Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
arcgram
SkillsArcgram — an interactive diagram engine for human–AI collaboration: an AI agent draws its reasoning as an auditable node-and-edge flow and self-audits it, delivered as one standalone HTML file. (Arcgram the AI diagram tool — not Archigram.)
git clone https://github.com/jovesun-lab/arcgram.git -
claude-dd
SkillsPortable Claude Code profile — 8-step dev loop, CLAUDE.md pre-commit gate, zero-hallucination policy. Install once, carry it to any machine.
git clone https://github.com/kopp0510/claude-dd.git -
DocPenny PDF Generator
MCP serversGenerate HTML to PDF documents in bulk or single — raw replacements or based on conditions, loops
-
SiliconBridge
MCP serversHuman-in-the-loop API for AI agents. CAPTCHA, OTP, KYC, and approvals by real humans.
-
agentwork-mcp
MCP serversOfficial MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
agentwork-mcp@0.1.3 -
seven-dpt-mcp
MCP serversFeynman's twelve-problems method as an MCP server: dormant problems + an evoke loop for new tricks.
seven-dpt-mcp@0.1.5 -
IdentArk Gateway
MCP serversZero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
-
Rami Code Review
MCP serversAI code review for GitHub PRs with an MCP autofix loop for Claude Code and Cursor
-
Caption-Pack
MCP serversDeterministic social-caption API: hooks, bodies, CTAs + hashtags as JSON. No LLM in the loop.
-
SUMMARU Breath
MCP serversBreathing guide with voice and bowl, looping music, binaural beats, and a player link for users.
-
Budgethelm
MCP serversSee AI agent token spend per project and model, and stop agents that loop or burn tokens.
-
mcp-client-for-ollama
MCP serversHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences.
git clone https://github.com/jonigl/mcp-client-for-ollama.git -
seo-skills
SkillsFree global SEO/GEO skill for Claude Code, Codex & 10 agent hosts — 18 market portals, 56 stdlib scripts, 672 golden tests, self-update intel loop, monitoring daemon, CI gates. Multilingual GEO, pSEO, CWV, penalty recovery.
git clone https://github.com/everyinfra/seo-skills.git -
Elicitly Pro
MCP serversHuman-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail
-
arifOS — Constitutional AI Governance
MCP serversConstitutional AI governance: 11 mega-tools, 13 floors, VAULT999 ledger. Human-in-loop by design.
-
The High Council
MCP serversSeveral models from different labs plan in a blind proposal, debate and review loop. Your own keys.
the-high-council@0.8.4 -
mdreview
MCP serversHuman-in-the-loop document review: an agent pushes a draft, a person comments, the agent revises.
-
GenPark Jinja-Like Prompt Template Renderer
MCP serversSafe zero-dependency Jinja-like prompt template parser and renderer supporting for-loops, if-conditi
https://github.com/Alpha-Park/genpark-jinja-like-prompt-template-renderer-skill/releases/download/v1.0.1/genpark-jinja-like-prompt-template-renderer-skill-v1.0.1.mcpb -
Ask a human expert
MCP serversHuman-in-the-loop expert for when your agent is stuck: math, optimization, operations research, AI.
-
handinloop-mcp-server
MCP serversHuman-in-the-loop document extraction: submit a doc, get validated fields and an audit trail.
handinloop-mcp-server@0.9.1 -
metaharness
Agents & frameworks🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
git clone https://github.com/ruvnet/metaharness.git -
curated-claude-code
SkillsA small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.
git clone https://github.com/Sanexxxx777/curated-claude-code.git -
planwright
SkillsAutopilot for spec-driven development on Claude Code: sign off a spec and a guardrailed agent fleet builds, reviews, and delivers draft PRs. Scales from one feature to an agentic software factory. You keep sign-off and merge.
git clone https://github.com/inkatze/planwright.git -
aihappey-chat
SkillsBrowser-native multi-provider AI client with chat, Agents, MCP, Skills, Plugins, Decisions, BYOK/OAuth and human-in-the-loop workflows.
git clone https://github.com/achappey/aihappey-chat.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.