发现 Skills

Perform custom classification statistics, cross-analysis, and visualization on Excel data, and compute comprehensive scoring and grading based on multi-dimensional metrics (such as text length, term density, regex matches, etc.). Suitable for multi-category data distribution statistics and text content difficulty/quality assessment scenarios.

Extracts a specified categorical column and computes the count and proportion of each category, producing high-resolution bar charts, pie charts and other combined visual reports. Suitable for analyzing the distribution of categorical data.

Automatically choose a read strategy based on data size (convert large files to Parquet), extract key metrics for unit-consistency validation and ranking analysis, and output a downloadable results table.

Intelligent cleaning, cross-sheet reconciliation, and visualization analysis for multi-sheet Excel workbooks.

Base-layer skill for the SenseNova-Skills project, providing low-level APIs for image generation, recognition (VLM), and text optimization (LLM). This skill does not preprocess inputs; it only calls backend services and returns results. This skill is not user-facing and is intended for upper-layer skills only.

Environment diagnostic for the PPT family. Validates sn-image-base, API keys, Node runtime, and optional deps; interactively writes .env for required vars. Runs before sn-ppt-entry; does not modify sn-image-* skills.

Search Chinese social platforms: Bilibili videos, Zhihu Q&A, and Douyin videos. Some platforms require cookie authentication; stability varies by platform.

Processes categorical share data that contain percentage strings by filling in missing dimensions and generating stacked bar charts to visually show how multi-dimensional compositions change over time or across categories.

Jira conventions for the CNTRLPLANE project used by OpenShift teams

Intelligently identify missing test coverage based on component type

Detailed implementation guide for validating proposed release blockers

List all OCPBUGS components, optionally filtered by team

Fetch and analyze component health regressions for OpenShift releases

Automatisierte Wiederherstellung gelöschter Google Workspace Accounts und Login in Chrome.

Transform ANY repository into a visually stunning, instantly understandable experience for BOTH developers AND non-developers. Mermaid diagrams for devs, benefit-focused infographics for users, 3-second-hook psychology for maximum impact. Enterprise-level with llms.txt, social preview, CI badges, and AI discoverability.

Understand and work with WebF's async rendering model - handle onscreen/offscreen events and element measurements correctly. Use when getBoundingClientRect returns zeros, computed styles are incorrect, measurements fail, or elements don't layout as expected.

Build the project. Use when the user says 'build', 'compile', or after making code changes that need compilation.

Claiming work is complete without verification is dishonesty, not efficiency. Use when ANY variation of success/completion claims, ANY expression of satisfaction, or ANY positive statement about work state.

Headless browser automation via playwright-cli for testing, screenshots, scraping, and parallel sessions. Use it for UI testing, web scraping, screenshot capture, or any browser-based workflow.

Parallel UI validation that discovers user stories from YAML files, fans out browser-qa agents to test each story, and aggregates pass/fail results with screenshots. Use for acceptance testing, UI review, or regression testing across multiple user stories.

Use when Git needs to switch user.name and user.email automatically based on repository location (per-folder identities via includeIf gitdir).

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Set up the Orderful SuiteApp's "Packaging Data Source" feature for a customer whose carton/item data lives in non-standard custom records (Manhattan WMS, BluJay, custom 3PL feeds, etc.) instead of the SuiteApp's native customrecord_orderful_carton. Walks through identifying candidate records, mapping fields to Orderful's required column contract, building a validation CSV from a real Item Fulfillment, authoring the NetSuite Analytics Dataset in the UI, pulling it back via SDF for version control, and setting the customer's Packaging Data Source entity field. Use when the user mentions an alternative packing source, a customer that already has carton records (but not Orderful's), Manhattan/3PL-fed packing data, or asks how to power 856 ASNs from existing carton/SSCC data.