abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Map candidate research fields or subfields, their maturity, competition, entry barriers, and opportunity structure. Evidence/tool acquisition is host-selected.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-research-landscape --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-research-landscape -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-research-landscape -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-research-landscape -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-research-landscape -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-research-landscape -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-research-landscape -a windsurf -y
name: map-research-landscape description: "Map candidate research fields or subfields, their maturity, competition, entry barriers, and opportunity structure. Evidence/tool acquisition is host-selected."
Map candidate research fields or subfields, maturity, competition, entry barriers, tractability, and opportunity structure.
required: [research_intent, scope_anchor] optional: [actor_profile, seed_evidence, constraints] constraints: [candidate fields require evidence references and declared comparison dimensions]
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `generate-candidate-directions` to generate diverse candidate fields and deliberate boundary crossings. 2. You MUST load skill `synthesize-field-panorama` to synthesize maturity, competition, entry-barrier, tractability, and opportunity evidence. If the resulting fields must be ordered, screened, or selected under explicit criteria, consider `rank-candidates` as the next tactic.
Deviation: Evidence acquisition is host-selected; do not invoke removed tool wrappers. Re-run candidate generation only when intent or scope changes materially.
produces: [candidate_field_set, field_panorama, maturity_map, competition_map, opportunity_structure] delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
Reject niche lists with no evidence, maturity claims based on publication volume alone, and opportunity claims that omit competition or entry barriers.
| source | source line | kind | source criterion | |---|---:|---|---| | none retained | - | - | No source numeric/textual criterion retained after normalization. |
Append candidate fields, evidence references, dimension assessments, boundary-crossing rationale, and unresolved acquisition questions.
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…