Library
86,689 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
kharcha
SkillsTrack every expense automatically by converting bank messages into a clear, private spending ledger.
git clone https://github.com/Adnaninho/kharcha.git -
html-deck-kit
SkillsSpec + template + 6 themes + AI Skill for delivery-ready single-file HTML presentation decks (1600×900, speaker notes, 70% layout rule).
git clone https://github.com/Gavinluo19/html-deck-kit.git -
awesome-ai-agent-skills
SkillsCategorized index of 718 public GenPark AI agent skills, with tested Python packages and MCP integrations.
git clone https://github.com/alphaparkinc/awesome-ai-agent-skills.git -
fava-trails
MCP servers🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.
git clone https://github.com/MachineWisdomAI/fava-trails.git -
Anthropic: Claude Opus 5
ModelsClaude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
anthropic/claude-opus-5 -
Anthropic: Claude Opus 4.8
ModelsClaude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...
anthropic/claude-opus-4.8 -
webapp-testing
SkillsToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
/plugin marketplace add anthropics/skills -
workspace-architect
SkillsWorkspace Architect is a zero-friction CLI tool that provides curated collections of specialized agents, instructions, and prompts to supercharge your GitHub Copilot experience.
git clone https://github.com/archubbuck/workspace-architect.git -
klaussy-agents
SkillsA multi-agent context, rules, and hooks boilerplate generator. With a single command, it scaffolds conventions, namespaced skills, stack-appropriate settings, and interactive guardrails for seven major AI coding environments, matching each agent's native file formats and capability profiles.
git clone https://github.com/steph-dove/klaussy-agents.git -
AgentCompass
SkillsDeterministic multi-agent task router & subscription quota scheduler for Claude Code, Codex, Agy CLI (Antigravity), Grok, and Paseo. Routes sub-agents by model DNA, ability floor, and 5h/7d rate-limit windows with a PreToolUse spawn gate.
git clone https://github.com/akiiwa-games/AgentCompass.git -
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
anthropic/claude-opus-5:batch -
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...
anthropic/claude-opus-4.8:batch -
Anthropic: Claude Opus 4.5
ModelsClaude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
anthropic/claude-opus-4.5 -
Anthropic: Claude Opus 4.1
ModelsClaude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
anthropic/claude-opus-4.1 -
Anthropic: Claude Fable 5.2
ModelsClaude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...
anthropic/claude-fable-5.2 -
Data-Pro-Skill
SkillsData Pro Max: The Ultimate AI-Powered Intelligence Suite for Data Science, Survey Analysis, and Professional Reporting.
git clone https://github.com/pablodiegoo/Data-Pro-Skill.git -
content-generation-skills
SkillsMira AI content generation skills: genre playbooks and prompting knowledge for AI agents that generate video and images through the Mira MCP server
git clone https://github.com/Global-AI-Group-Inc/content-generation-skills.git -
EverOS-Tools
SkillsOfficial EverOS developer tools for AI coding assistants: migrate EverOS Cloud callers from the v1 API to v2 (Python SDK and raw HTTP), with a scan-only impact report.
git clone https://github.com/EverMind-AI/EverOS-Tools.git -
Relay
MCP serversMCP relay server for Claude Desktop <-> Claude Code communication
mcp-server-relay@1.2.4 -
flightwake
SkillsHand this repo to another person or another agent, and they can see how it was built: what was done, why each choice was made, and which traps were found.
git clone https://github.com/kaiwutech-TW/flightwake.git -
awesome-ai-agent-stack
MCP serversCurated map of 6,000+ open-source AI agent tools: coding agents, agent frameworks, MCP servers, RAG, memory and local LLMs, sorted by layer and ranked by GitHub stars.
git clone https://github.com/tayyabimam1/awesome-ai-agent-stack.git -
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
anthropic/claude-opus-4.5:batch -
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
anthropic/claude-opus-4.1:batch -
Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...
anthropic/claude-fable-5.2:batch
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.