Search

Count how many times you swear at your coding agents

Métricas para evaluar LLMs en su capacidad de hablar una lengua sin datasets de Q&A

Asynchronous, persistent, key-value storage system for React Native.

A skill that translates colloquial Brazilian Portuguese messages into structured English prompts.

🔍 Find real academic papers across 5 scholarly databases & deep-read any open-access PDF — grounded, never fabricated. Runs on Claude & Codex. A lite, open-source edition of AcademiCats. 跨 5 大学术库检索真实论文、精读 PDF。可在 Claude / Codex 上使用。

让 AI 写出"你导师改过三遍之后"的那种论文 ✍️ 中文核心期刊文体级写作 Skill

A Claude Code skill for managing Slidev presentations — scaffold, style, review, polish, and deploy each deck as its own GitHub repo with automatic GitHub Pages publishing.

✍️ Turn your sources into polished academic writing — reviews, proposals, essays, SoPs, résumés — every citation cross-checked, not invented. Runs on Claude & Codex. A lite, open-source edition of AcademiCats. 用你的文献写出有据成稿、引用逐条核对 —— 可在 Claude / Codex 上使用。

🧪 Peer-review your draft across 5 lenses, methodology checked against the right standard per paper type (STROBE/PRISMA/CONSORT/COREQ/Toulmin). Referee letter + scored verdict. Runs on Claude & Codex. A lite, open-source edition of AcademiCats. 按论文类型套用学术标准的模拟同行评审 —— 可在 Claude / Codex 上使用。

Elite frontend design taste for Claude Code / Cowork — a merged synthesis of emilkowalski/skill, pbakaus/impeccable, and leonxlnx/taste-skill. Typography, color, motion, components, anti-slop.

Claude Code skill that audits and revises academic papers against paper-type and venue conventions. Six paper types, five venues, tiered voice rules.

Claude Code skill — delegate coding tasks to Opencode, supervise via git diff & save 50-90% Claude token usage

No description available

Stacks storage library

Reusable cognitive operation factories for llm-ports: classify, score, draft, summarize, extract, plan, analyze. Configure once at definition time, call many times.

OpenAI SDK adapter for llm-ports. Implements LLMPort and EmbeddingsPort. baseURL support covers 10+ OpenAI-compatible providers (Azure, Groq, Together, Fireworks, DeepInfra, Perplexity, Cerebras, LiteLLM proxy).

Google Gemini adapter for llm-ports — native @google/genai SDK integration with bundled pricing, content-block translation, validation repair, and image-size + URL validation.

Ollama native adapter for llm-ports. Local LLMs via the Ollama daemon. Implements LLMPort, EmbeddingsPort, and ModelManagement (list/pull/delete/health).

Boruna: a deterministic, capability-safe programming language and framework for LLM-native applications