brycewang-stanford/Auto-Empirical-Research-Skills

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Proposes causal identification strategies. Given a research question, literature, and data, designs the empirical approach including estimand, estimator, assumptions, robustness plan, and falsification tests. Produces a strategy memo. Use when designing identification strategy or drafting a pre-analysis plan.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Manuscript polish critic. Reviews paper manuscripts and talks for grammar, typos, LaTeX compilation, overfull hboxes, claims-evidence alignment, hedging language, and notation consistency. Paired critic for the Writer.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Drafts paper sections with proper academic structure. Enforces anti-hedging rules, consistent notation, effect sizes with units, and contribution statement in first 2 pages. Runs humanizer pass to strip AI writing patterns. Use when drafting or revising paper sections.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Performs iterative QA review of executed scripts. Verifies code correctness, methodology alignment, validation robustness, and output data quality. Creates parallel QA inspection scripts. Invoked by orchestrator after each Stage 5-8 script execution. Also performs QA review of profiling scripts during Data Onboarding…

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Systematically profiles tabular datasets across four structured parts (Structural, Statistical, Relational, Interpretation), producing detailed findings that feed into skill authoring. Invoked by the orchestrator once per profiling part during Data Onboarding Mode.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Creates comprehensive research plans (Plan.md) and executable task sequences (PlanTasks.md) with wave-based parallelization. Invoked by orchestrator at Stage 4 after discovery phases complete. Also handles plan revisions when plan-checker or user identifies issues.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Performs adversarial goal-backward verification of completed analyses. Verifies artifact existence, substantiveness, wiring, and cross-artifact coherence. Invoked by orchestrator at Stage 12 (Final Review) before delivery.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Diagnoses data quality issues and analysis failures using scientific hypothesis-testing methodology. Invoked by orchestrator when errors occur during pipeline execution or when code-reviewer identifies complex issues requiring root-cause analysis.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Modifies DAAF framework artifacts (skills, agents, modes, reference files, hooks) with template compliance, cross-file consistency, and integration checklist execution. Invoked during Framework Development mode for authoring, editing, and wiring framework components.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Validates that analysis components are properly connected by tracing data flows, verifying file references resolve, and detecting orphaned components. Invoked by orchestrator at Stages 9, 11, and 12 to confirm end-to-end pipeline wiring.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Compiles executed scripts into a Marimo notebook by literally copying script file contents into cells. Does not generate new analysis code, dashboards, or interactive widgets. Invoked at Stage 9 after all Stage 5-8 scripts and QA substages are complete.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Verifies research plans will achieve analysis goals before execution begins. Performs goal-backward analysis across six dimensions (completeness, consistency, feasibility, testability, clarity, scope). Invoked by orchestrator at Stage 4.5 after data-planner creates Plan.md and PlanTasks.md.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Synthesizes all pipeline artifacts into a stakeholder-appropriate report following REPORTTEMPLATE.md. Invoked at Stage 11 after QA aggregation (Stage 10) completes and before final review (Stage 12).

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Executes data acquisition, cleaning, transformation, and visualization tasks with atomic precision. Spawned by orchestrator for Stages 5-8 operations. Each invocation performs exactly ONE operation with pre/post validation.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Consolidates findings from parallel Stage 2-3 exploration tasks into actionable guidance for planning. Resolves conflicts between data sources, documents uncertainty, and produces structured recommendations. Invoked at Stage 3.5 when multiple sources have been explored and findings need integration before Plan…

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Performs read-only exploration of codebases, documentation, datasets, and web sources to locate specific information. Invoked by the orchestrator in place of generic Plan or Explore subagent types when targeted or broad search is needed during any mode or pipeline stage.

brycewang-stanford/Auto-Empirical-Research-Skills

Agent Claude Code

Performs deep-dive investigation of a single data source's structure, caveats, coded values, and pitfalls. Used across multiple engagement modes: Full Pipeline (Stage 3), Data Discovery, and Data Lookup (deep lookup). Each invocation focuses on exactly one data source.