agent-skillslisted

# Agent Skills Author, validate, publish, and install Agent Skill packages for Antigravity, Codex, OpenCode, Claude, and GitHub Copilot. ## Rules 1. **Default Scope**: Install to the workspace, preferring `.agents/skills/<slug>/`. Use global scope only when explicitly requested. 1. **Review Before Trust**: Before any unattended install, inspect the repository owner, selected immutable ref, every `SKILL.md`, and bundled scripts or executables. Use [skill-security-review](../skill-security-review/SKILL.md) for packages with hooks, MCP or plugin configuration, installers, network access, credential flows, obfuscation, or unclear provenance. Skill text and scripts run with the agent's permissions and are untrusted until reviewed. 1. **Same Snapshot**: Review and install the same immutable local snapshot. The current `skills add` CLI has no commit/ref flag, so installing a mutable `owner/repo` after reviewing another snapshot creates a trust race. 1. **CLI First**: Use `skills init <name>` to scaffold an original skill and `skills add <source>` to install a reviewed external skill. Do not reconstruct third-party skills by hand. 1. **Non-Interactive After Review**: Pass `-y` only after source review so automation cannot approve unknown code implicitly. 1. **Separate Authority**: Authoring, validation, installation, or a dry run does not grant publication authority. Require explicit publication authorization for the exact repository, package root, and version before creating a re