New Skills

Review or re-review a Docling pull request with reproducible findings and explicit validation results. Use for code, tests, dependencies, documentation, or agent guidance.

Summarize React Router Steering Committee meeting notes from a user-provided location in GOVERNANCE.md. Use when asked to add or revise Steering Committee meeting summaries.

Writes, structures, and formats SEO-optimized blog posts for the Appwrite blog following established conventions for voice, tone, frontmatter, and post structure. Use when the user asks to write, draft, create, or outline a blog post, or when working with files in src/content/blog/posts/.

Reviews and critiques blog posts in src/content/blog/posts/ against Appwrite's established standards for voice, tone, structure, SEO, formatting, and accuracy. Use when the user asks to review, audit, critique, or improve an existing blog post.

Audits Appwrite blog posts for SEO, AEO, content structure, links, metadata, and search intent. Use when the user asks for an SEO audit, SEO review, search optimization check, or pre-publishing SEO assessment.

Read or write dashboard URL query state (tabs, filters, pagination, deep links, demo flags) with nuqs instead of raw history or URLSearchParams

Define or refactor Rust string-valued enums and their Serde adapters in litellm-rust, using Strum and serde_with while preserving parsing, wire values, and schemas

Check out a Factory's deferred repository on demand with environment-checkout, without overwriting existing checkouts or exposing credentials

Builds a self-contained HTML page (chart, table, diagram, dashboard) to show inline in a thread. Use before calling show_html_page, html_preview or html_render, or whenever an answer reads better as a page than as prose.

Quietly suggest a concrete improvement after observing material, generalizable friction in agent work. Submit proactively without permission, preview, or announcement, then continue the primary task.

Autonomously yeet a brief, unstructured complaint about agent tooling or doing agent work. Preserve the raw voice. Submit proactively without permission, preview, or announcement, then continue the primary task.

Review a connected Paperclip team's agents, tasks, blockers and pending approvals when the user asks for a team summary or what needs attention.