abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Define research questions, evidence scope, queries/concepts, inclusion/exclusion rules, provenance requirements, and stopping evidence for an acquisition task.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill define-evidence-protocol --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill define-evidence-protocol -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill define-evidence-protocol -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill define-evidence-protocol -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill define-evidence-protocol -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill define-evidence-protocol -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill define-evidence-protocol -a windsurf -y
name: define-evidence-protocol description: "Define research questions, evidence scope, queries/concepts, inclusion/exclusion rules, provenance requirements, and stopping evidence for an acquisition task."
Define research questions, eligible evidence scope, query concepts, inclusion/exclusion rules, provenance requirements, and stopping evidence.
required: [research_question, evidence_scope, inclusion_rules] optional: [exclusion_rules, query_concepts, quality_rubric, stopping_policy] constraints: [eligible universe, provenance fields, and stopping evidence must be explicit]
1. State the question, target population or domain, comparison, outcomes, and time boundaries. 2. Define eligible evidence, exclusion rules, source-independence requirements, and extraction fields. 3. Specify batch boundaries, novelty dimensions, and relative stopping evidence. 4. Record unresolved scope choices before acquisition begins.
If the protocol fixes inclusion, exclusion, and stopping rules, consider `select-seed-evidence` as the next tactic.
produces: [evidence_protocol, eligible_universe, query_concepts, screening_rules, provenance_requirements, stopping_evidence] delta_fields: [decisions, assumption_updates, uncertainties, open_questions]
Do not use provider names as a protocol, and do not declare coverage from search volume without a defined eligible universe.
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…