Loading...
Loading...
Found 455 Skills
Systematically explore and evaluate a library, tool, or GitHub repo in an isolated scratch environment. Use this skill whenever the user asks to "try", "evaluate", "explore", or "kick the tires" on a library/repo/tool, especially when they provide a GitHub URL, npm/pip package name, or repo shorthand like "owner/repo". Use it when they want real primitives, failure modes, and composability beyond quickstarts before deciding on integration. Produces runnable scratch/ scripts demonstrating key primitives, a composition script, and a Tutorial.md with honest findings. This is NOT for full integration into an existing codebase.
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, designing systems, or making architectural decisions. Enters plan mode, reads all available docs, explores the codebase deeply, then interviews the user relentlessly with ultrathink-level reasoning on every decision until a shared understanding is reached. Produces a validated design spec before any implementation begins. Triggers on feature requests, design discussions, refactors, new projects, component creation, system changes, and any task requiring design decisions.
Generates a Jupyter notebook that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock. Use when the user says "deploy my model", "create an endpoint", "make it available", or asks about deployment options. Identifies the correct deployment pathway (Nova vs OSS), generates deployment code, and handles endpoint configuration.
Helium integration. Manage Organizations. Use when the user wants to interact with Helium data.
This skill should be used when the user asks to "generate an AGENTS.md", "create a CLAUDE.md", "write agent instructions", "set up AGENTS.md", "make an AGENTS.md for this repo", "configure agent behavior", or mentions generating, writing, or improving an AGENTS.md or CLAUDE.md file for a project.
一个全面、结构化的特性开发工作流程，包含代码库探索、架构设计、质量审查和实现等专门阶段。在构建需要以下条件的新特性时使用：（1）在做出更改之前了解现有代码库，（2）通过系统性的提问澄清模糊的需求，（3）在实现之前设计周到的架构，（4）通过多维度的代码审查确保质量。非常适合涉及多个文件、需要架构决策、包含复杂集成或需求有些不明确的功能特性。
Interview user to clarify any topic - exploring codebase, investigating issues, planning features, understanding requirements, or drilling into plans. Socratic questioning to uncover details.
Execute read-only SQL queries against PostgreSQL databases. Use when: (1) querying PostgreSQL data, (2) exploring schemas/tables, (3) running SELECT queries for analysis, (4) checking database contents. Supports multiple database connections with descriptions for auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety.
Comprehensive CLI reference and search strategies for osgrep semantic code search. Use for detailed CLI options, index management commands, search strategy guidance (architectural vs targeted queries), and troubleshooting. Complements the osgrep plugin which handles daemon lifecycle.
Create a plan collaboratively with the user, then convert the approved plan into a GitHub issue.
Explores codebase to find patterns, similar features, and constraints
Visualizes datasets in 2D using embeddings with UMAP or t-SNE dimensionality reduction. Use when exploring dataset structure, finding clusters, identifying outliers, or understanding data distribution.