Loading...
Loading...
Found 3,920 Skills
End-to-end pipeline from unlabeled ml_app traces to a bootstrapped evaluator suite. Runs trace classification → root cause analysis → eval bootstrap in sequence with user checkpoints. Use when user says "run the eval pipeline", "go from traces to evals", "bootstrap evals end to end", "classify then RCA then bootstrap", "build an eval set from scratch", or wants a guided walkthrough from production data to evaluator code.
Attach judges to AI Config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.
Generate beautiful Excalidraw diagrams from natural language. Diagrams that "argue visually" — built-in Playwright visual validation loop, brand-customizable palette, and 3.2k+ GitHub stars. By coleam00.
Use when working with UnifAPI public-data APIs or the UnifAPI MCP server: connecting OAuth MCP clients, discovering operations, calling social/search/scrape/news APIs, troubleshooting UnifAPI auth, or deciding between MCP OAuth and API-key fallback. Always use before asking for UnifAPI credentials or calling UnifAPI tools.
Builds geocoding workflows in CARTO that convert street addresses or place names into geographic coordinates. Triggers when the user mentions geocoding, address to coordinates, address resolution, geolocate addresses, "add geometry from addresses", lat/lon from address, place name to point, address matching, forward geocoding, converting addresses to points, or has tabular data with address columns but no spatial geometry column and needs to create one.
Choose and configure the data warehouse engine connection for CARTO (BigQuery, Snowflake, Redshift, Postgres, Databricks, Oracle).
Redis Query Engine (RQE) guidance covering FT.CREATE schema design, field type selection (TEXT, TAG, NUMERIC, GEO, GEOSHAPE, VECTOR), DIALECT 2 query syntax, efficient FT.SEARCH and FT.AGGREGATE queries, zero-downtime index updates via aliases, and the SKIPINITIALSCAN option. Use when defining a search index on Hash or JSON documents, picking between TEXT and TAG for filtering, writing FT.SEARCH queries with filters and SORTBY, managing or swapping indexes in production, or troubleshooting slow searches with FT.PROFILE.
Vendor-neutral skill to analyze onboarding funnel dropoff and propose prioritized interventions.
Core Oodle CLI usage — auth, output formats, time flags, file input, and common patterns for all oodle commands.
This skill should be used when the user asks to "set up oodle integration", "onboard to oodle", "integrate kubernetes with oodle", "connect AWS to oodle", "install oodle collector", or mentions setting up observability with Oodle. Discovers the environment, recommends matching integrations from available setup specs, and executes step-by-step installation. Not for querying existing metrics, logs, or traces (use /oodle-metrics-query, /oodle-logs, /oodle-traces instead).
Explains how to create and review TypeORM migrations. Use this skill whenever the user wants to change an entity, add or update schema-related database objects, generate a migration, or decide whether a database change should be handled through TypeORM metadata or a custom migration.
Use this skill whenever the user asks to read, summarize, review, create, revise, polish, format, preview, or export PowerPoint/PPT/PPTX presentations on Windows, including presentation creation from notes, documents, images, synthesized content, an existing deck, or a template. Use PowerPoint desktop automation through Windows COM for file-producing or editing work, with explicit confirmation before writes. For any new PPT based on documents, PDFs, reports, or synthesized source materials, require a detailed approved Markdown slide plan before producing PPTX unless the user already supplied a sufficient plan. For clear academic paper or literature-presentation tasks, offer optional coordination with nature-paper2ppt.