数据与 AI技能

Turn blog data into inline SVG charts for HTML or MDX. Choose from seven chart types to show comparisons, trends, shares, or scores, with responsive sizing, screen reader descriptions, and source attribution.

中文简介正在准备中。当前显示英语简介。

• Compare before and after results
• Show market share or category proportions
• Visualize a trend over time

Choose useful metrics for a startup or feature based on its business model and stage. The framework helps separate decision-making measures from vanity numbers, select one current priority metric with a guardrail, audit dashboards, and set baselines, targets, and instrumentation plans.

中文简介正在准备中。当前显示英语简介。

• Choosing KPIs for a startup or feature
• Auditing a dashboard for vanity metrics
• Setting a north star metric and target

Calculate a controlled set of two-dimensional molecular descriptors and Morgan, RDKit, or MACCS fingerprints from standardized compounds. Review dataset quality through missing values, unusual ranges, repeated structures, and fingerprint density summaries.

中文简介正在准备中。当前显示英语简介。

• Calculate molecular descriptors for standardized compounds
• Generate Morgan, RDKit, or MACCS fingerprints
• Check missing or constant feature columns

Clean local chemical structure data from SMILES, CSV, SDF, or MolBlock files. Preserve each original record while standardizing structures, deriving parent forms, checking quality issues, and grouping duplicates for review or downstream analysis.

中文简介正在准备中。当前显示英语简介。

• Standardize a batch of SMILES or structure files
• Check valence, stereochemistry, or mixture issues
• Group records by original, standardized, or parent structure

Search a standardized compound library for similar structures or substructures, group molecules, and select diverse representatives. The skill also reviews indexing and risk records, while keeping the library unchanged and recording the parameters and results.

中文简介正在准备中。当前显示英语简介。

• Finding the closest structures to a molecule
• Filtering compounds by a SMARTS substructure
• Clustering a compound library

Review structured chemical reaction records while preserving their original entries. Check participants, reported roles, yields, duplicates, and element or charge differences, then produce searchable records and a review queue with clear reasons.

中文简介正在准备中。当前显示英语简介。

• Clean a batch of reaction SMILES
• Check ORD reaction records for quality issues
• Find duplicate reactions, role conflicts, or unusual yields

Design, audit, troubleshoot, or refactor the software harness that coordinates an AI agent. It offers provider-neutral guidance for model loops, tools, permissions, memory, planning, connectors, observability, evaluation, and safety across different domains.

中文简介正在准备中。当前显示英语简介。

• Planning an MVP agent architecture for a domain
• Auditing an agent’s tools, permissions, and safety
• Troubleshooting a stalled or unreliable agent run

Prepare a vector geospatial dataset for a PortalJS portal by converting its coordinate system, creating a map-ready PMTiles file and a queryable GeoParquet file, and registering both with the original data for an automatically rendered showcase.

中文简介正在准备中。当前显示英语简介。

• Turn GeoJSON into a portal map and spatial query view
• Ingest a zipped Shapefile from a URL
• Publish a GeoPackage layer with its original file

Generate DCAT catalog feeds for a PortalJS site so open data catalogs can harvest its datasets. The skill supports JSON-LD, Turtle, and RDF/XML formats, adds feed discovery, and checks conformance to selected profiles.

中文简介正在准备中。当前显示英语简介。

• Making a PortalJS catalog harvestable by an EU open data portal
• Preparing feeds for a US or national open data catalog
• Publishing catalog metadata in multiple RDF formats

Create a new PortalJS data portal from a project brief. The skill gathers missing details about pages, datasets, language, and catalog organization, then applies them to the PortalJS template and checks the generated project with type and localization checks.

中文简介正在准备中。当前显示英语简介。

• Starting a data portal from a short project brief
• Choosing how datasets are grouped in the catalog
• Creating a portal in a non-English interface language

Register a CSV, TSV, JSON, or GeoJSON source in an existing PortalJS portal. The skill adds it to the dataset catalog and routes local files or remote URLs so the catalog and showcase can display the data.

中文简介正在准备中。当前显示英语简介。

• Register a local CSV in a PortalJS catalog
• Add a public dataset URL without copying the file
• Publish a GeoJSON dataset through the portal

Add a line, bar, area, pie, or scatter chart to the showcase for a dataset already registered in PortalJS. The skill creates a reusable Chart component and displays it in the dataset’s Views section using the existing data source.

中文简介正在准备中。当前显示英语简介。

• Show yearly emissions as a line chart
• Compare imports and exports with grouped series
• Display a categorical budget breakdown as a pie chart

Describe what a registered dataset contains by inferring field types and constraints from tabular data, then adding catalog details such as license, sources, and keywords to datasets.json. Choose a standard or custom profile so the PortalJS showcase can display typed fields.

中文简介正在准备中。当前显示英语简介。

• Add inferred field types to a registered CSV dataset
• Record license, sources, and keywords for a dataset
• Set metadata for a JSON or GeoJSON dataset

Check a local or remote CSV or TSV for missing values, mixed types, duplicate rows, suspicious dates, and other common data issues. The skill returns a structured JSON report with column profiles and recommendations, while leaving the source file and project data unchanged.

中文简介正在准备中。当前显示英语简介。

• Checking a dataset before publishing it in a portal
• Investigating blank cells or garbled values in a showcase
• Finding duplicate rows and repeated identifier values

Connect a PortalJS catalog to a live CKAN instance through its API. The skill generates a small server-side client and updates search and dataset showcase pages to fetch CKAN data, while pre-rendering pages for static deployment.

中文简介正在准备中。当前显示英语简介。

• Connecting an existing PortalJS site to a CKAN catalog
• Showing CKAN datasets in the portal search page
• Filtering catalog results by organization or group

Plan a data portal before development by matching its purpose, data shape, audience, and constraints to choices for storage, catalog, compute, access, hosting, and metadata. The skill documents the recommendation and suggests the next build steps.

中文简介正在准备中。当前显示英语简介。

• Choose an architecture for a new data portal
• Compare storage and query options for a dataset catalog
• Plan a portal for public or access-controlled data

Add an interactive Leaflet map to a selected GeoJSON dataset’s PortalJS showcase. The skill can register a local or remote GeoJSON source, install the map dependencies, and render the map in the page’s Views section.

中文简介正在准备中。当前显示英语简介。

• Show a map alongside a registered GeoJSON dataset
• Register a local GeoJSON file and display it on a map
• Add a remote GeoJSON source to a PortalJS showcase

Migrate an ArcGIS Hub open data site into a PortalJS catalog. The skill collects the inventory, exports and converts spatial and tabular data for publishing, uploads files to Cloudflare R2 through Git LFS, and produces a report comparing source and derived data.

中文简介正在准备中。当前显示英语简介。

• Moving a city ArcGIS Hub catalog to PortalJS
• Migrating selected datasets from a Hub site
• Comparing exported data with its ArcGIS source

Add another file to an existing PortalJS dataset, such as a data dictionary, methodology document, or another period of data. The skill updates the dataset manifest and makes the showcase display a section for each resource.

中文简介正在准备中。当前显示英语简介。

• Adding a data dictionary to an existing dataset
• Attaching a methodology document to a dataset
• Adding another period's data as a separate resource

Move datasets from CKAN, DCAT catalogs, Socrata, OpenDataSoft, or ArcGIS into a static PortalJS catalog or another CKAN instance. It previews the collected records, then writes dataset metadata and links or copied resource files to the chosen destination.

中文简介正在准备中。当前显示英语简介。

• Moving a CKAN catalog into a standalone PortalJS portal
• Copying selected data.gov datasets into PortalJS
• Previewing a DCAT feed before importing it

Create a domain-specific skill bundle through discussion and source-based research. The deliverable includes a concrete workflow and flowchart, an adapter, a trap fixture for testing common failures, and a smoke evaluation that compares results with and without the bundle.

中文简介正在准备中。当前显示英语简介。

• Creating a reusable workflow for a new field
• Turning researched domain practices into an agent skill
• Testing a domain skill against a representative trap

Create and manage portable dstack presets for model inference optimization. A preset records the serving configuration, benchmark result, and hardware used, so teams can reuse the optimized setup across clouds, Kubernetes clusters, or bare-metal fleets.

中文简介正在准备中。当前显示英语简介。

• Finding an optimized inference baseline
• Optimizing inference by patching source code
• Recording results for new hardware

Create agent skills with clear procedures and metadata that follow the agentskills.io specification. Use it to structure a new skill directory, write step-by-step instructions, and make a skill easier to find through its description.

中文简介正在准备中。当前显示英语简介。

• Starting a new agent skill directory
• Writing a skill's procedural instructions
• Improving skill metadata for discoverability

Create or improve Claude skills with guidance on SKILL.md structure, reusable scripts, reference files, and packaging. The skill helps turn a task into practical agent instructions and resources, then refine them after use.

中文简介正在准备中。当前显示英语简介。

• Drafting a new Claude skill for a recurring workflow
• Organizing references, scripts, and assets for a skill
• Improving an existing skill’s instructions and metadata