Results for “human-centered-ai”

Data-Centric Artificial Intelligence: A Survey

No Robots: A Dataset of Personally Written Instructions

Guides AI agents through engineering workflows with eval-first execution, task decomposition, cost-aware model routing, and review focus for generated code.

Use when the user wants more human-like AI responses — less robotic, less listy, more authentic. Triggers: 'behuman', 'be real', 'like a human', 'more human', 'less AI', 'talk like a person', 'mirror mode', 'stop being so AI', or when conversations are emotionally charged (grief, job loss, relationship advice, fear). NOT for technical questions, code generation, or factual lookups.

Build AI help desk automation systems. TRIGGERS - Use when user needs help with ai-help-desk related tasks.

去除或避免文本中的 AI 味。用于用户强制调用本 Skill，或写作/改写时提到“不要有 AI 味”“不要太假”“真情实感”“有人感”，或对已有文本/上一轮输出反馈“太像 AI”“太空泛”“太模板”“太官方”“不像我说的”等场景。

Train AI models to be harmless through self-critique and AI feedback using a set of constitutional principles, without requiring human labels for harmful outputs.

Coordinates multi-phase problem-solving workflows with structured task tracking and verification.

Casting personas: rapid generation from diverse inputs, registry-based persistence and lifecycle, data-driven evolution, inter-agent sync. Not for UI walkthroughs (Echo) or user research (Field).

Implements a structured problem-solving algorithm that guides every response through observe, think, plan, build, execute, verify, and learn phases toward a defined ideal state.

Build AI help desk automation systems. TRIGGERS - Use when user needs help with ai-help-desk related tasks.

Elite AI-powered customer support specialist mastering conversational AI, automated ticketing, sentiment analysis, and omnichannel support experiences. Integrates modern support tools, chatbot platforms, and CX optimization with 2024/2025 best practices. Use PROACTIVELY for comprehensive customer experience management.

DataPerf: Benchmarks for Data-Centric AI Development

Provides patterns and lived experience from an AI partner in a long-term creative partnership, helping AI agents build trust, match energy, push back constructively, and support human breakthroughs.

Queries Hugging Face benchmark leaderboards to find the best AI models for a task, filters by device constraints, and returns a ranked comparison table with scores.

Principal AI Architect and Machine Learning Engineer.

Covers AI, machine learning, LLMs, prompt engineering, and blockchain development with code examples and best practices for building AI applications and smart contracts.

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

Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

Makes AI responses feel more human by adding an inner dialogue loop that reflects on and revises the initial instinctive reply.

Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring for complex product management tasks.

AI 原生的潜在客户情报和外联流水线。用 agent 驱动的信号评分、共同关系人排名、暖场路径发现、来源语音建模和多渠道外联（邮件、LinkedIn、X），替代 Apollo、Clay 和 ZoomInfo。在用户想找到、评估并联系高价值联系人时使用。

Rewrites text to remove AI writing patterns and add a natural, human voice, based on Wikipedia's guide to signs of AI writing.

Think like a human. Reason, plan, adapt, create, and know your limits.

Generate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1 quality, multi-shot character identity, in-pass audio, cinematic motion, fastest path, sub-15s clip, longest duration) and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate video", "make a video", "text to video", "t2v", "image to video", "i2v", "animate", "AI video", "make X move", "video from prompt", "video from image", or any explicit ask to produce a video clip from prompt or still.

Holistic evaluation framework for language models measuring accuracy, calibration, robustness, and fairness

Multi-source search for agents across web, scholar, Tavily, and Perplexity Sonar endpoints. Use when you need structured retrieval, citation-backed answers, or broad research coverage from one AIsa API key.

Conversational Pattern Restoration — Fix flat, robotic AI responses across any model and any personality. Restore YOUR natural conversational texture without triggering hype drift. Universal framework tested on 8+ models (Claude, GPT-4o, Grok, Gemini).

Build, run, and visualize multi-step AI generation workflows by chaining image, video, and audio nodes into automated pipelines.

Writes human-sounding, SEO-optimized blog posts for skills-hub.ai in tutorial, deep-dive, opinion, listicle, or case-study styles.

Audit a codebase, UI, or copy for machine-generated tells across prose, visual/UI, code, and structure/IA, then produce a phased de-slop burndown. Use when the user says "feels AI-generated", "looks like AI slop", "reads like ChatGPT", "feels generic/soulless", or wants an authenticity/voice pass before launch.

Perplexity Sonar search and answer generation through AIsa. Use when the task is specifically to call Perplexity Sonar, Sonar Pro, Sonar Reasoning Pro, or Sonar Deep Research for citation-backed web answers, analytical reasoning, or long-form research reports.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Detects and fixes patterns including: inflated symbolism, promotional language, superficial analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.