データ・AIのスキル

Designs adaptive clinical trials including group-sequential (O'Brien-Fleming, Pocock, Lan-DeMets spending), sample-size re-estimation (blinded Friede-Kieser, unblinded Cui-Hung-Wang, Mehta-Pocock promising zone), seamless Phase 2/3 with treatment-arm selection, population enrichment, and response-adaptive randomisation. Covers FDA 2019 Final Adaptive Designs Guidance, FDA 2022 Master Protocols, and ICH E20 Step 2b/3 draft (June 2025, NOT final). Use when planning interim analyses, sample-size re-estimation, or master/platform-trial designs.

日本語の概要は準備中です。原文の説明を表示しています。

Workflow for pseudotime, lineage branching, and state-transition analysis in single-cell data.

日本語の概要は準備中です。原文の説明を表示しています。

SPR and BLI assay planning, kinetic interpretation, and troubleshooting guidance. Use when: (1) Planning binding kinetics experiments, (2) Troubleshooting poor/no binding signal, (3) Interpreting kinetic data artifacts, (4) Choosing between SPR vs BLI platforms.

日本語の概要は準備中です。原文の説明を表示しています。

Workflow for untargeted or targeted metabolomics including preprocessing, normalization, annotation, statistics, and pathway mapping.

日本語の概要は準備中です。原文の説明を表示しています。

ESM2 protein language model for sequence scoring, embeddings, and plausibility checks. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships. For structure prediction, use chai1-structure-prediction or boltz-structure-prediction. For QC thresholds, use protein-design-qc.

日本語の概要は準備中です。原文の説明を表示しています。

End-to-end EHR predictive modeling pipeline with PyHealth, covering dataset loading, task definition, model training, evaluation, calibration, and clinical interpretation.

日本語の概要は準備中です。原文の説明を表示しています。

Workflow for ligand-receptor communication inference in single-cell or spatial data with sender-receiver summaries and cautious interpretation.

日本語の概要は準備中です。原文の説明を表示しています。

ESM2 protein language model for embeddings and sequence scoring. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships. For structure prediction, use chai or boltz. For QC thresholds, use protein-qc.

日本語の概要は準備中です。原文の説明を表示しています。

Workflow for read alignment, sorting, indexing, mapping statistics, and downstream-ready alignment artifacts.

日本語の概要は準備中です。原文の説明を表示しています。

Guidance for SPR and BLI binding characterization experiments. Use when: (1) Planning binding kinetics experiments, (2) Troubleshooting poor/no binding signal, (3) Interpreting kinetic data artifacts, (4) Choosing between SPR vs BLI platforms.

日本語の概要は準備中です。原文の説明を表示しています。

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.

日本語の概要は準備中です。原文の説明を表示しています。

Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.

日本語の概要は準備中です。原文の説明を表示しています。

Call the free Agnes text model API for chat completions, streaming answers, coding help, tool-calling experiments, and OpenAI-compatible text generation. Use when the user asks for 免费文本, 免费的文本模型, free text API, Agnes text, Agnes-2.0-Flash, free LLM calls, or wants to use a free chat/completion model through an Agent skill.

日本語の概要は準備中です。原文の説明を表示しています。

Read metrics off web dashboards with Firecrawl browser: public stats, status and transparency pages as well as analytics tools the user is signed in to. Use when the user wants numbers, KPIs or charts from a dashboard turned into a report, summary or date-range table, even without an explicit request to scrape.

日本語の概要は準備中です。原文の説明を表示しています。

Build a knowledge base from web content with Firecrawl. Use for local reference docs, RAG-ready chunks, fine-tuning datasets, documentation mirrors, topic corpora, or LLM-ready markdown organized from web sources.

日本語の概要は準備中です。原文の説明を表示しています。

Researches products across retailers and review sites with Firecrawl and recommends what to buy within the user's budget and preferences, with current prices and sources. Use when the user wants to compare products, find the best option or check reviews before buying, since prices and models change faster than training data. Adds to a cart only when asked and a signed-in browser profile exists.

日本語の概要は準備中です。原文の説明を表示しています。

Find and qualify new prospects with Firecrawl Alexandria people and company data: people by role, seniority, company, industry, size, location or technology, target accounts that match criteria, or the right contacts at companies, returned as a ranked, sourced table or CSV. Also extracts lead lists from a database or directory the user names, and refreshes a prospect list with only new matches. Use when the user wants a lead list, prospects, target accounts or the people to reach out to at companies that fit criteria. Not for enriching people or companies the user already supplied (use firecrawl-lead-research).

日本語の概要は準備中です。原文の説明を表示しています。

Analyze influencer performance metrics across TikTok, Instagram, YouTube, Bilibili, and Kuaishou. Compare engagement rates, audience growth, content consistency, and cross-platform presence for data-driven partnership decisions.

日本語の概要は準備中です。原文の説明を表示しています。

Enrich any entity — companies, domains, emails, or people — with verified data from multiple sources. Combines Apollo, Strale, LinkedIn, and Akta data to fill gaps in your CRM, lead databases, or research datasets with production-quality enrichment.

日本語の概要は準備中です。原文の説明を表示しています。

Apply validate data in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses validate data or its strengths fit the task.

日本語の概要は準備中です。原文の説明を表示しています。

Apply sql queries in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses sql queries or its strengths fit the task.

日本語の概要は準備中です。原文の説明を表示しています。

Design production-ready music prompts and optionally generate music through SandBase. Use for songs, instrumentals, soundtracks, jingles, loops, or multi-part music; use a speech or sound-effect workflow when music is not the main deliverable.

日本語の概要は準備中です。原文の説明を表示しています。

Apply sql optimization patterns in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses sql optimization patterns or its strengths fit the task.

日本語の概要は準備中です。原文の説明を表示しています。

Analyze estimated website traffic, engagement, rankings, channel mix, and geographic distribution through SandBase. Use for domain benchmarking, acquisition-channel analysis, or traffic trend research; do not present third-party estimates as first-party analytics.

日本語の概要は準備中です。原文の説明を表示しています。