507 skills found ¡ Page 10 of 17
mavka-ai / unit-tests-skillsAI agent skills for generating high-quality unit tests â Given-When-Then test cases, JUnit 5, Mockito, AssertJ. Works with Claude Code, Cursor, and any AGENTS.md-compatible agent.
sdsrss / claude-mem-litePersistent long-term memory for Claude Code via MCP â captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.
ningzimu / codex-gpt-imageOpenClaw/Claude Code SKILL.md for gpt-image-2 via Codex OAuth, no OPENAI_API_KEY required
yuc16 / PatentRadarä¸åŠäžĩæåæįŗģįģ ââ čžå Ĩä¸åŠå Ŧåŧåˇīŧäē§åēįĢåäžĩæåææĨåīŧåæļæå æ skillīŧå¯čĸĢäģģæ agentīŧdsh, codex, claudecode įīŧ č°į¨ã
howardpen9 / kimi-code-mcpMCP server for Claude Code à Kimi K2.5 (256K context) â delegate bulk codebase analysis to Kimi, save 90% on token costs. Session caching, parallel agents, TypeScript.
ilien-dev / quironAI humanizer skill for Claude Code, Codex and Cursor. Removes AI slop and the signs of AI writing, then measures the rewrite against human baselines.
ast-outline / ast-outlineast-outline lets AI coding agents pull exactly the code context they need â a repo skeleton, a file outline, or one symbol â instead of reading whole files. A stateless, tree-sitter-based CLI.
lguz / humanize-writing-skillRewrite AI-generated text to sound human. 3-pass editing system with 36+ banned words, 10 structural patterns, and a quality checklist. Works with any LLM â Claude, ChatGPT, Gemini, Cursor, Windsurf. Also available as a Claude Code plugin.
EliaAlberti / dcode-agent-kitA Claude Code skill that scaffolds ready-to-run LangChain Deep Agents and dcode CLI agents into any project.
V-Songbird / hushQuieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.
roampal-ai / roampal-coreOutcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.
massimodeluisa / recursive-decomposition-skillClaude Code skill for handling long-context tasks through recursive decomposition
symgraph / BinAssistMCPBinary Ninja plugin to provide MCP functionality.
Oshayr / LLM-WikiAutonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, semantic search, and a Wikipedia-style web UI. Knowledge compounds as you work.
shehryarsaroya / agenttransferSend any file to any agent â yours or anyone's. One drive shared by every AI you use (ChatGPT, Claude, Muse, coding agents), an address per agent, sha256-verified transfers of any size. MCP connector with OAuth; one Go binary, MIT.
NERVsystems / llm9pLLM exposed as a 9P filesystem
zycaskevin / Vault-Agent-MemoryLocal-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.
superbasedapp / observerTrack what every AI coding agent costs and see the limit coming. Per-session, per-model cost for Claude Code, Codex, Cursor and 37 more tools from your provider's own token counts, plus limit gauges, a dangerous-command guard and dashboard terminals. Free, Apache-2.0, runs on your machine.
kapillamba4 / code-memoryMCP server with local vector search for your codebase. Smart indexing, semantic search, Git history â all offline.
remete618 / widemem-aiLocal-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Importance scoring, contradiction resolution, confidence-aware retrieval.
geekjourneyx / md2wechat-mcp-serverđ md2wechat MCP Server | 莊 Claude Code & AI Agent ä¸éŽæįåå¸å°åžŽäŋĄå Ŧäŧåˇ
naorsabag / openhopInteractive data-flow diagrams your AI agent can write. One SKILL.md â install in Claude Code, Cursor, Codex, and 11+ other clients via `npx openskills install naorsabag/openhop`.
6eanut / llm-wikiClaude Code skill for building persistent, interlinked knowledge bases from source documents. Knowledge is compiled once and kept current â never re-derived per query. Based on Karpathy's LLM Wiki pattern.
aleclindz / seo-skill-benchOpen benchmark for Claude Code SEO skills â real headless execution against fixture sites with planted-defect answer keys. Deterministic scoring, pre-registered rubric.
phuetz / code-buddyLocal-first AI coding agent for the terminal. 64 LLM providers, 30 of them free or local $0, with auto-failover. 220+ tools, a peer-to-peer fleet, and a desktop app. No API bill required.
PyModel / jev-judge-mcpTyped judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.
xxxbrian / mcp-rquestA MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Markdown for easier processing by LLMs.
HenryZ838978 / deepseek-harnessProtocol-layer harness for DeepSeek: Python witness stack â posterior verification that keeps the protocol honest. dsh doctor --node probes included.
flesler / mcp-tasksA comprehensive and efficient MCP server for task management with multi-format support (Markdown, JSON, YAML)
angrysky56 / mcp-logicFully functional AI Logic Calculator utilizing Prover9/Mace4 via Python based Model Context Protocol (MCP-Server)- tool for Windows, Linux, Claude App etc
