agents

Fetch and read web pages using Lightpanda headless browser, or automate full browser interactions using agent-browser. Use when you need to read articles, documentation, any web content, or interact with web pages.

Fetch transcripts from YouTube videos for summarization and analysis.

Create an implementation spec and/or execution plan for a task. Self-discovers context before asking questions, then writes to docs/specs/ and/or docs/exec-plans/active/.

Grilling session that challenges a plan against the existing domain model, sharpens terminology, and updates documentation (`CONTEXT.md`, `CONTEXT-MAP.md`, ADRs) inline as decisions crystallize. Use when the user wants to stress-test a plan against the repo's language and documented decisions.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Review code changes, diffs, or files for correctness, architecture, security, quality, testing, and dependency risks.

Sets up repo-local methodology docs so shared engineering skills know this repo's issue tracker, triage label vocabulary, and domain doc layout. Run before first use of `grill-with-docs`, `zoom-out`, `improve-codebase-architecture`, future issue-workflow skills, or whenever those skills appear to be missing repo-local context.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Git and GitHub workflows: conventional commits, PR review, CI status, issues, and gh CLI. Load when committing code, creating or reviewing pull requests, checking CI, or interacting with GitHub.

Interact with Linear using the `linear` CLI for managing issues, projects, and teams.

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".

Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop immediately. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".

End-user control of cmux topology and routing (windows, workspaces, panes/surfaces, focus, moves, reorder, identify, trigger flash). Use when automation needs deterministic placement and navigation in a multi-pane cmux layout.

Audit this repository for documentation freshness and code design quality. Produces a structured report. Use when asked to audit, health check, review code quality, check design health, or do a maintenance pass.