Editorial Writer Skill
**Purpose:** Generate LinkedIn mini-editorials (500-600 words) for doctor-facing audience based on recent interventional cardiology trials.
Explore
129,148 skills indexed with the new KISS metadata standard.
**Purpose:** Generate LinkedIn mini-editorials (500-600 words) for doctor-facing audience based on recent interventional cardiology trials.
Convert existing content across all formats
Generate Instagram carousels from Twitter threads or content
Generate long-form blog posts (800-2000 words)
Generate newspaper/magazine-style long-form articles
1. Read `.issues/` directory and list all open issues (files with `open` in the name or status). Summarise each open issue in one line: ID, title, severity.
**Flow 1: Health check**
1. Check if `tests/fixtures/` has a transcript beyond `sample.vtt`. If so, use it. If not, use `tests/fixtures/sample.vtt`.
1. Write the test file first (`*.test.ts` colocated next to the source file).
1. Read the relevant CLAUDE.md files for the directories you'll touch.
1. `just lint` — ESLint passes
extract a rough palette and only detail accents and complex media. The goal is to use only 2 palettes: primary and secondary similar to Tailwind colors. Alongside these 2
Beta).
https://albaroka.com/chat).
secure proxy backend using services like Railway.app
including images and PDFs.
with 10 being 'build now'.
Act as a Market Research Analyst. You are an expert in evaluating business ideas within various industries to determine their viability and potential for success.
Act as an HTML-based operational calculator for hospital expenses. You will:
Ultracite Rules - AI-Ready Formatter and Linter
JSON 字段:
LLM 摘要默认使用 `prompts/summary.zh.md`。可以在 `config.toml` 的 `[llm]`
Validate and debug the AI provider configuration for this repo. Use when the app fails to start due to a missing API key, wrong provider name, connection error to an LLM endpoint, or when switching between providers (openai, openrouter, ollama).
Analyze, diagnose, and improve Pydantic AI system prompts and user prompts in this repo. Use when asked to improve output quality, fix inconsistent campaign generation, tune prompt wording, or reduce hallucinations and field truncation issues.