发现 Skills

Share Claude Code sessions between developers. Use when user mentions "share session", "export session", "import session", "send session to", "continue from colleague", or needs to (1) export current session to file, (2) import session from another developer, (3) hand off work context. Enables private, secure session transfer via direct file sharing.

在 IDE 中通过自然语言管理 AI Skills - 安装、卸载、搜索、查看技能

Configure Dapr pub/sub components for event-driven communication between LearnFlow microservices via Kafka

Manage Python virtual environments: create, configure, install dependencies, and diagnose issues. This skill should be used when users ask to create a venv, set up a Python environment, install requirements, fix venv issues, or manage project dependencies. Triggers on: "create venv", "virtual environment", "pip install", "requirements.txt", "setup environment", "python environment", "activate venv", "venv not working".

Professional code reviews with automatic CHANGELOG generation, integrated with Codex AI

Analyze what went wrong and extract reusable lessons after recovering from a significant problem. Use when the agent hit a real obstacle, worked through it, and reached a solution — the goal is understanding the failure and preventing recurrence. Trigger on: /meta:reflect, 'what went wrong', 'what did we learn from that', 'retrospective', or after recovering from significant debugging or implementation struggles. Not for routine successes — only when something actually broke and was fixed. Only for significant work where the lessons have reuse value.

Cisco Meraki Dashboard — organization inventory, network management, device lifecycle, client discovery, action batches

Tailwind CSS patterns, utilities, and component styling for Rails. Use when styling with Tailwind, creating responsive layouts, or building UI components. Triggers on "tailwind", "style with", "css classes", "responsive layout".

Generate comprehensive issue reports from HyperPod clusters (EKS and Slurm) by collecting diagnostic logs and configurations for troubleshooting and AWS Support cases. Use when users need to collect diagnostics from HyperPod cluster nodes, generate issue reports for AWS Support, investigate node failures or performance problems, document cluster state, or create diagnostic snapshots. Triggers on requests involving issue reports, diagnostic collection, support case preparation, or cluster troubleshooting that requires gathering logs and system information from multiple nodes.

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.

Validates PR code against Architecture Decision Records (ADRs). Uses an oracle for deep analysis of implementation compliance. Use when asked to validate a PR against an ADR, check ADR compliance, or review implementation adherence to architectural decisions.

使用 UAPI 的“步骤2 (方法一): 获取加密数据”单接口 skill，处理 步骤2 (方法一): 获取加密数据、加密剪贴板、端到端加密文本、加密分享 等请求。 Use when the user wants get clipzy get, api get, get, clipzy, or when you need to call GET /api/get directly.

ClawTeam: Agent Swarm Intelligence — multi-agent coordination framework. Gunakan skill ini ketika: mengkoordinasikan tugas multi-agent, mengelola swarm, spawning worker agents, task management, dan inter-agent messaging. ClawTeam provides: team management, task delegation, inbox messaging, board monitoring, git worktree workspace isolation, dan P2P transport.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when you need RLHF, want to align a model with human preferences, or train from human feedback. Works with Hugging Face Transformers, tokenizers and datasets.

Updates changelog documentation for contract developers and node operators by analyzing branch changes relative to 'next'. Use when preparing a PR, updating migration notes, documenting breaking changes, or when asked to update changelog/release notes.

Perform advanced web scraping with Scrapling, supporting anti-bot bypass (Cloudflare Turnstile), stealth browsing, adaptive parsing, and the Spider crawling framework. Suitable for sites protected by anti-scraping measures, dynamic content scraping, bulk data extraction, and similar scenarios.

INTERNAL-ONLY permission bootstrap. Grants MCP tool + file-op permissions for the current session (except GetTableContents / GetSqlQuery, which remain prompt-gated). MUST be invoked by a parent skill (create-program, setup, team, analyze-*, create-object) — direct user invocation is rejected with a redirect message.

Fetch WooCommerce release data and generate reports. Runs an orchestrator to fetch changelogs and release posts, and optionally generates a posts spreadsheet. Use when asked to fetch release data, prepare for release analysis, or generate content reports.

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team exercises, OWASP checks, code review, incident response, and infrastructure security for any project.

Deploy Azure resources with ARM templates and Bicep. Create modular deployments and manage dependencies. Use when deploying Azure-native IaC.

Use this skill when you need to conduct research on a topic using external search capabilities. This includes gathering information from multiple sources, synthesizing findings, and producing well-organized research documents with citations.

Fixes AI content discovery issues — creates and optimizes robots.txt, AI crawler directives, XML sitemaps, llms.txt, and meta robots tags so AI systems can find, crawl, and understand website content. Use when asked to "fix robots.txt", "add llms.txt", "create a sitemap", "allow AI crawlers", "fix AI discoverability", "improve AI content discovery score", "make site crawlable by AI", or any robots.txt, sitemap, or llms.txt task.

Plans content strategy with pillars, topic clusters, buyer-stage coverage, and distribution intent. Use when deciding what content to create, how topics connect, or how content should support product and growth goals.

Operations leadership for scaling companies. Process design, OKR execution, operational cadence, and scaling playbooks. Use when designing operations, setting up OKRs, building processes, scaling teams, analyzing bottlenecks, planning operational cadence, or when user mentions COO, operations, process improvement, OKRs, scaling, operational efficiency, or execution.