Back to directory

DSkills

A collection of command-line tool skills for AI coding assistants such as Claude Code, Codex and Antigravity CLI, covering web search, semantic code search, delegating tasks between agents, literature search and other developer utilities.

DSkills

DSkills packages a set of installable skills, each wrapping an existing command-line tool or API for use by an AI coding assistant, including enhanced web search through the Grok and Exa APIs, semantic code understanding with IDE-like symbol operations, deterministic software-graph analysis, an incremental wiki generator for Obsidian vaults, a self-evolution engine for agents, delegating coding or research tasks between Claude Code, Codex CLI and Google's Antigravity CLI, crawling and summarizing trending GitHub repositories, fetching current library documentation through Context7, and searching CrossRef, OpenAlex, PubMed, Semantic Scholar and optionally Scopus for academic literature with deduplication and open-access PDF downloads.

Skills can be installed individually through Claude Code's plugin marketplace, through a separate agent-skills CLI tool, or by copying a skill's folder directly; some skills need additional Python dependencies installed first.

It is written in Python and released under the MIT license.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.