Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.
.claude/skills/mkurman-research-lookup/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 166% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 93% | 0% |
Default backend. Provides comprehensive, multi-source research with citations via the Chat API (core model).
Query Examples:
- "Recent advances in CRISPR gene editing 2025"
- "Compare mRNA vaccines vs traditional vaccines for cancer treatment"
- "AI adoption in healthcare industry statistics"
- "Global renewable energy market trends and projections"
- "Explain the mechanism underlying gut microbiome and depression"Response includes:
Used for academic-specific queries. Prioritizes scholarly databases and peer-reviewed sources.
Query Examples:
- "Find papers on transformer attention mechanisms in NeurIPS 2024"
- "Foundational papers on quantum error correction"
- "Systematic review of immunotherapy in non-small cell lung cancer"
- "Cite the original BERT paper and its most influential follow-ups"
- "Published studies on CRISPR off-target effects in clinical trials"Response includes:
Query Examples:
- "Western blot protocol for protein detection"
- "Statistical power analysis for clinical trials"
- "Machine learning model evaluation metrics comparison"Query Examples:
- "Prevalence of diabetes in US population 2025"
- "Global AI market size and growth projections"
- "COVID-19 vaccination rates by country"CRITICAL: When searching for papers, ALWAYS prioritize high-quality, influential papers.
| Paper Age | Citation Threshold | Classification | |-----------|-------------------|----------------| | 0-3 years | 20+ citations | Noteworthy | | 0-3 years | 100+ citations | Highly Influential | | 3-7 years | 100+ citations | Significant | | 3-7 years | 500+ citations | Landmark Paper | | 7+ years | 500+ citations | Seminal Work | | 7+ years | 1000+ citations | Foundational |
Tier 1 - Premier Venues (Always prefer):
Tier 2 - High-Impact Specialized (Strong preference):
Tier 3 - Respected Specialized (Include when relevant):
bash# Primary backend (Parallel Chat API) - REQUIRED export PARALLEL_API_KEY="your_parallel_api_key" # Academic search backend (Perplexity) - REQUIRED for academic queries export OPENROUTER_API_KEY="your_openrouter_api_key"
Parallel Chat API:
https://api.parallel.ai (OpenAI SDK compatible)core (60s-5min latency, complex multi-source synthesis)openaiPerplexity sonar-pro-search:
perplexity/sonar-pro-search (via OpenRouter)bash# Auto-routed research (recommended) — ALWAYS save to sources/ python research_lookup.py "your query" -o sources/research_YYYYMMDD_HHMMSS_<topic>.md # Force specific backend — ALWAYS save to sources/ python research_lookup.py "your query" --force-backend parallel -o sources/research_<topic>.md python research_lookup.py "your query" --force-backend perplexity -o sources/papers_<topic>.md # JSON output — ALWAYS save to sources/ python research_lookup.py "your query" --json -o sources/research_<topic>.json # Batch queries — ALWAYS save to sources/ python research_lookup.py --batch "query 1" "query 2" "query 3" -o sources/batch_research_<topic>.md
Every research-lookup result MUST be saved to the project's sources/ folder.
This is non-negotiable. Research results are expensive to obtain and critical for reproducibility.
| Backend | -o Flag Target | Filename Pattern | |---------|-----------------|------------------| | Parallel Deep Research | sources/research_<topic>.md | research_YYYYMMDD_HHMMSS_<brief_topic>.md | | Perplexity (academic) | sources/papers_<topic>.md | papers_YYYYMMDD_HHMMSS_<brief_topic>.md | | Batch queries | sources/batch_<topic>.md | batch_research_YYYYMMDD_HHMMSS_<brief_topic>.md |
CRITICAL: Every call to research_lookup.py MUST include the -o flag pointing to the sources/ folder.
CRITICAL: Saved files MUST preserve all citations, source URLs, and DOIs. The default text output automatically includes a Sources section (with title, date, URL for each source) and an Additional References section (with DOIs and academic URLs extracted from the response text). For maximum citation metadata, use --json.
bash# General research — save to sources/ (includes Sources + Additional References sections) python research_lookup.py "Recent advances in CRISPR gene editing 2025" \ -o sources/research_20250217_143000_crispr_advances.md # Academic paper search — save to sources/ (includes paper citations with DOIs) python research_lookup.py "Find papers on transformer attention mechanisms in NeurIPS 2024" \ -o sources/papers_20250217_143500_transformer_attention.md # JSON format for maximum citation metadata (full citation objects with URLs, DOIs, snippets) python research_lookup.py "CRISPR clinical trials" --json \ -o sources/research_20250217_143000_crispr_trials.json # Forced backend — save to sources/ python research_lookup.py "AI regulation landscape" --force-backend parallel \ -o sources/research_20250217_144000_ai_regulation.md # Batch queries — save to sources/ python research_lookup.py --batch "mRNA vaccines efficacy" "mRNA vaccines safety" \ -o sources/batch_research_20250217_144500_mrna_vaccines.md
Each output format preserves citations differently:
| Format | Citations Included | When to Use | |--------|-------------------|-------------| | Text (default) | Sources (N): section with [title] (date) + URL + Additional References (N): with DOIs and academic URLs | Standard use — human-readable with all citations | | JSON (--json) | Full citation objects: url, title, date, snippet, doi, type | When you need maximum citation metadata |
For Parallel backend, saved files include: research report + Sources list (title, URL) + Additional References (DOIs, academic URLs). For Perplexity backend, saved files include: academic summary + Sources list (title, date, URL, snippet) + Additional References (DOIs, academic URLs).
Use --json when you need to:
sources/ folder documents exactly how all research information was gatheredsources/ for existing results before making new API callsBefore calling research_lookup.py, check if a relevant result already exists:
bashls sources/ # Check existing saved results
If a prior lookup covers the same topic, re-read the saved file instead of making a new API call.
When saving research results, always log:
[HH:MM:SS] SAVED: Research lookup to sources/research_20250217_143000_crispr_advances.md (3,800 words, 8 citations)
[HH:MM:SS] SAVED: Paper search to sources/papers_20250217_143500_transformer_attention.md (6 papers found)This skill enhances scientific writing by providing:
sources/sources/sources/sources/sources/| Task | Tool | |------|------| | General web search | parallel-web skill (parallel_web.py search) | | Citation verification | parallel-web skill (parallel_web.py extract) | | Deep research (any topic) | research-lookup or parallel-web skill | | Academic paper search | research-lookup (auto-routes to Perplexity) | | Google Scholar search | citation-management skill | | PubMed search | citation-management skill | | DOI to BibTeX | citation-management skill | | Metadata verification | parallel-web skill (parallel_web.py search or extract) |
Known Limitations:
Fallback Behavior:
Query: "Recent advances in transformer attention mechanisms 2025"
Backend: Parallel Chat API (core model)
Response: Comprehensive markdown report with citations from authoritative sources, covering recent papers, key innovations, and performance benchmarks.
Query: "Find papers on CRISPR off-target effects in clinical trials"
Backend: Perplexity sonar-pro-search (academic mode)
Response: Curated list of 5-8 high-impact papers with full citations, DOIs, citation counts, and venue tier indicators.
Query: "Compare and contrast mRNA vaccines vs traditional vaccines for cancer treatment"
Backend: Parallel Chat API (core model)
Response: Detailed comparative report with data from multiple sources, structured analysis, and cited evidence.
Query: "Global AI adoption in healthcare statistics 2025"
Backend: Parallel Chat API (core model)
Response: Current market data, adoption rates, growth projections, and regional analysis with source citations.
This skill serves as the primary research interface with intelligent dual-backend routing:
core model): Comprehensive, multi-source research for any topicparallel-web skill for web search and URL extraction| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 27,491 | 11,050 | -60% | 1 | 1 | 0% | 4,802 | 5,053 | +5% | 0 | 0 | — |
case-02 | fail→pass | 40,761 | 36,697 | -10% | 1 | 1 | 0% | 6,204 | 7,760 | +25% | 0 | 0 | — |
case-03 | fail→pass | 17,367 | 7,679 | -56% | 1 | 1 | 0% | 2,607 | 3,640 | +40% | 0 | 0 | — |
case-04 | fail→pass | 18,075 | 17,179 | -5% | 1 | 1 | 0% | 2,269 | 6,034 | +166% | 0 | 0 | — |
case-05 | fail→pass | 13,236 | 4,879 | -63% | 1 | 1 | 0% | 2,056 | 3,968 | +93% | 0 | 0 | — |
case-06 | fail→pass | 6,526 | 2,865 | -56% | 1 | 1 | 0% | 955 | 3,562 | +273% | 0 | 0 | — |
case-07 | fail→pass | 15,468 | 2,730 | -82% | 1 | 1 | 0% | 2,606 | 3,546 | +36% | 0 | 0 | — |
case-08 | pass→pass | 13,237 | 2,377 | -82% | 1 | 1 | 0% | 2,164 | 3,495 | +62% | 0 | 0 | — |
case-09 | fail→pass | 15,053 | 2,999 | -80% | 1 | 1 | 0% | 2,454 | 3,639 | +48% | 0 | 0 | — |
case-10 | pass→pass | 12,770 | 4,544 | -64% | 1 | 1 | 0% | 2,340 | 3,898 | +67% | 0 | 0 | — |
case-11 | pass→pass | 13,364 | 15,406 | +15% | 1 | 1 | 0% | 2,243 | 5,551 | +147% | 0 | 0 | — |
case-12 | pass→pass | 12,749 | 2,612 | -80% | 1 | 1 | 0% | 1,995 | 3,526 | +77% | 0 | 0 | — |
case-13 | fail→pass | 9,365 | 3,236 | -65% | 1 | 1 | 0% | 1,696 | 3,625 | +114% | 0 | 0 | — |
case-14 | pass→pass | 5,908 | 1,612 | -73% | 1 | 1 | 0% | 983 | 3,307 | +236% | 0 | 0 | — |
case-15 | pass→pass | 13,519 | 1,549 | -89% | 1 | 1 | 0% | 2,245 | 3,302 | +47% | 0 | 0 | — |
case-16 | fail→pass | 7,571 | 2,747 | -64% | 1 | 1 | 0% | 1,054 | 3,526 | +235% | 0 | 0 | — |
case-17 | fail→pass | 10,668 | 2,686 | -75% | 1 | 1 | 0% | 1,795 | 3,596 | +100% | 0 | 0 | — |
case-18 | fail→pass | 11,996 | 3,206 | -73% | 1 | 1 | 0% | 1,746 | 3,662 | +110% | 0 | 0 | — |
case-19 | pass→pass | 9,388 | 2,980 | -68% | 1 | 1 | 0% | 1,553 | 3,611 | +133% | 0 | 0 | — |
case-20 | fail→pass | 12,562 | 1,990 | -84% | 1 | 1 | 0% | 1,885 | 3,395 | +80% | 0 | 0 | — |
case-21 | fail→pass | 10,412 | 1,748 | -83% | 1 | 1 | 0% | 1,859 | 3,373 | +81% | 0 | 0 | — |
case-22 | fail→fail | 9,732 | 10,458 | +7% | 1 | 1 | 0% | 1,634 | 4,964 | +204% | 0 | 0 | — |
case-23 | fail→pass | 5,906 | 2,983 | -49% | 1 | 1 | 0% | 1,126 | 3,596 | +219% | 0 | 0 | — |
case-24 | fail→pass | 8,457 | 2,990 | -65% | 1 | 1 | 0% | 1,327 | 3,637 | +174% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +67 percentage points is the difference between those two pass rates over the 24 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.