obstacles -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-obstacles -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-obstacles -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-obstacles -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill identify-obstacles -a windsurf -y
name: identify-obstacles description: "Enumerate obstacles that block a target goal/direction, with type, evidence, and blocking relation."
Enumerate obstacles blocking a target goal or direction, with evidence and blocking relations.
required: [target_goal, current_state, domain_context] optional: [timeline, resource_inventory, prior_failures] constraints: [each obstacle has type, evidence, and blocking relation]
1. Compare target requirements with current capabilities and constraints. 2. Enumerate technical, evidential, resource, temporal, and dependency obstacles. 3. Link each obstacle to blocked outcomes and supporting evidence. 4. Return severity, uncertainty, and candidate removal questions.
If obstacles have comparable evidence, severity, and tractability fields, consider `score-object` as the next tactic.
produces: [obstacle_register, blocking_relations, evidence_links, removal_questions] delta_fields: [findings, uncertainties, open_questions]
Caller supplies goal schema, obstacle taxonomy, evidence fields, severity scale, and merge policy.
Reject generic risks, unsupported blockers, or lists with no relation to the target goal.
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…