Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
16 Claude Code skills for data engineers: profile a new source, investigate a failed run, review a change, document the platform. Most end in a page you can share.
git clone https://github.com/DataWithBaraa/claude-code-data-engineering-skills.git -
build-it
SkillsAutonomous delivery orchestrator for Claude Code — hand it a goal and a numbered Definition of Done, it runs the whole job to completion
git clone https://github.com/DevOtts/build-it.git -
claude-show-your-work
Agents & frameworksClaude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.
git clone https://github.com/iamumeransari/claude-show-your-work.git -
awesome-llm-observability
Skills50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.
git clone https://github.com/ContextJet-ai/awesome-llm-observability.git -
temporalite-archived
Tools & appsAn experimental distribution of Temporal that runs as a single process
git clone https://github.com/temporalio/temporalite-archived.git -
spark-agent
Agents & frameworksSparkWork is a local-first desktop Agent workbench for professional development and complex work. Orchestrate workflows, collaborate across Agent sessions, route tasks to the right models, and extend the workspace with custom tools and apps. Reviewable, steerable, reversible runs on macOS, Windows and Linux.
git clone https://github.com/alexanderizh/spark-agent.git -
claude-seo-skills
Skills60 free Claude Skills for SEO and AI search. Built by Hawk Academy + StudioHawk. Drop into Claude Desktop and run.
git clone https://github.com/lhitches/claude-seo-skills.git -
Azure Container Registry
Public APIsMetadata API definition for the Azure Container Registry runtime
-
Compute Engine API
Public APIsCreates and runs virtual machines on Google Cloud Platform.
-
e2b
MCP serversCreate and manage secure sandboxes for running AI agent code
mcparmory-e2b@1.0.5 -
Apple Shortcuts
MCP serversList, inspect, and run Apple Shortcuts on macOS.
apple-shortcuts-mcp@1.1.7 -
OpenHCS
MCP serversInspect, author, validate, and run high-content microscopy workflows.
openhcs@0.8.6 -
seristack
MCP serversRun YAML-defined shell command stacks as MCP tools
https://github.com/TechXploreLabs/seristack/releases/download/mcp-v0.4.6/seristack-darwin_amd64.mcpb -
MCP Trace
MCP serversQuery OpenTelemetry traces from agent runs through MCP.
abhishekash-mcp-trace@0.1.1 -
Sounio Compiler
MCP serversCheck, compile, run, and test Sounio programs locally.
sounio-mcp-server@0.1.0 -
mcp-server-commands
MCP serversAn MCP server to run arbitrary commands
@agent-infra/mcp-server-commands@latest -
Scripthold
MCP serversSecure encoding-aware local workspace runtime for AI agents
https://github.com/zoster81/scripthold/releases/download/v4.0.1/scripthold_windows_amd64.mcpb -
WattFigure
Public APIsUS electricity rates by state, with appliance and EV charging running costs
-
modelrun
MCP serversReplicate models, collections, versions, and predictions: browse and run.
@reneturcios/modelrun@0.1.0 -
AgrusScanner
MCP serversWindows network scanner that finds AI/ML services and MCP servers on your network (shadow AI discovery). Signed, self-updating detection signatures. Runs as an MCP server too.
git clone https://github.com/NYBaywatch/AgrusScanner.git -
jason-ai
SkillsJason AI: an AI SDR harness. The runtime's source, the skills, plugins, contracts, install path and releases.
git clone https://github.com/reply-team/jason-ai.git -
great_cto
SkillsYou already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.
git clone https://github.com/avelikiy/great_cto.git -
claude-qa-flow
SkillsQA workflow for AI coding agents: ticket → reviewed test plan → real-browser run with independent evidence review → bug tickets. Claude Code, OpenCode, any Agent Skills harness.
git clone https://github.com/QAMarcos/claude-qa-flow.git -
Flaky Test Detector
Prompts--- name: flaky-test-detector description: Finds flaky tests from repeated CI runs: parses JUnit XML or a CSV run history, flags tests that both pass and fail (confirmed when on the same commit), ranks them by flip and…
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.