查找技能

Investigate cloud configuration weaknesses across AWS, GCP, and Azure, including public storage, exposed services, and leaked credentials. Find candidates in public information and JavaScript, then verify data access and permissions to establish practical impact.

中文简介正在准备中。当前显示英语简介。

• Checking public access to S3, GCS, and Azure Blob storage
• Reviewing exposed serverless and managed services
• Assessing CloudWatch RUM guest role permissions

Test CDN-backed websites for cache poisoning and Web Cache Deception, where private pages are mistakenly cached as public content. The skill guides cache behavior checks, input testing, and independent-client verification to establish reproducible impact.

中文简介正在准备中。当前显示英语简介。

• Reviewing cache behavior on CDN-backed websites
• Checking whether private pages enter public caches
• Verifying cached responses influenced by headers

Plan and coordinate penetration tests with checklists covering objectives, scope, environment preparation, tester selection, monitoring, and follow-up. Helps teams define deliverables, prioritize vulnerabilities, arrange fixes and verification, and clean up test accounts and artifacts.

中文简介正在准备中。当前显示英语简介。

• Defining penetration test objectives and scope
• Preparing test environments and monitoring
• Selecting testers and agreeing on report requirements

Assess Azure, AWS, and GCP security through resource inventories, authentication checks, permission reviews, and misconfiguration testing. Supports authorized assessments that document exposed credentials, rate risks, and recommend improvements for each cloud platform.

中文简介正在准备中。当前显示英语简介。

• Inventorying cloud resources and permissions
• Checking for exposed credentials and secrets
• Testing the impact of cloud misconfigurations

Apply safeguards when analyzing external articles or posts. Validate URLs, limit fetched content, label source text as untrusted data, and clean analysis output so embedded instructions are treated as material rather than commands.

中文简介正在准备中。当前显示英语简介。

• Checking external URLs before fetching content
• Preparing article or post analysis
• Passing untrusted text to subagents

Compare Zephyr changes using the same prepared dataset and matching execution settings. Analyze Finelog metrics for each processing stage to distinguish CPU efficiency, elapsed time, and peak memory changes, then report improvements, regressions, or tradeoffs.

中文简介正在准备中。当前显示英语简介。

• Compare Zephyr performance before and after a PR
• Assess speed gains against additional CPU usage
• Check peak memory and out-of-memory regressions

Check a new internal Marin developer’s local environment and access to development services. Distinguish setup problems from missing permissions, repair authorized local issues, and provide a checklist of verified capabilities and remaining access requests.

中文简介正在准备中。当前显示英语简介。

• Setting up a new Marin developer
• Validating a completed development setup
• Diagnosing missing service access

Turn a specified GCP access request into a reviewable Pulumi change and pull request. Select the narrowest suitable role and encrypt personal email identities, covering resource permissions and Cloud Run viewer access through IAP, an access gateway.

中文简介正在准备中。当前显示英语简介。

• Prepare a request for GCS bucket read access
• Add a viewer to a Cloud Run service protected by IAP
• Prepare service account impersonation permissions

Investigate GitHub security incidents by querying archived public activity with BigQuery. Recover recorded details of deleted issues and pull requests, identify the accounts involved, and reconstruct timelines to check claims about repository activity.

中文简介正在准备中。当前显示英语简介。

• Reconstructing a security incident timeline
• Recovering recorded text from deleted issues or pull requests
• Checking claims about repository activity

Collect GitHub activity and local git history as evidence for investigations, then save, filter, and share it as JSON. The skill also supports recovering deleted content from archives and checking stored evidence against its original sources.

中文简介正在准备中。当前显示英语简介。

• Preserving GitHub commits, issues, and pull requests as evidence
• Examining local commits no longer linked to branches or tags
• Recovering deleted GitHub content from archives

Store large multidimensional arrays in compressed chunks, small sections that can be read separately. Guides local and cloud storage, partial reads and writes, and integration with NumPy, Dask, and Xarray for scientific data workflows.

中文简介正在准备中。当前显示英语简介。

• Processing arrays larger than available memory
• Reading and writing array subsets on S3 or GCS
• Appending new time steps to scientific datasets

Create or update Codex skills that package specialized knowledge, repeatable workflows, and tool instructions. The guide covers concrete use cases, folder structure, reusable resources, starter generation, and basic validation of names and required metadata.

中文简介正在准备中。当前显示英语简介。

• Turning recurring work into a reusable skill
• Packaging company knowledge and API instructions
• Reorganizing an existing skill and its reference files

Build production systems for machine learning models, from deployment to monitoring and retraining. The skill also guides LLM integration and retrieval augmented generation, which uses retrieved information to support answers, with scripts and architecture references.

中文简介正在准备中。当前显示英语简介。

• Deploying machine learning models to production
• Setting up model monitoring and retraining
• Building applications that answer using retrieved information

Configure machine learning training and batch jobs across multiple clouds with SkyPilot. The skill guides GPU selection, lower-cost cloud and region choices, and automatic recovery when discounted spot instances are interrupted.

中文简介正在准备中。当前显示英语简介。

• Choose a lower-cost cloud for GPU training
• Run long training jobs with recovery after interruptions
• Configure distributed training across multiple machines

Design and improve prompts and structured responses for AI applications. The skill also guides evaluation, retrieval augmented generation, which uses retrieved material to inform answers, and agent architecture, with references and scripts for production workflows.

中文简介正在准备中。当前显示英语简介。

• Improving prompts and response formats
• Evaluating answers based on retrieved documents
• Designing AI agent systems

Plan experiments, analyze data, and build and evaluate predictive models. The skill also covers explaining findings to stakeholders and designing production workflows for model deployment, monitoring, and retraining to support business decisions.

中文简介正在准备中。当前显示英语简介。

• Designing experiments and A/B tests
• Preparing model inputs and evaluating predictions
• Planning model deployment and monitoring

Build image and video AI systems for object detection and segmentation, which identifies separate image regions. The skill covers custom model training, dataset pipelines, inference optimization, real-time processing, and deployment and monitoring in production.

中文简介正在准备中。当前显示英语简介。

• Developing object detection and image segmentation systems
• Training custom vision models with project data
• Optimizing inference for real-time video processing

Create or improve Claude skills that package specialized knowledge, repeatable workflows, and tool instructions. The guide covers concise instructions, reusable scripts and resources, template initialization, validation, and packaging into a distributable .skill file.

中文简介正在准备中。当前显示英语简介。

• Turning recurring work into a reusable Claude skill
• Organizing company knowledge and API references
• Improving an existing skill after practical use

Find and download public cancer imaging datasets from NCI Imaging Data Commons. Filter scans and pathology images by metadata, preview them in a browser, check licenses, and generate source citations for research or AI training.

中文简介正在准备中。当前显示英语简介。

• Select cancer imaging datasets for AI training
• Find scans by cancer type, imaging modality, or anatomical site
• Preview radiology and pathology images in a browser

Use LaminDB to organize biological datasets, search their metadata, and track how analyses produce results. Standardize annotations with biological vocabularies, validate data structures, and record versions and computational history for reproducible research.

中文简介正在准备中。当前显示英语简介。

• Standardizing cell type annotations in single-cell data
• Searching datasets across multiple experiments
• Tracing analysis results back to their inputs and code

Draft case reports, diagnostic reports, clinical trial reports, and patient records using document-specific structures and templates. The skill guides completeness checks, patient de-identification, and documentation aligned with named clinical reporting guidelines and regulatory frameworks.

中文简介正在准备中。当前显示英语简介。

• Drafting case reports for journal submission
• Organizing radiology, pathology, and laboratory reports
• Preparing clinical trial and serious adverse event reports

Interactive setup wizard for the claude-ops plugin. Installs missing CLIs, configures env vars for each channel (Telegram, WhatsApp, Email, Slack, Notion, Linear, Sentry, Vercel), builds the project registry, and saves user preferences. Run once after installing the plugin or any time to reconfigure.

中文简介正在准备中。当前显示原文说明。

Deploy to Cloudflare (Workers, R2, D1), Docker, GCP (Cloud Run, GKE), Kubernetes (kubectl, Helm). Use for serverless, containers, CI/CD, GitOps, security audit.

中文简介正在准备中。当前显示原文说明。

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

中文简介正在准备中。当前显示原文说明。