Agent skills for Perplexity

Use when creating or updating the project skill discovery config — generates or regenerates .dh/skill_discovery.yaml by scanning the repo…

This skill should be used before any Snowflake command to verify MCP connectivity, guide users through access provisioning, and set the…

Comprehensive knowledge for interactive setup and validation of the AWS EKS + Helm + Keycloak + Harness ecosystem.

Decide when Zoom MCP is the right fit and produce a safe setup plan for Claude.

Fast structured generation and serving for LLMs with RadixAttention prefix caching.

Perform SGLang code review in the style of human maintainers by consulting the full non-agent PR review episode corpus from project start…

Replay-first debug flow for SGLang serving problems.

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.

shadcn-vue for Vue/Nuxt with Reka UI components and Tailwind.

Comprehensive GLSL shader techniques for creating stunning visual effects — ray marching, SDF modeling, fluid simulation, particle…

Find and fix drift between docs and code.

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

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

Automate SharePoint tasks via Rube MCP (Composio): document libraries, sites, lists, and content management.

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

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

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