Agent skills for Claude Code

Run an autonomous Humanize-governed SGLang SOTA performance loop for one LLM model: first perform a fixed fair SGLang benchmark against…

Verdict-first standards review (PASS / PASS WITH CONCERNS / FAIL) of a code change — GitHub PR, branch, local diff, or pasted diff…

shadcn/ui component patterns including CVA variants, OKLCH theming, cn() utility, and composition.

Find and fix drift between docs and code.

Autonomous AI pentester for web apps and APIs.

Create, consume, or manage MotherDuck data shares, including audience grants, table filters, and refresh policy.

Perform thorough code reviews with security, performance, and maintainability analysis.

Shared artifact registry, common artifact patterns, and integration validation.

Build a shared, self-persisting knowledge ledger as a Claude Artifact, a private page that stores its own data, renders itself from that…

Automatic GitHub credential detection and verification

SharePoint integration via Apideck's File Storage unified API — same methods work across every connector in File Storage, switch by…

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API…

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

Google Sheets: Append a row to a spreadsheet.

Dry-run audit + targeted cleanup for shell command history.

Write robust, portable shell scripts with proper error handling, argument parsing, and testing.

Use when writing or reviewing production Bash scripts that need strict error handling, safe file operations, argument validation, cleanup…

Use when configuring ShellCheck, fixing ShellCheck findings, choosing Bash versus POSIX analysis mode, setting project suppressions, or…

ShellCheck validation as a non-negotiable 2025 workflow practice.

Five-phase umbrella playbook for an initiative shepherd.

Local text-to-speech via sherpa-onnx (offline, no cloud)