Developer Tools / Code Assistant
A searchable index of Claude Code skills, subagents, plugins, and marketplaces, each scored on whether it actually loads. The site says listings are rebuilt nightly from GitHub and skills.sh and includes breakdowns for score components, install counts, and last commit data.
The page is clearly an AI/developer tool directory with a specific utility: it catalogs Claude Code-related repositories and scores them on loadability. The crawl shows substantial public-facing evidence, including category browsing, ranking views, scoring methodology, listing counts, and example entries with facts like install counts and commit recency.
The snapshot shows the index and scoring system, but not the underlying checks for individual listings or how the 0–100 score maps to failures in practice. It is also hard to tell how complete the source coverage is beyond GitHub and skills.sh, or whether the data has any known gaps.
Last evaluated 20 days ago. Current rank #108. Holding steady in the rankings.
CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.
Mercemur is a store automation platform with three interfaces: a REST API, an MCP server for AI agents, and a CLI for editing storefronts as files. The docs show authentication, scopes, rate limits, error handling, pagination, idempotency, and a large API surface for catalogue, orders, customers, pricing, and money.
A zero-dependency C++23 CLI and MCP server that gives coding agents a ranked map of a repository, including call context, blast radius, and tests to run.
Traccia is an AI agent observability and governance platform with OpenTelemetry-native tracing, runtime policy enforcement, prompt registry, evals, cost attribution, and compliance evidence export.
