jagc

Mandatory read before creating git commits. Stages only intended files, groups changes into logical commits, and writes concise Conventional Commits-style subjects.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Canonical jagc scheduled-task operations playbook. Use when the user asks for one-off or recurring scheduled work, asks to manage existing jagc tasks (create/list/get/update/delete/run/enable/disable), or when you want to suggest automating repeatable/future work as a task (get user approval first). Covers the exact `jagc task` command contract, JSON-first low-turn workflows, RRULE + one-off scheduling, deterministic relative-time -> UTC conversion, and verification policy.

Use this skill before creating/modifying any `AGENTS.md` (including create/edit/move/split). It explains why AGENTS guidance should stay scoped and terse, when to edit root vs subtree files, and what content belongs in AGENTS.md.

Use this skill before creating/modifying any skill (global, project, or package-level). It defines hard rules for writing tight, information-dense `SKILL.md` files, valid frontmatter, and when to move details into `references/` or `scripts/`.