obsidian-research-synthesis
Searches across Obsidian vault, synthesizes findings from multiple notes, and creates comprehensive research documentation. Gathers scattered information using filesystem search and dataview queries, analyzes content, and produces structured research reports with proper citations and wiki-links.
What this skill does
# Research & Synthesis Enables comprehensive research workflows within Obsidian: search for information across your vault, analyze and synthesize findings from multiple notes, and create well-structured research documentation with proper citations. ## Quick Start When asked to research and document a topic: 1. **Search vault**: Use filesystem search, grep, and dataview to find relevant notes 2. **Read notes**: Parse markdown files and extract relevant information 3. **Synthesize findings**: Analyze and combine information from multiple sources 4. **Create research note**: Generate structured documentation with citations ## Research Workflow ### Step 1: Search for relevant information **Filesystem search:** ```bash # Search by filename find /path/to/vault -name "*keyword*" # Search file content grep -r "search term" /path/to/vault/ --include="*.md" # Search with context grep -r -C 3 "search term" /path/to/vault/ # Case-insensitive search grep -ri "keyword" /path/to/vault/ ``` **Search by frontmatter:** ```bash # Find notes with specific tag grep -l "tags:.*keyword" /path/to/vault/**/*.md # Find notes of specific type grep -l "type: research" /path/to/vault/**/*.md ``` **Dataview queries** (if using Dataview plugin): ```dataview TABLE file.ctime, tags FROM "research" OR "projects" WHERE contains(file.name, "keyword") OR contains(tags, "#topic") SORT file.mtime DESC ``` **Search strategies:** - Topic-based: Search for concept or domain keywords - Tag-based: Filter by relevant tags - Date-based: Recent notes using mtime - Author-based: Notes created by specific person - Link-based: Notes linking to specific concept ### Step 2: Read and extract information For each relevant note: ```bash # Read full note cat /path/to/vault/note-name.md # Read just frontmatter head -20 /path/to/vault/note-name.md | sed -n '/^---$/,/^---$/p' # Extract specific sections sed -n '/## Section Name/,/^## /p' /path/to/vault/note-name.md ``` Extract and organize: - Key concepts and definitions - Data points and metrics - Insights and analysis - Quotes and specific claims - Relationships between concepts - Gaps in knowledge ### Step 3: Analyze and synthesize **Identify patterns:** - Common themes across notes - Contradictions or conflicts - Knowledge gaps - Complementary information - Chronological developments **Connect concepts:** - How topics relate to each other - Dependencies and prerequisites - Cause and effect relationships - Examples and counter-examples **Note limitations:** - Missing information - Uncertain claims - Areas needing more research - Conflicting viewpoints ### Step 4: Create research documentation **Choose output format:** - **Research Summary**: Quick overview with key findings (see [reference/research-summary-template.md](reference/research-summary-template.md)) - **Comprehensive Report**: Detailed analysis with full citations (see [reference/comprehensive-report-template.md](reference/comprehensive-report-template.md)) - **Literature Review**: Academic-style review (see [reference/literature-review-template.md](reference/literature-review-template.md)) - **Synthesis Note**: Integration of multiple sources (see [reference/synthesis-note-template.md](reference/synthesis-note-template.md)) **Create research note:** ```bash touch /path/to/vault/research/topic-research.md ``` See [reference/format-selection-guide.md](reference/format-selection-guide.md) for choosing the right format. ## Research Output Formats ### Research Summary Brief overview synthesizing key findings: ```markdown --- type: research-summary topic: [Topic] created: YYYY-MM-DD tags: - research - TOPIC sources: X notes --- # Research Summary: [Topic] ## Executive Summary One paragraph capturing the main findings. ## Key Findings 1. Finding 1 [[source-note-1]] 2. Finding 2 [[source-note-2]] 3. Finding 3 [[source-note-3]] ## Main Themes - Theme 1: Description - Theme 2: Description ## Conclusions Summary of insights and implications. ## Further Research - Question 1 - Question 2 ## Sources - [[note-1]] - [[note-2]] - [[note-3]] ``` ### Comprehensive Report Detailed analysis with full exploration: ```markdown --- type: research-report topic: [Topic] created: YYYY-MM-DD tags: - research - report - TOPIC --- # Research Report: [Topic] ## Executive Summary Comprehensive overview of research and conclusions. ## Background Context and motivation for research. ## Methodology How information was gathered and analyzed. ## Findings ### Theme 1: [Name] Detailed discussion with evidence. **Evidence from sources:** - [[source-1]]: Specific claim or data - [[source-2]]: Supporting information - [[source-3]]: Additional context ### Theme 2: [Name] Continue analysis... ## Analysis Synthesis and interpretation of findings. ## Limitations Gaps in current research and uncertainties. ## Conclusions Key takeaways and implications. ## Recommendations Actionable suggestions based on research. ## Further Research Areas needing additional investigation. ## References Complete list of source notes with brief descriptions. ``` See [reference/comprehensive-report-template.md](reference/comprehensive-report-template.md) for full template. ## Citation Patterns ### Basic Citation ```markdown According to [[note-name]], the primary factor is X. ``` ### Citation with Context ```markdown The implementation pattern [[patterns/circuit-breaker]] suggests using exponential backoff. ``` ### Multiple Sources ```markdown Multiple sources ([[source-1]], [[source-2]], [[source-3]]) indicate that X is common. ``` ### Direct Quote Attribution ```markdown > "Key insight here" > — [[person-name]] in [[meeting-notes-2025-10-15]] ``` ### Conflicting Sources ```markdown While [[source-1]] suggests X, [[source-2]] presents evidence for Y, indicating further investigation is needed. ``` ## Search Techniques ### Content-Based Search **Exact phrase:** ```bash grep -r "exact phrase here" /path/to/vault/ ``` **Multiple keywords:** ```bash grep -r "keyword1" /path/to/vault/ | grep "keyword2" ``` **Exclude certain directories:** ```bash grep -r "keyword" /path/to/vault/ --exclude-dir=".obsidian" ``` ### Metadata-Based Search **Find by tag:** ```bash grep -l "tags:.*#specific-tag" /path/to/vault/**/*.md ``` **Find by type:** ```bash grep -l "type: research" /path/to/vault/**/*.md ``` **Find by date range:** ```bash find /path/to/vault -name "*.md" -newermt "2025-01-01" -not -newermt "2025-12-31" ``` ### Link-Based Analysis **Find all notes linking to specific note:** ```bash grep -r "\[\[target-note\]\]" /path/to/vault/ ``` **Find orphan notes (no incoming links):** ```bash # Requires custom script python scripts/find_orphans.py /path/to/vault ``` **Find highly connected notes:** ```bash # Count outgoing links per note for file in /path/to/vault/**/*.md; do count=$(grep -o "\[\[" "$file" | wc -l) echo "$count $file" done | sort -rn | head -10 ``` ## Synthesis Strategies ### Thematic Synthesis Group findings by common themes across sources. ### Chronological Synthesis Trace development of ideas over time. ### Comparative Synthesis Compare and contrast different perspectives. ### Integrative Synthesis Build unified understanding from diverse sources. ## Quality Checks Before finalizing research: - [ ] All claims cited to source notes - [ ] Contradictions noted and explained - [ ] Knowledge gaps identified - [ ] Key themes clearly articulated - [ ] Executive summary captures essence - [ ] Recommendations are actionable - [ ] Further research questions listed - [ ] All source links valid ## Best Practices 1. **Search broadly first**: Cast wide net initially 2. **Read critically**: Evaluate quality and relevance of sources 3. **Take structured notes**: Extract key points during reading 4. **Cite consistently**: Always link to source notes 5. **Note conflicts**: Document disagreements between sources 6. **Identify gaps**: What's missing from current knowle
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.