Loading...
Loading...
Found 286 Skills
Automate College Football Data tasks via Rube MCP (Composio). Always search tools first for current schemas.
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "replication lag", "partitioning strategy", "consistency vs availability", or "stream processing". Covers data models, batch/stream processing, and distributed consensus. For system design, see system-design. For resilience, see release-it.
Use when writing or running Nushell commands, scripts, or pipelines - via the Nushell MCP server (mcp__nushell__evaluate), via Bash (nu -c), or in .nu script files. Also use when working with structured data (JSON, YAML, TOML, CSV, Parquet, SQLite), doing ad-hoc data analysis or exploration, or when the user's shell is Nushell.
This skill should be used when the user asks to "use NumPy", "write NumPy code", "optimize NumPy arrays", "vectorize with NumPy", or needs guidance on NumPy best practices, array operations, broadcasting, memory management, or scientific computing with Python.
This Skill supports screening qualified stocks based on stock selection criteria (such as market indicators, financial indicators, etc.); it allows querying stocks, listed companies within specified industries/sectors, as well as component stocks of sector indices; it also supports related tasks such as stock, listed company, and sector/index recommendations, avoiding the use of outdated information by large models during stock selection.
Use when asked to generate multiple QR codes from CSV data, create bulk QR codes with tracking, or generate QR codes for events/products.
Collect validated Xiaohongshu image assets from normalized XHS datasets into local manifests and downloaded files. Use this when you need reproducible local media artifacts from note covers or other already-exposed remote asset URLs.
Reconcile general ledger to subledger for a trade date or period — match at the position or transaction level, surface breaks, and classify each break by likely cause. Use for daily or month-end recon runs across asset classes.
Earnings estimate revision analysis for listed companies via Longbridge — tracks analyst consensus revision direction (upgrade / downgrade), earnings surprise (SUE = standardised unexpected earnings), PEAD post-earnings drift signals (consecutive beats + upward revisions = positive momentum), and management guidance revision impact. Builds on raw data from longbridge-consensus. Triggers: "预期修正", "盈利修正", "分析师上调", "分析师下调", "超预期", "低于预期", "PEAD", "财报后漂移", "业绩意外", "管理层指引", "預期修正", "盈利修正", "分析師上調", "分析師下調", "超預期", "低於預期", "財報後漂移", "業績意外", "管理層指引", "earnings revision", "estimate revision", "analyst upgrade", "analyst downgrade", "beat miss surprise", "SUE", "PEAD post-earnings drift", "guidance revision", "estimate cut raise".
Assess construction data quality using completeness, accuracy, consistency, timeliness, and validity metrics. Automated validation with regex patterns, thresholds, and reporting.
Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.
Search ClinicalTrials.gov with natural language queries. Find clinical trials, enrollment, and outcomes using Valyu semantic search.