Agent skills for Zed

Picks which Cursor model a task should run on for a Pro Plus account (Composer 2.5 Fast, Grok 4.6, Auto Cost, GPT-5.6 Sol/Terra/Luna…

Choose the appropriate CausalPy experiment class from a causal question, data structure, treatment assignment, and identification…

Christian mystical wisdom through Aramaic lens - Kingdom within, Christ consciousness, feminine divine, embodiment navigation

Use PROACTIVELY when the user wants to test, verify, or interact with a local or remote web app in the browser.

Chrome extension development guide. Use for creating browser extensions, manifest files, background scripts, content scripts, Chrome APIs…

Automates the verification of acceptance criteria by controlling an active Chrome browser to perform UI and API testing with detailed…

Run local test/style checks and open GitHub PRs for lance-context.

Classify CI failures — distinguish clear regressions from infra flakes and security-test failures.

Create cinematic scroll-driven landing pages with Lenis smooth scrolling, GSAP ScrollTrigger, scroll-linked progression, staggered text…

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

Audit in-text/reference parity, DOIs, claim support, and citation style.

Use when formatting citations and references for a Journal of the American Academy of Religion (JAAR) article.

Stateful MCP-first producer for branded AI UGC shorts.

Integrate Clari export pipeline testing and validation into CI/CD.

Build Clari revenue analytics: pipeline coverage, forecast accuracy,

Deploy Clari export pipelines to production with Airflow, Cloud Functions,

Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand.

Use this skill whenever the user's instruction is too generic or unspecific to act on directly, whether or not a file is attached.

Score any MCP server, API, or CLI for agent-readiness using Clarvia AEO (Agent Experience Optimization).

Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude…

Use when Codex should ask Claude CLI for an adversarial challenge review that pressure-tests implementation direction, design choices…