pi-maestro-flow 0.2.0

package/skills/scholar-experiment/SKILL.md

@@ -0,0 +1,321 @@
+---
+name: scholar-experiment
+description: "Systematic experimental results analysis workflow for ML/AI research papers. Connects experimental data to publication-ready Results sections with statistical validation, visualizations, and quality checks. Triggers on \"analyze experimental results\", \"generate results section\", \"statistical analysis of experiments\", \"compare model performance\", \"create results visualization\"."
+allowed-tools: Read Write Edit Bash Glob Grep AskUserQuestion TodoWrite
+---
+
+# Scholar Experiment: Results Analysis Workflow
+
+A systematic workflow for analyzing ML/AI experimental results and generating publication-ready Results sections. Transforms raw experimental data into validated statistical analyses, publication-quality visualizations, and well-structured paper content.
+
+## Pre-load (before execution)
+
+1. **Codebase docs**: If `.workflow/codebase/ARCHITECTURE.md` exists, read for project context
+2. **Specs**: `maestro load --type spec --category coding` — load coding conventions
+3. **Wiki knowledge**: `maestro search "academic writing research paper" --json` — top 5 entries as prior context
+4. All optional — proceed without if unavailable
+
+## Architecture Overview
+
+```
+                     scholar-experiment
+                           |
+     ┌─────────────────────┼─────────────────────┐
+     |                     |                       |
+  [User Input]    [Experiment Context]    [Preferences]
+     |                     |                       |
+     └─────────┬───────────┘                       |
+               v                                   |
+┌──────────────────────────┐                       |
+│  Phase 1: Data Loading   │ <─ preferences ───────┘
+│  Load, validate, inspect │
+└────────────┬─────────────┘
+             │ cleanedData, dataProfile
+             v
+┌──────────────────────────┐
+│  Phase 2: Statistical    │
+│  Analysis & Testing      │
+└────────────┬─────────────┘
+             │ statisticalResults
+             v
+┌──────────────────────────┐
+│  Phase 3: Visualization  │
+│  Plots, charts, tables   │
+└────────────┬─────────────┘
+             │ figureSpecs, tableSpecs
+             v
+┌──────────────────────────┐
+│  Phase 4: Results Writing│
+│  Draft Results section   │
+└────────────┬─────────────┘
+             │ resultsDraft
+             v
+┌──────────────────────────┐
+│  Phase 5: Quality Check  │
+│  Validate & verify       │
+└──────────────────────────┘
+             │
+             v
+        [Output Files]
+        - analysis-report.md
+        - results-draft.md
+        - visualization-specs.md
+```
+
+## Key Design Principles
+
+1. **Statistical rigor first**: Every claim must be backed by appropriate statistical tests with complete reporting (mean, SD/SE, p-value, effect size)
+2. **Pre-test before test**: Always check assumptions (normality, variance homogeneity) before selecting parametric vs non-parametric tests
+3. **Publication-quality output**: All visualizations must meet journal standards (vector format, colorblind-friendly, proper error representation)
+4. **Complete reporting**: Never report p-values alone — always include effect sizes, confidence intervals, and descriptive statistics
+5. **No cherry-picking**: Report all planned comparisons, not just significant results
+6. **Reproducibility**: Document all analysis steps, parameters, and random seeds
+
+## Statistical Tools and Libraries
+
+This workflow requires statistical computing capabilities. Recommended implementations:
+
+**Python Stack** (recommended for ML/AI research):
+```python
+import numpy as np              # Numerical computing
+import pandas as pd             # Data manipulation
+import scipy.stats as stats     # Statistical tests
+import matplotlib.pyplot as plt # Visualization
+import seaborn as sns           # Statistical visualization
+from statsmodels.stats import multitest  # Multiple comparison corrections
+```
+
+**R Stack** (alternative for advanced statistics):
+```r
+library(tidyverse)  # Data manipulation and visualization
+library(stats)      # Statistical tests
+library(effsize)    # Effect size calculations
+library(multcomp)   # Multiple comparisons
+```
+
+**Minimum Requirements**:
+- Statistical test functions (t-test, ANOVA, Mann-Whitney, Kruskal-Wallis, etc.)
+- Effect size calculations (Cohen's d, eta-squared, r)
+- Multiple comparison corrections (Bonferroni, Holm, FDR)
+- Normality tests (Shapiro-Wilk, Kolmogorov-Smirnov)
+- Variance homogeneity tests (Levene's test)
+
+**Note**: If these libraries are not available, the workflow will guide you to use online statistical calculators or manual computation, but automated analysis is strongly recommended for reproducibility.
+2. **Pre-test before test**: Always verify assumptions (normality, homogeneity of variance) before selecting parametric tests
+3. **No cherry-picking**: Report all experimental runs, not just the best ones
+4. **Publication-quality output**: All visualizations follow colorblind-friendly, vector-format, error-bar standards
+5. **Reproducibility**: Track random seeds, hyperparameter ranges, compute resources, and experimental setup
+
+## Interactive Preference Collection
+
+Before dispatching to phases, collect analysis preferences:
+
+```javascript
+const prefResponse = AskUserQuestion({
+  question: "How would you like to configure the analysis?",
+  options: [
+    {
+      label: "Analysis Type",
+      description: "Select the type of analysis",
+      choices: [
+        { value: "full", label: "Full Analysis", description: "Complete pipeline: stats + visualization + writing" },
+        { value: "comparison", label: "Model Comparison", description: "Focus on comparing multiple models/methods" },
+        { value: "ablation", label: "Ablation Study", description: "Focus on component contribution analysis" },
+        { value: "visualization", label: "Visualization Only", description: "Generate visualization specs only" }
+      ]
+    },
+    {
+      label: "Statistical Reporting",
+      description: "Choose error reporting format",
+      choices: [
+        { value: "sd", label: "Standard Deviation (SD)", description: "Report mean +/- SD (describes data variability)" },
+        { value: "se", label: "Standard Error (SE)", description: "Report mean +/- SE (describes mean uncertainty)" },
+        { value: "ci", label: "95% Confidence Interval", description: "Report mean [95% CI: low, high]" }
+      ]
+    },
+    {
+      label: "Visualization Style",
+      description: "Choose visualization palette",
+      choices: [
+        { value: "okabe-ito", label: "Okabe-Ito (Recommended)", description: "Most widely used colorblind-friendly palette" },
+        { value: "paul-tol", label: "Paul Tol", description: "Alternative colorblind-friendly palette" }
+      ]
+    }
+  ]
+});
+
+const workflowPreferences = {
+  analysisType: prefResponse.analysisType || "full",
+  errorFormat: prefResponse.statisticalReporting || "sd",
+  colorPalette: prefResponse.visualizationStyle || "okabe-ito"
+};
+```
+
+## Auto Mode Defaults
+
+When user provides explicit analysis type (e.g., `/scholar-experiment comparison`):
+- `analysisType`: from argument
+- `errorFormat`: "sd" (standard deviation)
+- `colorPalette`: "okabe-ito"
+
+## Execution Flow
+
+> **COMPACT DIRECTIVE**: Context compression MUST check TodoWrite phase status.
+> The phase currently marked `in_progress` is the active execution phase -- preserve its FULL content.
+> Only compress phases marked `completed` or `pending`.
+
+### Phase 1: Data Loading
+Load experimental data, validate format, perform initial inspection.
+- Ref: phases/01-data-loading.md
+- Input: raw data files (CSV, JSON, TensorBoard logs, pickle), experiment context
+- Output: `cleanedData`, `dataProfile` (format, dimensions, completeness, outlier flags)
+
+### Phase 2: Statistical Analysis
+Compute descriptive statistics, run pre-tests, perform hypothesis testing, calculate effect sizes.
+- Ref: phases/02-statistical-analysis.md
+- Input: `cleanedData`, `dataProfile`, `workflowPreferences`
+- Output: `statisticalResults` (descriptive stats, test results, effect sizes, multiple comparison corrections)
+
+### Phase 3: Visualization
+Generate visualization specifications for publication-quality figures and tables.
+- Ref: phases/03-visualization.md
+- Input: `cleanedData`, `statisticalResults`, `workflowPreferences`
+- Output: `figureSpecs`, `tableSpecs`, `visualization-specs.md`
+
+### Phase 4: Results Writing
+Draft the Results section with proper statistical reporting and figure/table references.
+- Ref: phases/04-results-writing.md
+- Input: `statisticalResults`, `figureSpecs`, `tableSpecs`, `workflowPreferences`
+- Output: `resultsDraft`, `results-draft.md`
+
+### Phase 5: Quality Check
+Validate analysis completeness, check reproducibility, verify statistical reporting.
+- Ref: phases/05-quality-check.md
+- Input: all prior outputs
+- Output: `analysis-report.md` (final validated report), quality checklist
+
+**Phase Reference Documents** (read on-demand when phase executes):
+
+| Phase | Document | Purpose | Compact |
+|-------|----------|---------|---------|
+| 1 | [phases/01-data-loading.md](phases/01-data-loading.md) | Load and validate data | TodoWrite driven |
+| 2 | [phases/02-statistical-analysis.md](phases/02-statistical-analysis.md) | Statistical testing | TodoWrite driven + sentinel |
+| 3 | [phases/03-visualization.md](phases/03-visualization.md) | Figure/table specs | TodoWrite driven |
+| 4 | [phases/04-results-writing.md](phases/04-results-writing.md) | Draft Results section | TodoWrite driven + sentinel |
+| 5 | [phases/05-quality-check.md](phases/05-quality-check.md) | Validate and verify | TodoWrite driven |
+
+**Compact Rules**:
+1. **TodoWrite `in_progress`** -> preserve full content, do not compress
+2. **TodoWrite `completed`** -> may compress to summary
+3. **sentinel fallback** -> phases marked with sentinel contain compact sentinel; if after compact only sentinel remains without full Step protocol, MUST immediately `Read("phases/0N-xxx.md")` to recover before continuing
+
+## Core Rules
+
+1. **Never skip pre-tests**: Always run normality (Shapiro-Wilk) and homogeneity of variance (Levene) tests before parametric testing
+2. **Report completely**: Every statistical result must include test statistic, degrees of freedom, p-value, and effect size
+3. **Correct for multiple comparisons**: When running multiple tests, apply Bonferroni or FDR correction
+4. **Use appropriate tests**: Select parametric or non-parametric tests based on pre-test results
+5. **Vector format only**: All figure specs must target PDF/EPS output format
+6. **Colorblind-friendly**: All visualizations must use Okabe-Ito or Paul Tol palettes
+7. **Honest reporting**: Report all runs including negative results; never cherry-pick
+
+## Input Processing
+
+User provides data path and optional analysis type:
+
+```
+USER INPUT: [data_path] [analysis_type?]
+
+Structured format:
+  DATA_PATH: path/to/results/ or path/to/results.csv
+  ANALYSIS_TYPE: full | comparison | ablation | visualization
+  EXPERIMENT_CONTEXT: (read from experiment session if available)
+```
+
+Supported data formats:
+- CSV files: tabular data with headers
+- JSON files: structured results objects
+- TensorBoard logs: training curves
+- Python pickle: complex objects
+
+## Data Flow
+
+```
+Phase 1 output:
+  cleanedData    → Phase 2, 3
+  dataProfile    → Phase 2
+
+Phase 2 output:
+  statisticalResults → Phase 3, 4, 5
+
+Phase 3 output:
+  figureSpecs    → Phase 4, 5
+  tableSpecs     → Phase 4, 5
+
+Phase 4 output:
+  resultsDraft   → Phase 5
+
+Phase 5 output:
+  analysis-report.md      (final report)
+  results-draft.md        (paper-ready text)
+  visualization-specs.md  (figure specifications)
+```
+
+## TodoWrite Pattern
+
+```
+Phase starts:
+  -> Sub-tasks ATTACHED to TodoWrite (in_progress + pending)
+  -> Execute sub-tasks sequentially
+
+Phase ends:
+  -> Sub-tasks COLLAPSED back to high-level summary (completed)
+  -> Next phase begins
+```
+
+Example:
+```
+[x] Phase 1: Data Loading (completed - 3 datasets loaded, validated)
+[ ] Phase 2: Statistical Analysis (in_progress)
+    [ ] 2.1 Descriptive statistics
+    [ ] 2.2 Pre-tests (normality, variance)
+    [ ] 2.3 Hypothesis testing
+    [ ] 2.4 Effect size calculation
+    [ ] 2.5 Multiple comparison correction
+[ ] Phase 3: Visualization
+[ ] Phase 4: Results Writing
+[ ] Phase 5: Quality Check
+```
+
+## Error Handling
+
+| Error | Recovery |
+|-------|----------|
+| Data format unreadable | Ask user for format clarification, try alternative parsers |
+| Sample size too small (< 3 runs) | Warn user, proceed with non-parametric tests, note limitation |
+| Normality assumption violated | Switch to non-parametric tests (Wilcoxon, Mann-Whitney U, Kruskal-Wallis) |
+| Variance homogeneity violated | Switch to Welch's t-test or Welch's ANOVA |
+| Missing values detected | Report percentage, suggest imputation or exclusion strategy |
+| Outliers detected | Report via IQR method, run sensitivity analysis (with/without outliers) |
+
+## Coordinator Checklist
+
+**Before each phase**:
+- [ ] Previous phase output available
+- [ ] TodoWrite updated (current phase in_progress)
+- [ ] Phase document read via `Read("phases/0N-xxx.md")`
+
+**After each phase**:
+- [ ] Output files generated
+- [ ] TodoWrite updated (current phase completed, next phase in_progress)
+- [ ] Data flow variables passed to next phase
+
+**After all phases**:
+- [ ] All output files present (analysis-report.md, results-draft.md, visualization-specs.md)
+- [ ] Quality checklist completed
+- [ ] User notified of results
+
+## Related Skills
+
+- **scholar-writing**: Integrates results-draft.md into full paper structure
+- **scholar-review**: Reviews the Results section for quality and completeness

package/skills/scholar-ideation/SKILL.md

@@ -0,0 +1,288 @@
+---
+name: scholar-ideation
+description: "Research ideation workflow from literature search to research planning. Triggers on \"brainstorm research ideas\", \"identify research gaps\", \"conduct gap analysis\", \"start research project\", \"conduct literature review\", \"define research question\", \"select research method\", \"plan research\", \"research ideation\"."
+allowed-tools: WebSearch WebFetch Read Write Edit Bash Glob Grep TodoWrite AskUserQuestion
+---
+
+# Scholar Ideation
+
+Supports the complete research project initiation workflow: from literature search and gap analysis through research question formulation, method selection, and research planning. Produces a structured research plan with literature review, identified gaps, formulated questions, selected methods, and a timeline.
+
+## Pre-load (before execution)
+
+1. **Codebase docs**: If `.workflow/codebase/ARCHITECTURE.md` exists, read for project context
+2. **Specs**: `maestro load --type spec --category coding` — load coding conventions
+3. **Wiki knowledge**: `maestro search "academic writing research paper" --json` — top 5 entries as prior context
+4. All optional — proceed without if unavailable
+
+## Architecture Overview
+
+```
+User Input (research topic/interest)
+        |
+        v
+┌─────────────────────────────────────────────────────────────┐
+│  SKILL.md Orchestrator                                       │
+│  Collect preferences → Dispatch phases → Track progress      │
+└──────────┬──────────────────────────────────────────────────┘
+           |
+   ┌───────┼───────┬───────────┬───────────┬───────────┐
+   v       v       v           v           v           v
+┌──────┐┌──────┐┌──────┐┌──────────┐┌──────────┐┌──────────┐
+│Input ││Phase1││Phase2││  Phase3  ││  Phase4  ││  Phase5  │
+│Parse ││LitSrc││GapAnl││  RQ Form ││  Method  ││  Plan    │
+└──────┘└──────┘└──────┘└──────────┘└──────────┘└──────────┘
+   |       |       |         |           |           |
+ topic   papers   gaps    questions    methods    plan
+ scope   trends   opps    hypotheses   justify    timeline
+```
+
+## Key Design Principles
+
+1. **Progressive depth**: Each phase builds on previous outputs — literature informs gaps, gaps inform questions, questions inform methods
+2. **Interactive guidance**: Collect user preferences and domain context before each major phase
+3. **Zotero integration**: Automatically organize discovered papers into Zotero collections when MCP tools are available
+4. **Structured outputs**: Each phase produces structured artifacts that feed into the final research plan
+5. **5W1H grounding**: Use the 5W1H framework to ensure comprehensive research scoping
+
+## Interactive Preference Collection
+
+Before dispatching to phases, collect research context and workflow preferences:
+
+```
+AskUserQuestion:
+  question: "Please describe your research topic or interest area."
+  → Store as: researchTopic
+
+AskUserQuestion:
+  question: "What is the scope and context of your research?"
+  options:
+    - "Broad exploration (survey a field)"
+    - "Focused investigation (specific problem)"
+    - "Applied research (practical application)"
+  → Store as: researchScope
+
+AskUserQuestion:
+  question: "What is your target research timeline?"
+  options:
+    - "Short-term (3-6 months)"
+    - "Medium-term (6-12 months)"
+    - "Long-term (1-2 years)"
+  → Store as: researchTimeline
+
+AskUserQuestion:
+  question: "Do you have access to Zotero for literature management?"
+  options:
+    - "Yes (auto-import papers to Zotero)"
+    - "No (skip Zotero integration)"
+  → Store as: useZotero
+
+AskUserQuestion:
+  question: "Workflow mode?"
+  options:
+    - "Interactive (confirm at each phase)"
+    - "Auto (run all phases continuously)"
+  → Store as: workflowMode
+```
+
+Derived preferences:
+```
+workflowPreferences = {
+  topic: researchTopic,
+  scope: researchScope,
+  timeline: researchTimeline,
+  useZotero: useZotero === "Yes",
+  autoYes: workflowMode === "Auto"
+}
+```
+
+## Auto Mode Defaults
+
+When `workflowPreferences.autoYes === true`: Execute all 5 phases sequentially without confirmation prompts between phases. Still pause for user input when phase-specific questions arise (e.g., confirming search keywords, selecting papers for deep reading).
+
+## Execution Flow
+
+> **COMPACT DIRECTIVE**: Context compression MUST check TodoWrite phase status.
+> The phase currently marked `in_progress` is the active execution phase — preserve its FULL content.
+> Only compress phases marked `completed` or `pending`.
+
+### TodoWrite Initialization
+
+```
+TodoWrite:
+  - "Phase 1: Literature Search" (pending)
+  - "Phase 2: Gap Analysis" (pending)
+  - "Phase 3: Research Question Formulation" (pending)
+  - "Phase 4: Method Selection" (pending)
+  - "Phase 5: Research Planning" (pending)
+```
+
+### Phase Dispatch
+
+```
+Phase 1: Literature Search
+   Mark TodoWrite Phase 1 → in_progress
+   └─ Ref: phases/01-literature-search.md
+      ├─ Input: workflowPreferences (topic, scope, useZotero)
+      └─ Output: literatureResults (papers, trends, keyFindings)
+
+Phase 2: Gap Analysis
+   Mark TodoWrite Phase 1 → completed, Phase 2 → in_progress
+   └─ Ref: phases/02-gap-analysis.md
+      ├─ Input: literatureResults
+      └─ Output: gapAnalysis (gaps, opportunities, priorities)
+
+Phase 3: Research Question Formulation
+   Mark TodoWrite Phase 2 → completed, Phase 3 → in_progress
+   └─ Ref: phases/03-research-question.md
+      ├─ Input: gapAnalysis + literatureResults
+      └─ Output: researchQuestions (questions, hypotheses, objectives)
+
+Phase 4: Method Selection
+   Mark TodoWrite Phase 3 → completed, Phase 4 → in_progress
+   └─ Ref: phases/04-method-selection.md
+      ├─ Input: researchQuestions + gapAnalysis
+      └─ Output: selectedMethods (methods, justification, resources)
+
+Phase 5: Research Planning
+   Mark TodoWrite Phase 4 → completed, Phase 5 → in_progress
+   └─ Ref: phases/05-research-planning.md
+      ├─ Input: ALL previous outputs
+      └─ Output: research-plan.md (final deliverable)
+
+Mark TodoWrite Phase 5 → completed
+```
+
+**Phase Reference Documents** (read on-demand when phase executes):
+
+| Phase | Document | Purpose | Compact |
+|-------|----------|---------|---------|
+| 1 | [phases/01-literature-search.md](phases/01-literature-search.md) | Search, discover, and organize literature | TodoWrite driven |
+| 2 | [phases/02-gap-analysis.md](phases/02-gap-analysis.md) | Identify research gaps and opportunities | TodoWrite driven |
+| 3 | [phases/03-research-question.md](phases/03-research-question.md) | Formulate research questions and hypotheses | TodoWrite driven |
+| 4 | [phases/04-method-selection.md](phases/04-method-selection.md) | Select and justify research methods | TodoWrite driven + sentinel |
+| 5 | [phases/05-research-planning.md](phases/05-research-planning.md) | Create timeline, milestones, and final plan | TodoWrite driven + sentinel |
+
+**Compact Rules**:
+1. **TodoWrite `in_progress`** — preserve full content, do not compress
+2. **TodoWrite `completed`** — may compress to summary
+3. **sentinel fallback** — phases marked with sentinel: if compact leaves only sentinel without full Step protocol, immediately `Read()` to recover
+
+## Core Rules
+
+1. **Literature first**: Always complete literature search before gap analysis — gaps must be grounded in actual literature
+2. **Evidence-based gaps**: Every identified gap must reference specific papers or missing coverage areas
+3. **SMART questions**: Research questions must satisfy Specific, Measurable, Achievable, Relevant, Time-bound criteria
+4. **Method-question alignment**: Selected methods must directly address the formulated research questions
+5. **Feasibility check**: Research plan must account for available resources (compute, data, time, personnel)
+6. **No hallucinated papers**: Only reference papers actually found via WebSearch — never fabricate citations
+
+## Input Processing
+
+User input (free text or structured) is converted to:
+
+```
+TOPIC: [research topic or interest]
+SCOPE: [broad | focused | applied]
+TIMELINE: [short | medium | long]
+CONTEXT: [additional constraints, domain, background]
+```
+
+If user provides a simple topic string, derive scope and timeline from the topic description or ask via AskUserQuestion.
+
+## Data Flow
+
+```
+workflowPreferences
+    ├─→ Phase 1: topic, scope, useZotero
+    │       └─→ literatureResults {papers[], trends[], keyFindings[], zoteroCollection?}
+    │
+    ├─→ Phase 2: literatureResults
+    │       └─→ gapAnalysis {gaps[], opportunities[], prioritizedGaps[]}
+    │
+    ├─→ Phase 3: gapAnalysis + literatureResults
+    │       └─→ researchQuestions {questions[], hypotheses[], objectives[]}
+    │
+    ├─→ Phase 4: researchQuestions + gapAnalysis
+    │       └─→ selectedMethods {methods[], justification, resources[]}
+    │
+    └─→ Phase 5: ALL outputs
+            └─→ research-plan.md (final structured document)
+```
+
+## TodoWrite Pattern
+
+**Phase start — Attach sub-tasks**:
+```
+Mark Phase N → in_progress
+Add sub-tasks:
+  - "Step N.1: ..." (in_progress)
+  - "Step N.2: ..." (pending)
+  - "Step N.3: ..." (pending)
+```
+
+**Phase end — Collapse**:
+```
+Mark all Phase N sub-tasks → completed
+Mark Phase N → completed
+Mark Phase N+1 → in_progress
+```
+
+## Post-Phase Updates
+
+After each phase completes, update an accumulated research notes document:
+
+```markdown
+## Research Notes (accumulated)
+
+### After Phase 1 (Literature Search)
+- Papers found: [count]
+- Key trends: [list]
+- Zotero collection: [name, if applicable]
+
+### After Phase 2 (Gap Analysis)
+- Gaps identified: [count]
+- Top priorities: [list]
+
+### After Phase 3 (Research Questions)
+- Primary RQ: [question]
+- Sub-questions: [count]
+
+### After Phase 4 (Method Selection)
+- Selected approach: [method]
+- Required resources: [list]
+```
+
+## Error Handling
+
+1. **WebSearch fails**: Retry with modified keywords; if persistent, ask user for alternative search terms
+2. **No papers found**: Broaden search scope, try synonyms and related terms, try different databases
+3. **Zotero unavailable**: Skip Zotero integration, continue with manual paper tracking in markdown
+4. **Gap analysis inconclusive**: Return to Phase 1 for additional targeted literature search
+5. **Infeasible plan**: Adjust scope, timeline, or methods; consult user for trade-off decisions
+
+## Coordinator Checklist
+
+**Pre-phase**:
+- [ ] Verify previous phase outputs are available
+- [ ] Update TodoWrite status
+- [ ] Read phase document (`Read("phases/0N-xxx.md")`)
+
+**Post-phase**:
+- [ ] Validate phase outputs (non-empty, well-structured)
+- [ ] Update accumulated research notes
+- [ ] Collapse TodoWrite sub-tasks
+- [ ] If not autoYes, confirm with user before proceeding
+
+## Output Files
+
+The workflow produces:
+- **`research-plan.md`** — Final structured research proposal with all sections
+- **`literature-review.md`** — Structured literature review with categorized papers
+- **Zotero collection** — Organized papers with PDFs (if Zotero enabled)
+
+## Related Skills
+
+- **scholar-experiment** — Experiment execution and tracking (follows this skill)
+- **scholar-writing** — Paper writing workflow (uses outputs from experiment)
+- **scholar-review** — Paper review and revision workflow