agentry

Authoring skills and review support for building AI agent extensions: create and review skills, subagents, commands, rules, prompt templates, and plugins/marketplaces that follow open agent conventions.

Code review, integrated review orchestration, test-engineering, review publishing, and specialist subagents that catch correctness, security, maintainability, and test-quality issues with actionable guidance.

Author and triage collaboration artifacts across the change lifecycle: change requests (feature requests, bug reports, refactor proposals) that frame the Why, and design proposals or RFCs that answer the How, for work carried out by humans or AI agents.

Lightweight documentation authoring for software repositories, currently focused on accurate README creation and maintenance.

Git workflow and Conventional Commits skills for branching, merging, rebasing, pull requests, releases, and well-formed commit messages.

Security audit skill that runs a threat-driven review of code: maps the attack surface and trust boundaries, hunts vulnerability classes (injection, auth/authz flaws, SSRF, secrets, weak crypto, and more), rates findings by likelihood and impact, and reports exploit scenarios with concrete remediations.