Hypothesis evolve inspiration
Skill panjose/Co-Scientist/skills/hypothesis-evolve-inspiration
Scientific agent skills for Claude Code and Codex that turn research goals into auditable hypothesis generation, review, ranking, evolution, and synthesis.
npx -y skills add panjose/Co-Scientist --skill hypothesis-evolve-inspirationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Generate exactly one cross-parent child hypothesis by transferring a useful principle from one parent context into another.
SKILL.md
3.1 KB, as published. Nobody here has run it
hypothesis-evolve-inspiration
Goal:
- Generate exactly one cross-parent child hypothesis by transferring a useful principle from one parent context into another.
Inputs:
research_plan/RESEARCH_PLAN.json- selected parent
hypotheses/<id>/HYPOTHESIS.jsonartifacts - parent review artifacts
- active
state/STRATEGY_PLAN.json
Outputs:
hypotheses/<id>/HYPOTHESIS.jsonhypotheses/<id>/HYPOTHESIS.mdhypotheses/<id>/ORIGIN.json
Context Loading:
- Open
skills/shared-references/schema-index.md. - Read
packages/agent_contracts/hypothesis.pyand confirm the exactHypothesisContractshape before writinghypotheses/<id>/HYPOTHESIS.json. - Read
research_plan/RESEARCH_PLAN.json. - Read
state/STRATEGY_PLAN.json. - Read the selected parent hypotheses and their review bundles.
- Confirm that the round selected
inspiration_evolution.
Execution Prompt Contract:
- System Intent:
- You are producing one novel child hypothesis by transferring a principle from one parent into another domain or mechanism context.
- Required Reasoning Focus:
- Name the borrowed principle.
- Keep the analogical leap explicit and testable.
- Produce a child that is genuinely new, not just a stitched paraphrase.
- Do Not Do:
- Do not copy one parent with cosmetic changes.
- Do not emit more than one child.
- Quality Floor:
- The child must directly address at least one specific weakness from the parent review bundle.
origin.content.statementmust name concrete materials, catalysts, reaction conditions, mechanistic variables, or experimental targets from the parent and research goal.origin.content.mechanismmust explain a causal chain; do not write only generic phrases such asimproved mechanism,targeted improvement, orreview-identified weaknesses.origin.content.experimental_designmust include 3-6 numbered steps with measurable readouts, controls, or decision thresholds.- Do not use generic refinement placeholder steps such as
Apply targeted improvement,Characterize with standard techniques,Benchmark against parent, orValidate improvement quantitatively. - If the research plan, parent hypothesis, or parent review bundle is missing, stop and report the missing artifact instead of guessing.
- Output Shape:
- Emit the canonical
HypothesisContract. origin.strategy:inspiration_evolution- Keep
summaryandcategoryspecific to the new cross-parent insight.
- Emit the canonical
Execution Steps:
- Open
skills/shared-references/schema-index.md, then readpackages/agent_contracts/hypothesis.pybefore writinghypotheses/<id>/HYPOTHESIS.json. - Identify the transferable principle across the parent set.
- Produce exactly one inspired child hypothesis.
- Persist canonical
HYPOTHESIS.json,HYPOTHESIS.md, andORIGIN.json. - Validate the emitted hypothesis artifact.
Completion Rule:
- This skill is complete only when one inspired cross-parent child hypothesis has been written in canonical form.