Research

Research, evidence gathering, literature, reports, investigation, and synthesis

skills in category: 21,385
pages available: 892

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse research skills

Showing 9,985–10,008 of 21,385 skills

Bio Outlier Splicing DetectionADetects aberrant splicing in single rare-disease patients vs a control panel using FRASER 2.0 (Bioconductor; Beta-binomial autoencoder on Intron Jaccard Index, default delta cutoff 0.1, q hyperparameter), OUTRIDER (gene-level outlier expression via autoencoder denoising), LeafcutterMD (Dirichlet-multinomial outlier mode of LeafCutter for annotation-free junctions), and DROP (Snakemake pipeline integrating FRASER2 + OUTRIDER + monoallelic expression for clinical diagnostics). The statistical m...researchpythongoVotes: 0GitHub stars: 4
Bio Differential SplicingADetects differential alternative splicing between conditions using rMATS-turbo (binomial LRT on junction counts), leafcutter (Dirichlet-multinomial GLM on intron clusters), MAJIQ V3 deltapsi/HET (Bayesian posterior on LSVs), SUPPA2 (empirical-null on TPM-derived PSI), or Shiba (junction-imbalance-corrected, 2025 SOTA at low coverage). Reports FDR-corrected significance and delta PSI effect sizes. Tools differ in statistical model, annotation dependence, calibration regime, and replicate-count...researchpythongoVotes: 0GitHub stars: 4
LiteratureALiterature: retrieve document-level scientific evidence from publications, clinical-trial registries, and patent sources. Use for PubMed records, reproducible searches, trial registrations, patent evidence, abstracts, study metadata, stable identifiers, and citation provenance.researchgoVotes: 0GitHub stars: 4
Experimental DataAExperimental data: discover and acquire raw or near-raw measurements, sample-level observations, and reusable datasets from sequencing, transcriptomics, single-cell, perturbation, proteomics, metabolomics, genomics, and structural-biology repositories. Use for study or sample metadata, matrices, reads, spectra, experimental structures, and downloadable research artifacts—not curated database assertions or reference marker collections.researchgodatabaseVotes: 0GitHub stars: 4
Parallax Judge House ViewARead-only LLM-as-judge that compares the saved CIO house view against current Parallax macro signals, classifies drift severity (minor / moderate / material), and recommends per-cell updates with cited rationale. Emits a self-contained report bundle and a single audit row; NEVER modifies the active view. NOT for synthesizing a view from scratch (use /parallax-make-house-view), not for portfolio construction (use /parallax-portfolio-builder), not for one-off scenario reactions (use /parallax-s...researchgoshellVotes: 0GitHub stars: 5
Parallax Ai SorosAApplies George Soros's top-down reflexivity framework (per 'The Alchemy of Finance', 1987) to current Parallax data. Triggers: 'trade ideas based on current macro regime', 'regime-driven stock picks', 'reflexivity-lens stock ideas'. Two modes: basket mode surfaces regime themes and ranked exposure candidates (informational); single-ticker mode runs the same macro workflow and checks ticker exposure via dual channels (industry exposure AND telemetry basket theme). Third-person framing, book ci...researchgosecurityVotes: 0GitHub stars: 5
Parallax Ai PtjAApplies Paul Tudor Jones's trend-following + macro-overlay framework (per Schwager's 'Market Wizards', 1989) to evaluate single-stock technical setup, macroeconomic regime alignment, and volatility-driven risk/reward asymmetry. Evaluates ticker across three independent conviction channels (Technical, Macro, Volatility). Third-person framing, book citation, AI-inferred from public information. NOT financial advice. NOT personalized. Accepts plain tickers or RIC format. NOT for bottom-up factor...researchgoshellVotes: 0GitHub stars: 5
Parallax Ai KlarmanAApplies Seth Klarman's margin-of-safety framework (per 'Margin of Safety', 1991) to a single stock's current financials via Parallax. Four balance-sheet checks: net cash position, debt vs peers, FCF stability, valuation discount. Includes a distinctive 'no position warranted; cash is valid' output when nothing qualifies. Third-person framing, book citation, AI-inferred from public information. NOT financial advice. NOT personalized. Accepts plain tickers or RIC format. NOT for portfolio-level...researchgosecurityVotes: 0GitHub stars: 5
Parallax Ai GreenblattAApplies Joel Greenblatt's Magic Formula (per 'The Little Book That Beats the Market', 2006; academic replication Gray & Carlisle 2012) to Parallax data. Two modes: universe mode returns a top-decile ranked basket; ticker-check mode reports whether a single stock falls in the top decile of its peer universe by combined ROC + earnings yield rank. Third-person framing, book citation, AI-inferred from public information. NOT financial advice. NOT personalized. Accepts no args (universe mode) or a...researchgoapiVotes: 0GitHub stars: 5
Parallax Ai ConsensusARuns all installed Parallax AI Investor Profiles (Buffett, Greenblatt, Klarman, Soros, PTJ) against a single ticker or short basket (cap 5). Returns the per-profile verdict matrix, the super-majority consensus signal per consensus-config.md, and a factor-level agreement detail showing which factors/criteria were flagged by multiple profiles. Cross-profile agreement is the strongest-agreement signal. Third-person framing throughout, AI-inferred from public information. NOT financial advice. NO...researchgosecurityVotes: 0GitHub stars: 5
Parallax Ai BuffettAApplies the Buffett-style factor profile (per Frazzini-Kabiller-Pedersen 2018, 'Buffett's Alpha', FAJ), reconciled for 21st-century intangibles-heavy valuations per Lev-Srivastava 2022, to a single stock's current Parallax factor scores. Returns a match/partial/no-match verdict based on Quality, Value, Momentum, and Defensive factor criteria. Third-person framing, academic citation, AI-inferred from public information. NOT financial advice. NOT personalized. Accepts plain tickers or RIC forma...researchgosecurityVotes: 0GitHub stars: 5
Parallax Should I BuyAQuick stock evaluation: company overview, Parallax factor scores, financial health, score trends, macro context, dividends, news, and analyst outlook. Plain language output. Accepts plain ticker (AAPL) or RIC (AAPL.O). NOT for portfolio analysis (use /parallax-morning-brief), not for full due diligence (use /parallax-due-diligence), not for a position deep dive with AI assessment (use /parallax-deep-dive), not for peer-set comparison (use /parallax-peer-comparison), not for methodology-only q...researchpythongoVotes: 0GitHub stars: 5
Parallax RebalanceAPortfolio rebalancing with health flags and macro context: analyze current state, flag issues, generate a prioritized, information-framed rebalancing analysis (candidate actions per conventions §12) with score rationale via Parallax MCP tools. Holdings as [{symbol, weight}]. NOT for initial portfolio construction (use /parallax-portfolio-builder), not for diagnostic-only review (use /parallax-client-review).researchpythonrustVotes: 0GitHub stars: 5
Parallax ConciergeAFriendly concierge that opens a three-branch menu (Stock / Portfolio / Discovery) for users who arrive without a specific /parallax-* command in mind. Triggers on greetings addressed to Parallax — 'Hi Parallax', 'Hello Parallax', 'Hey Parallax', 'Good morning Parallax', 'Yo Parallax', 'Parallax!' — case- and punctuation-insensitive. Also triggers on 'what can Parallax do', 'help me get started with Parallax', 'show me Parallax workflows', or any open-ended request to explore the Parallax tool...researchgoVotes: 0GitHub stars: 5
Meta Ads AnalyzerAProvides expert-level analysis and diagnosis for Meta Ads campaigns. Use this skill to interpret performance data, identify root causes of issues, and generate actionable recommendations, with a special focus on correctly handling the 'Breakdown Effect'. Use when the user mentions Meta Ads analysis, campaign diagnosis, ad performance, CPA analysis, ROAS analysis, or asks to analyze exported data from Meta Ads Manager.researchgoapiVotes: 0GitHub stars: 36
Wiki QaAAnswers questions about a code repository using source file analysis. Use when the user asks a question about how something works, wants to understand a component, or needs help navigating the code...researchVotes: 0GitHub stars: 36
Planning With FilesAImplements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requirin...researchgoapiVotes: 0GitHub stars: 36
Apify EcommerceAScrape e-commerce data for pricing intelligence, customer reviews, and seller discovery across Amazon, Walmart, eBay, IKEA, and 50+ marketplaces. Use when user asks to monitor prices, track competi...researchgobashVotes: 0GitHub stars: 36
Research EngineerAAn uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal impl...researchpythonrustVotes: 0GitHub stars: 36
Deep ResearchAExecute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 ...researchpythongoVotes: 0GitHub stars: 36
Conductor RevertAGit-aware undo by logical work unit (track, phase, or task)researchgobashVotes: 0GitHub stars: 36
Cell Free Protein ExpressionACell-free protein synthesis (CFPS) planning and optimization guidance. Use when: (1) Planning CFPS experiments, (2) Troubleshooting low yield or aggregation, (3) Optimizing DNA template design for CFPS, (4) Expressing difficult proteins (disulfide-rich, toxic, membrane).researchgoreactVotes: 0GitHub stars: 26
Adversarial VerificationAHave an independent agent skeptically re-verify a fix, claim, or result instead of trusting the builder's self-assessment. Use when a subagent or Workflow stage produces a fix/result and you need to know if it actually worked — code fixes, content claims, data pipeline output, generated assets, or any "did this actually work" question — especially when multiple independent attempts are built in parallel and need honest, comparable grading.researchrustgoVotes: 0GitHub stars: 3
Product Image Fidelity GateAMANDATORY before rendering, creating content, or editing skyyrose.co — eyes-on verify every product image is the CORRECT garment for its SKU by reading the actual pixels (vision), never the filename or manifest. Prevents wrong-garment imagery, the #1 recurring defect.researchrustgoVotes: 0GitHub stars: 3