All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 304,988
- 12,708
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse ai & agents skills
Showing 2,041–2,064 of 304,988 skills
- 421 Getting Started 3ef6c70aVoiceMode brings voice conversations to AI coding assistants. It works as both an MCP server for Claude Code and as a standalone CLI tool.Votes: 0GitHub stars: 9
- 360 Faq D6f435f1Quick answers to common questions. For comprehensive coverage, see the [Complete FAQ](reference/FAQ.md). ---Votes: 0GitHub stars: 9
- 360 Faq 396c0a25**Last Updated:** January 26, 2026 **Version:** 0.5.1 ---Votes: 0GitHub stars: 9
- 360 Faq 1839ca4bYes. Use the `langgraph` adapter. See [examples/langgraph/](../examples/langgraph/).Votes: 0GitHub stars: 9
- 357 External Review Ec9e2f47This step sends `claude-plan.md` to external LLMs (Gemini and Codex) for independent review using CLI subagents.Votes: 0GitHub stars: 9
- 3070 Llamaindex 332803dbLlamaIndex is a framework for building retrieval-augmented generation (RAG) pipelines. ---Votes: 0GitHub stars: 9
- 3057 Dspy Integration Summary F5bcd178DSPy + PyO3 Integration Skills - Project SummaryVotes: 0GitHub stars: 9
- 3021 4 Core Patterns 600b8150| # | Pattern | Concept | | :---: | :--- | :--- | | **1** | **[`1_simple_triage.py`](../../examples/basic/1_simple_triage.py)** | Classification & Linear Routing | | **2** | **[`2_reward_code_agent.py`](../../examples/basic/2_reward_code_agent.py)** | Code-First Agent Logic | | **3** | **[`3_support_helper_agent.py`](../../examples/basic/3_support_helper_agent.py)** | Lightweight Tool Assistant | | **4** | **[`4_fastapi_server.py`](../../examples/basic/4_fastapi_server.py)** | FastAPI Wrapper...Votes: 0GitHub stars: 9
- 3020 2 Architecture 9b1b58f4**`Lár` is not a heavy, complex framework. It is a tiny, powerful engine with 8 core "primitives." You can combine these "Lego bricks" to build any agent, from a simple chatbot to a complex, multi-agent orchestrator.** - The `GraphExecutor` **What it is**: The "Engine" or "Conveyor Belt." **Job**: A simple `generator` that runs one node at a time. It's the "dumb" loop that powers the "smart" nodes. It is also the "flight data recorder" that `yields` the audit log for each step. - The `GraphSt...Votes: 0GitHub stars: 9
- 3018 Release Notes V120 2db65d36**Observability & Debugging Update** This release focuses on "Glass Box" visibility, incorporating feedback from power users who need granular cost tracking and cleaner debug logs.Votes: 0GitHub stars: 9
- 3018 Project Analyzer Daee3003Analyzes a native Claude Code project for conversion into a companionVotes: 0GitHub stars: 9
- 3007 11 Context Optimizeragent 10c95447Analyzes Copilot Chat debug logs to audit context window utilization across agents. Identifies bloated prompts, redundant file reads, missing hand-off points, and wasted tokens. Produces actionable optimization reports with specific agent/skill refactoring recommendations. Reusable across any project with custom agents. Does NOT modify agent definitions directly — produces recommendations only.Votes: 0GitHub stars: 9
- 3003 Beyond Vibe Coding 2653177c**Date**: 2026-02-01 **Evaluator**: Claude (Sonnet 4.5) **URL**: https://beyond.addy.ie **Author**: Addy Osmani (Engineering Leader, Google) **Publisher**: O'Reilly Media **Publication Date**: 2025 **Format**: Paid book ($B0F6S5425Y Amazon) + freemium web content **External References**: - Perplexity Deep Research: "Beyond Vibe Coding" book analysis - Simon Willison blog post (Sept 4, 2025) on title change from "Vibe Coding" - Gergely Orosz (Pragmatic Engineer) podcast interview (Oct 29, 2025...Votes: 0GitHub stars: 9
- 3002 Agentskills Io Specification 16dd0fd8**Date**: 2026-02-01 **Source**: [agentskills.io](https://agentskills.io/home) | [GitHub: agentskills/agentskills](https://github.com/agentskills/agentskills) (8.2K stars) | [GitHub: anthropics/skills](https://github.com/anthropics/skills) (60.1K stars) **Maintainer**: Anthropic (open development, community contributions) **Type**: Open specification + reference implementation + official skill library **License**: Apache 2.0 (spec + open skills), Source-available (document skills) ---Votes: 0GitHub stars: 9
- 2999 Ai Traceability C5cafdf2Industry standards, tools, and templates for AI-generated code attribution policiesVotes: 0GitHub stars: 9
- 2993 Mcp Sdk Summary 10755854**Date**: 2025-10-22 **Research Focus**: Existing MCP Python clients/SDKs for Figma integration ---Votes: 0GitHub stars: 9
- 2989 Iproute Review 943594e2Using the prompt `review-core.md` and the review prompt directory, do a deep dive regression analysis of the top commit, or the provided patch/commit.Votes: 0GitHub stars: 9
- 2964 Query Cda82841Query a user's index with Pinecone MCP. Accept an index name, input query, and optionally a top-k valueVotes: 0GitHub stars: 9
- 2964 Gepa Integration Analysis 120bea85We need to be able to integrate with other AI frameworks besides DSPY, so we can optimize the AI systems that our clients are already using. The most important AI frameworks we need to integrate with include Langchain, LangGraph, and OpenAI API.Votes: 0GitHub stars: 9
- 2959 Credential System Analysis 1da38287``` ┌──────────────┐ │ AgentRunner │ runner.py:_validate_credentials() └──────┬───────┘ │ ┌──────▼───────┐ │ validation │ validate_agent_credentials() │ (2-phase) │ Phase 1: presence Phase 2: health check └──────┬───────┘ │ ┌─────────────▼─────────────┐ Votes: 0GitHub stars: 9
- 2956 Vector C Cli Data Fetch F11d2333The prompt instructs the AI agent to fetch attacker-controlled content at runtime using `gh` CLI commands. The prompt itself may contain no dangerous expressions or env vars with attacker data, but the AI is directed to pull attacker content from GitHub at execution time. This vector is invisible to static YAML analysis because the data fetch happens inside the AI agent's execution environment -- the workflow YAML looks clean.Votes: 0GitHub stars: 9
- 2955 Vector A Env Var Intermediary 7903992fAttacker data flows from GitHub event context into `env:` blocks, and the AI prompt references those env var names -- the AI agent reads the attacker content from environment variables at runtime. The prompt field contains zero `${{ }}` expressions, making this pattern invisible to tools that only scan for direct expression injection.Votes: 0GitHub stars: 9
- 2950 Env Reference 3fae3281This document lists all environment variables supported by SkillLite, including default values, type descriptions, and usage scenarios. - **Quick Start**: Only `BASE_URL`, `API_KEY`, and `MODEL` are required to run - **Full Template**: See [.env.example.full](../../.env.example.full) ---Votes: 0GitHub stars: 9
- 2946 Rag Skill 937372f4The RAG (Retrieval-Augmented Generation) Architect skill provides comprehensive tools and knowledge for designing, implementing, and optimizing production-grade RAG pipelines. This skill covers the entire RAG ecosystem from document chunking strategies to evaluation frameworks, enabling you to build scalable, efficient, and accurate retrieval systems.Votes: 0GitHub stars: 9