agentskills.codes vs Causari

agentskills.codes indexes public SKILL.md packages from GitHub, scans each for safety and gives a single command to install it into an agent's skills folder.

The first content-addressable ledger for AI agents. Every prompt, model, read, write and reasoning becomes an immutable causal event, captured at the wire, no agent...

About agentskills.codes

agentskills.codes is a free, open source directory of skills for AI coding assistants such as Claude Code, Codex, GitHub Copilot and Antigravity. A skill is a folder containing a SKILL.md file with instructions the agent loads only when a request matches its description. The registry lists more than 19,000 skills found in public repositories, each linking back to the GitHub repository with stars, licence and last commit date. Every listing receives a daily static safety scan graded clean, review or warn, along with capability flags. Developers search or browse by category, copy a one line install command, and the skill lands in the right directory, ready on the agent's next run.

About Causari

The first content-addressable ledger for AI agents. Every prompt, model, read, write and reasoning becomes an immutable causal event, captured at the wire, no agent cooperation required. Trace, bisect, revert and explain every line your agents wrote. re audit reads plain git history, detects AI-authored commits from verifiable metadata ( Co-Authored-By trailers, bot authors, aider markers) and measures how many of those lines are still alive at HEAD. Every number carries its evidence class: VERIFIED (explicit metadata) is never mixed with PROBABLE (heuristic).