Results for “text-generation-metrics”

Evaluates the correlation between automatic text generation scores and human quality ratings, including robustness to domain and quality drift, using metrics like Kendall's Tau and Pearson correlation.

Generates a skill that computes and documents overall book metrics and chapter-by-chapter metrics for intelligent textbooks.

Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.

DALL-E: Zero-Shot Text-to-Image Generation

从真实的帖子、文章、发布说明、文档或网站文案中构建基于源材料的写作风格档案，然后在内容、外展和社交工作流中重复使用该档案。当用户希望保持声音一致性而不使用通用的AI写作套路时使用。

Evaluates text-to-image generation models by decomposing assessment into five specialized skills (object presence, count, spatial relations, scale, and text rendering) and open-ended prompts, producing interpretable binary scores with visual and textual explanations.

Score any piece of writing for AI-generation tells and produce a weighted 0-100 scorecard with flagged evidence and ranked fixes. Use this skill whenever the user asks "does this sound AI-written", "run this through the AI detector", "score this writing", "check this for AI tells", "would this pass as human", "humanize check", or wants any article, blog post, email, or copy audited for AI patterns before publishing. Also use it when the user pastes or points to text and asks how it reads, whether it's too "ChatGPT-ish", or wants a QA pass on generated content. Works on pasted text, files, and URLs.

AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.

Evaluates geometric consistency in text-to-video generation by measuring structural and motion coherence across camera trajectories, detecting deformation and occlusion artifacts in static scenes.

SynthText: Synthetic Data for Text Detection

Call the Gemini API for text generation, chat, multimodal understanding, image/video/audio generation, streaming, function calling, structured output, and managed agents using the Interactions API in Python and TypeScript.

Evaluates text-to-speech systems by measuring distributional distance between synthetic and real speech across five factors, producing a scalar score without subjective MOS ratings.

Provides startup metrics frameworks and stage-specific benchmarks for SaaS, Marketplace, Consumer, and B2B models, including investor-ready dashboard generation.

Set optimal line lengths for readability across typography scales and responsive layouts.

Creates modular typography scales with size, weight, and line-height relationships for consistent digital interfaces.

Multi-channel personalized message generation with 3 tiers of personalization

Phi-1.5: Textbooks Are All You Need II

Generating AI image-generation code using the Gemini API. Handles text-to-image generation, image editing, and prompt optimization. Use when image generation code is needed.

AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.

Generate consistent, auditable release notes from Conventional Commits, compute semantic version bumps, and enforce commit format linting.

Generates at most one token recommendation and one prediction-market pick per run, each with a falsifiable thesis, entry, sizing, and kill criterion. Returns NO_PICK when no candidate meets the bar.

Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.

Design a comprehensive product metrics dashboard with key metrics, data sources, visualization types, and alert thresholds.

<!-- IJFW: narration-not-applicable -->

Improves typography by fixing font choices, hierarchy, sizing, weight, and readability so text feels intentional. Use when the user mentions fonts, type, readability, text hierarchy, sizing looks off, or wants more polished, intentional typography.

Generates a long-form blog post with magazine-style typography, including masthead, hero, figures, pull quotes, and author bio.

Measures distributional similarity between original GAN-generated images and their semantically manipulated counterparts using the Fréchet Inception Distance (FID) metric.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

Improves typography by fixing font choices, hierarchy, sizing, weight consistency, and readability, making text feel intentional and polished.

Generates optimized prompts for AI video and image generation across multiple platforms, using cinematic styles and behavioral frameworks for commercial outcomes.

Detect and humanize AI-generated Chinese text. 20+ rule detection categories plus statistical features (sentence-length CV, short-sentence fraction, comma density, perplexity, GLTR, DivEye) plus scene-aware LR fusion (rule × 0.2 + LR × 0.8) trained on three scenes: general / academic / longform 长文本 (≥1500 字)。Unified CLI: ./humanize {detect,rewrite,academic,style,compare}. 8 style transforms (casual/zhihu/xiaohongshu/wechat/academic/literary/weibo/novel)。 Multi-paragraph rewriting (paragraph length CV、跨段 trigram 重复) plus best-of-N humanize (默认 N=10 取最低 LR)。165 replacement patterns + CiLin 同义词词林 38873 with collision blacklist。 Academic paper AIGC reduction for CNKI/VIP/Wanfang (知网/维普/万方 AIGC 检测降重)。 Pure Python, no dependencies, offline。v5.0.0 — HC3 fused 准确率 95%、学术 hero 100→35 (-65)、 工作汇报 96→13 (-83)、长篇博客 96→41 (-55)。 Use when user says: "去AI味", "降AIGC", "人性化文本", "humanize chinese", "AI检测", "AIGC降重", "去除AI痕迹", "文本改写", "论文降重", "知网检测", "维普检测", "AI写作检测", "让文字更自然", "detect AI text", "humanize text", "reduce AIGC sc

Use when writing Textual TUI CSS styles or checking valid CSS properties

Access AWS Bedrock foundation models for generative AI, including text generation, embeddings, and image generation, with CLI and Python examples.

Writes X/Twitter threads and single tweets in the user's own voice — the same craft standard as `linkedin-post-writer`, adapted for X's shorter, faster format. Use when drafting an X/Twitter thread, turning an insight into a tweet, or reviewing a thread draft for tone. Normally invoked by `writing-system` once X is the chosen platform, but works standalone too.

Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.