abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Maintain a diverse population of candidate solutions, mutate/recombine variants, select under explicit fitness and novelty criteria, and iterate while preserving useful niches rather than collapsing prematurely to one winner.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill evolve-solution-population --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill evolve-solution-population -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill evolve-solution-population -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill evolve-solution-population -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill evolve-solution-population -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill evolve-solution-population -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill evolve-solution-population -a windsurf -y
name: evolve-solution-population description: "Maintain a diverse population of candidate solutions, mutate/recombine variants, select under explicit fitness and novelty criteria, and iterate while preserving useful niches rather than collapsing prematurely to one winner."
Maintain diverse candidate solutions, mutate/recombine them, select under fitness and novelty criteria, and avoid premature convergence.
mode_contracts:
mutation-selection: &evolution_input
required: [initial_solution_population, fitness_criteria]
optional: [mutation_operators, novelty_criteria, iteration_budget]
constraints: [population_members_must_be_comparable_under_declared_criteria]
novelty-preserving-evolution: *evolution_inputDo not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
1. You MUST load skill `mutate-solution-population` to mutate or recombine the population. 2. You MUST load skill `select-solution-variants` to select solution variants. 3. You MUST load skill `measure-portfolio-diversity` to measure portfolio diversity. 4. You MUST load skill `assess-sensitivity` to assess selection sensitivity. 5. You MUST load skill `synthesize-idea` to synthesize the retained set. If the retained variants require an explicit final ordering, consider `rank-candidates` as the next tactic. Deviation: stop when added variation no longer changes the frontier or diversity objective; retain niche candidates when explicitly protected.
mode_contracts:
mutation-selection:
produces: [mechanism_to_design_mapping, generated_solutions, synthesis]
delta_fields: [findings, hypothesis_updates, uncertainties, decisions, open_questions]
novelty-preserving-evolution:
produces: [novelty_assessment]
delta_fields: [findings, hypothesis_updates, uncertainties, decisions, open_questions]Reject a single-winner result when novelty or niche preservation was required, and reject variants with untracked mutations.
Append population lineage, fitness changes, diversity deltas, and retained niches.
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…