Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
www-project-agent-memory-guard
MCP serversRuntime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
git clone https://github.com/OWASP/www-project-agent-memory-guard.git -
agentic-brownfield-coding
SkillsClaude Code scaffolding and first steps for complex brownfield projects
git clone https://github.com/ralfstrobel/agentic-brownfield-coding.git -
architecture-diagram-skill
SkillsBuild click-through, animated system architecture diagrams as a single HTML file. Drop it into a workshop, design review, or onboarding doc and let people watch the data flow instead of reading static boxes-and-arrows.
git clone https://github.com/konraddzbik/architecture-diagram-skill.git -
lattice
Agents & frameworksInstall engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts.
git clone https://github.com/techygarg/lattice.git -
mcp-server-python
MCP serversPython MCP Server for Kestra — you can use it as a tool in Kestra's AI Agents
git clone https://github.com/kestra-io/mcp-server-python.git -
humanities-writing-companion
SkillsEnd-to-end humanities writing assistant — an Agent Skill (open SKILL.md format). 11 modes from Socratic research-question sharpening through AI-use disclosure. Bilingual (EN/中文), discipline-aware (literature/history/philosophy/art/religion/linguistics + cross-disciplinary). Four-layer critique, calibratable devils advocate, voice preservation.
git clone https://github.com/tizzy916/humanities-writing-companion.git -
qwen-image-3.0 API (qwenimage3.0 / qwen image 3.0): default $0.0206; 1K $0.0206; 2K $0.0206. Model id, prompts settings, curl and Python examples over an OpenAI-compatible gateway,
git clone https://github.com/qh7wn6hrf9tx/qwenimage3.0-qwen-image-3.0-prompts.git -
wan-3.0-video API (wan3.0video / wan 3.0 video): 480P $0.0329; 720P $0.0658; default $0.1315. Model id, prompts settings, curl and Python examples over an OpenAI-compatible gateway
git clone https://github.com/gslsvt43llzsaw/wan3.0video-wan-3.0-video-prompts.git -
Claudebox
MCP serversSelf-hosted MCP server exposing Claude Code as an agentic AI tool over streamable HTTP.
docker.io/psyb0t/claudebox:v2.8.7 -
code-virtuoso
SkillsSkills, sub-agents, and playbooks for Claude Code, Cursor, and any Agent Skills-compatible AI coding assistant.
git clone https://github.com/krzysztofsurdy/code-virtuoso.git -
tree-sitter-analyzer
Tools & appsCross-language-safe code-intelligence MCP for AI agents: 13 languages, family-gated call graph, blast radius, health grading, 8 facade tools, JSON envelopes, 100% local. Run miswire-audit on your repo.
git clone https://github.com/aimasteracc/tree-sitter-analyzer.git -
Claude-Code-Design-AI
SkillsClaude Design: AI UI/UX architect. Screenshot to React, Figma components, Tailwind CSS generator. Prototyping agent, design systems, wireframe renderer. SVG icon creator, dark mode toggle, responsive layout tool. Front-end code export, shadcn/ui integration, vector assets, branding assistant.
git clone https://github.com/mikesheehan54/Claude-Code-Design-AI.git -
altium-designer-mcp
MCP serversMCP server for AI-assisted management of Altium Designer component libraries
git clone https://github.com/embedded-society/altium-designer-mcp.git -
moodle-mcp
MCP serversMoodle LMS for LLM agents — courses, assignments, files, submissions in one static binary.
moodle-mcp@0.2.1 -
mcpspan
MCP serversAsk your agent about your MCP servers: failing tools, releases, clients, sessions.
mcpspan-mcp@0.15.0 -
rikkahub-agent-pure
Agents & frameworksRikkaHub Agent · Pure — an Android AI agent that survives long runs. Independent hardening pass on the rikkahub on-device agent: usage ledger & budgets, on-demand tools, expert sub-agents, cold memory, chained workflows. Kotlin/Compose, Shizuku/Termux/MCP. QQ group 1030362371.
git clone https://github.com/wuyhong715/rikkahub-agent-pure.git -
dcc-mcp-zbrush
SkillsPre-alpha ZBrush MCP adapter for AI agents to inspect high-poly meshes and subtools, manage brushes, and export OBJ assets through the DCC-MCP gateway using the official Python SDK.
git clone https://github.com/dcc-mcp/dcc-mcp-zbrush.git -
portugues-tecnico-controlado
SkillsSkill do Claude Code para linguagem controlada em português do Brasil — inspirada no ASD-STE100, com 9 regras próprias (incluindo corte de ruído de texto gerado por IA), ortografia do Acordo de 1990 e modo bilíngue EN/PT
git clone https://github.com/kayquer/portugues-tecnico-controlado.git -
humanizer-lint
SkillsA local, zero-dependency prose, copywriting, UI-text, and code-comment linter that flags stiff, AI-sounding writing (stock phrases, flat sentence rhythm, repeated wording) and tells you what to revise. Includes 8 language packs. A style checker, not an AI detector.
git clone https://github.com/yanstd888/humanizer-lint.git -
Asia/Ashgabat clock
MCP serversCurrent local time in Asia/Ashgabat.
-
codex-mcp-tool
MCP serversMCP server bridging AI assistants to OpenAI Codex CLI for code analysis and review
@trishchuk/codex-mcp-tool@2.7.0 -
claude-code-docs
SkillsEverything Anthropic ships for builders, archived as markdown and refreshed 4× daily. 4,200+ files: API, Claude Code, MCP, support, cookbooks, skills, plugins.
git clone https://github.com/thevibeworks/claude-code-docs.git -
claude-humanizer-svenska
SkillsClaude skill that removes AI writing patterns from Swedish professional text. Covers 16 pattern types including significance inflation, nominalization overuse, passive voice as false formality, anglification, and bullet/emoji formatting. Tuned for Nordic professional voice.
git clone https://github.com/nordefors-max/claude-humanizer-svenska.git -
pi-herdsman
Agents & frameworksAsynchronous Pi subagents and agent fleet orchestration for parallel coding agents with nested delegation, background work, and supervision in herdr.
git clone https://github.com/boadij/pi-herdsman.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.