agent-auto-sci-methodology

Agent Auto Sci Methodology

Use this subskill when the research logic itself is uncertain or needs strengthening.

Fast Workflow

1. Convert broad interests into answerable research questions.
2. Define concepts, constructs, variables, mechanisms, and scope.
3. Generate competing hypotheses or explanations.
4. Choose design: review, observational, quasi-experimental, modeling, or mixed methods.
5. Audit bias, confounding, validity, and evidence strength.
6. Convert critique into concrete changes.

Read references/research_methodology_workflows.md.

For full paper projects, this skill owns topic selection, SMART research questions, hypothesis design, innovation diagnosis, feasibility, scope boundaries, conceptual framework, and reviewer-risk logic. When the task spans the whole manuscript lifecycle, coordinate through auto-sci-research/references/08_full_research_to_manuscript_pipeline.md.

For deeper K-Dense-style encapsulation:

• references/k_dense_methodology_mapping.md: how hypothesis generation, critical thinking, scholar evaluation, and peer-review logic are adapted.
• references/sport_geography_methodology_playbook.md: sport geography research questions, spatial justice, exposure mechanisms, bias, and evidence-grading playbook.

Related Helper Skills

• hypothesis-generation
• scientific-brainstorming
• scientific-critical-thinking
• scholar-evaluation
• statistical-analysis
• sport-geography-review-bibliometric

Must Not Do

• Do not turn a concept into a measurable variable without stating assumptions.
• Do not treat correlation, SHAP importance, or bibliometric co-occurrence as causal proof.
• Do not claim equity or justice from distribution maps alone.
• Do not hide uncertainty in policy language.