Browse Skills

Show recent Claude Code sessions across all projects, making it easy to pick up where you left off. Provides project paths, summaries, and resume commands, and can reopen all sessions in new terminal tabs.

Orchestrates the complete agricultural research-to-publication workflow, from journal selection and research to writing, figures, peer review, and final manuscript. Use when you want end-to-end management of an agricultural paper.

Generate spec-reliable App Store screenshots from HTML/CSS panels, with optional AI-generated assets. Ideal for store listings, marketing panels with device frames, and screenshot localization/translation.

Generate spec-reliable App Store screenshots from HTML/CSS panels. Supports localization, AI-generated stickers, device frames, and automated validation for App Store Connect submission.

Implement a piece of work based on a spec or set of tickets, using test-driven development, typechecking, and code review before committing.

Investigates a question using primary sources such as official docs, source code, and specs, then writes the findings to a Markdown file in the repo. Use when you need facts gathered or reading work delegated to a background agent.

Synthesizes the current conversation and codebase context into a spec (PRD) and publishes it to the project issue tracker with appropriate labels.

Breaks a plan, spec, or conversation into tracer-bullet tickets with blocking edge declarations, published to an issue tracker.

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

Copy approved design prototypes into the repo, verify artifact completeness, and request explicit lock approval before derivation begins.

Automatically detects long sessions, high token usage, or bulky context and enables the appropriate Paleo token-saving skills to optimize token consumption without manual intervention.

Practical guide for querying Brazilian court process metadata and movements from the DataJud public API. Use when integrating with or debugging DataJud Elasticsearch queries, handling common errors like 504/429, or syncing process movements.