SentrySkills - AI agent security framework with 33+ detection rules. Protects against prompt injection, data leaks, unsafe commands, and code vulnerabilities.
INVOKE THIS SKILL when creating, reading, updating, or deleting Arize AI integrations. Covers listing integrations, creating integrations for any supported LLM provider (OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM, custom), updating credentials or metadata, and deleting integrations using the ax CLI.
Vibe Memory，简称 vbm。用于为 Codex 与 Claude Code 初始化 .ai 项目记忆层、追加受控规则、启用全局引导，并在开发任务中读写已验证记忆。
Analyze a session transcript with AI and generate structured insights (prompt quality, strategy critique, key decisions, takeaways) for the rewind viewer.
[SPEC] Clear description of when this skill should be activated. Include keywords that Claude uses to decide whether to auto-invoke. The description is CRITICAL for auto-activation — be specific.
Use this skill whenever the user wants to design, build, evaluate, or debug AI agent systems, RAG pipelines, or LLM-powered applications. Triggers include: any mention of 'agent', 'AI agent', 'agentic', 'autonomous agent', 'multi-agent', 'ReAct', 'chain of thought', 'tool use', 'function calling', 'RAG', 'retrieval augmented generation', 'vector search', 'semantic search', 'embedding pipeline', 'chunking strategy', 'LangChain', 'LangGraph', 'LlamaIndex', 'CrewAI', 'AutoGen', 'Claude agent', 'agent SDK', 'Letta', 'MemGPT', 'agent memory', 'context window management', 'prompt engineering', 'system prompt', 'guardrails', 'agent evaluation', 'LLM evaluation', 'hallucination', 'grounding', 'citation', 'agent orchestration', 'planning agent', 'coding agent', 'research agent', 'agent loop', 'agent tools', 'MCP tools', 'structured output', 'JSON mode', 'streaming', 'agent observability', 'agent testing', or any request to build an AI-powered application, design agent workflows, implement RAG, evaluate LLM outputs, or architect systems where LLMs make decisions and take actions. Also use when the user asks 'how do I build an AI agent?', 'how should I chunk my documents?', 'why is my RAG returning bad results?', or wants to connect an LLM to external tools and data. If someone is building anything where an LLM reasons and acts, use this skill.
discipline, persistent connections, done signals. Triggers on Cross-Claude
Orchestrate AI agents (Claude Code, sub-agents, etc.) for software development workflows. Use when coordinating multiple AI assistants or planning AI-driven development processes.
An AI-friendly CLI for Jira designed for maximum efficiency and security. All output is structured JSON — no human-readable formatting, no interactive prompts.
Hand off the current Claude Code session to Microsoft Teams for mobile continuation
Persistent memory across sessions. Automatically captures your work and provides relevant context from past sessions. Shared with Claude Code.
This skill should be used when the user asks to 'evolve CLAUDE.md', 'update CLAUDE.md from experience', or 'self-evolve'. Scans conversations and notes to extract actionable findings and appends them to CLAUDE.md.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
