AI Developer Tool / Agent Skills / Prompting
A set of 20 Claude Code skills distilled from real engineering failures, each packaged as a short rule set with a pre-flight checklist and install instructions.
The page clearly presents a usable AI-adjacent product: a collection of 20 agent skills for Claude Code, each based on a concrete failure, with examples of the skill structure, install paths, and the intended use by coding agents or humans. The snapshot gives enough detail to understand what it is, how it is organized, and how someone would use or install it.
The snapshot doesn’t show the full contents of the individual SKILL.md files, so visitors can’t judge the depth of each skill or how much practical guidance each one contains beyond the excerpts. It also doesn’t show maintenance signals such as recent updates, releases, or issue activity.
Last evaluated 21 days ago. Current rank #634. Down 3 spots in the rankings.
A local-first Node.js utility that redacts emails, phone numbers, paths, secrets, URLs, and other identifiers from LLM prompts, then rehydrates responses locally using session-based mappings.
Self-hosted, OpenAI-compatible AI gateway for private RAG, natural-language data access, and tool-calling agents. It connects files, databases, vector stores, APIs, and MCP tools through one backend with auth, observability, and governance features.
A Claude Code skill that lets the model inspect live camera frames so it can verify hardware displays, spot wiring issues, and check physical UI behavior on real devices.
Runtime safety net for LLM agents that detects runaway token growth, classifies failure patterns, and suggests fixes without extra LLM calls. The project includes a Rust core, Python SDK, examples, benchmarks, and benchmark claims across multiple models and runs.
