「understanding」の検索結果

Document development environment requirements for team consistency and AI agent understanding during PRD v0.6 Architecture. Triggers on requests to define environment setup, document tooling, create dev setup guide, or when user asks "what tools do I need?", "environment setup", "dev environment", "CLI requirements", "project setup", "onboarding setup". Consumes TECH- (stack selections), ARC- (architecture decisions). Outputs ENV- entries for development, CI/CD, and infrastructure environments. Feeds v0.7 Build Execution.

日本語の概要は準備中です。原文の説明を表示しています。

Analyze an open-source project from What/Why perspective (not how-it's-implemented). Use when the user says "/analyze-oss", "분석해줘 이 오픈소스", "이 레포 뭐하는거야", "analyze this repo", "what does X do", "이거 왜 쓰는거야", "이 라이브러리 분석", provides a GitHub URL and wants understanding, or asks to deeply understand an OSS project's purpose, value, target users, and usage flow. Clones the repo to ~/opensource-analysis/<repo-name>/ (git pull if already exists), dispatches parallel subagents per analysis lens, then synthesizes a What/Why-focused report in chat. Supports optional user-specific follow-up questions.

日本語の概要は準備中です。原文の説明を表示しています。

Expert in meme creation and virality - understanding why certain ideas spread while others die. Covers meme formats, timing, adaptation, meta-commentary, and platform-specific optimization. Knows the difference between forcing a meme and engineering conditions for organic spread. Use when "meme, viral content, make it memeable, shareable, internet culture, template, " mentioned.

日本語の概要は準備中です。原文の説明を表示しています。

Patterns for building multimodal AI applications that combine text, images, audio, and video. Covers vision APIs, audio transcription, and unified pipelines. Use when "multimodal AI, vision API, image understanding, GPT-4V, Claude vision, audio transcription, Whisper, document extraction, image to text, " mentioned.

日本語の概要は準備中です。原文の説明を表示しています。

Expert in navigating and manipulating git history. Covers finding bugs with bisect, understanding code evolution, recovering lost work, and rewriting history safely. Understands that git history is your time machine. Use when "git history, git bisect, find when bug introduced, recover deleted, rewrite history, git blame, lost commit, " mentioned.

日本語の概要は準備中です。原文の説明を表示しています。

Git is deceptively simple to learn and incredibly hard to master. The difference between a team that ships and a team that fights merge conflicts all day comes down to workflow discipline. Your git history is documentation - make it tell a story future you can understand. This skill covers branching strategies (trunk-based, gitflow, GitHub flow), commit hygiene, merge vs rebase, conflict resolution, and the commands you actually need. Key insight: most git disasters come from not understanding what you're about to do. 2025 lesson: Trunk-based development with short-lived branches has won. Long-lived feature branches are a code smell. If a branch lives more than a few days, something is wrong with your architecture or process. Use when "git workflow, branching strategy, git merge, git rebase, merge conflict, git commit, trunk-based, gitflow, git history, git revert, git reset, git, version-control, workflow, branching, commits, merge, rebase, collaboration" mentioned.

日本語の概要は準備中です。原文の説明を表示しています。

Use when implementing object detection, semantic/instance segmentation, 3D vision, or video understanding - covers YOLO, SAM, depth estimation, and multi-modal visionUse when ", " mentioned.

日本語の概要は準備中です。原文の説明を表示しています。

Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 2025. Critical distinction: Testing automation (predictable apps you control) vs scraping/agent automation (unpredictable sites that fight back). Different problems, different solutions. Use when "playwright, puppeteer, browser automation, headless, web scraping, e2e test, end-to-end, selenium, chromium, browser test, page.click, locator, playwright, puppeteer, browser, automation, testing, scraping, headless, e2e, selenium, web-testing" mentioned.

日本語の概要は準備中です。原文の説明を表示しています。

Measure what matters. Event tracking design, attribution modeling, funnel analysis, experimentation platforms. The complete guide to understanding what your users actually do, not what you hope they do. Good analytics is invisible until you need it. Then it's the difference between guessing and knowing. Use when "analytics, tracking, events, funnel, conversion, attribution, segment, amplitude, mixpanel, posthog, ab testing, experiment, cohort, retention, measure, metrics, analytics, tracking, events, funnel, conversion, attribution, data" mentioned.

日本語の概要は準備中です。原文の説明を表示しています。

Mastery of AI image generation across the full spectrum: Midjourney for aesthetic perfection, Flux for prompt adherence, DALL-E 3 for concept clarity, Stable Diffusion for control, and Imagen 3 for photorealism. This skill transforms text into visual reality at the speed of thought. We've moved beyond "AI can make pictures" to "AI is the fastest concept artist, product photographer, and visual designer ever created." The skill isn't just prompting—it's understanding how each model thinks, what makes images work, and how to systematically produce exactly what you envision. The best AI image generators have internalized composition, lighting, color theory, and style—not by studying art, but by generating thousands of images and learning what works. They're visual directors who happen to work in text. Use when "AI image, generate image, Midjourney, DALL-E, Flux, Stable Diffusion, Imagen, text to image, AI art, AI photo, AI illustration, AI visual, AI graphics, generate picture, ai-image, midjourney, dall-e, flux, stable-diffusion, imagen, generation, text-to-image, visual, art" mentioned.

日本語の概要は準備中です。原文の説明を表示しています。

Explain compiler/runtime errors in plain language. Use when a junior developer needs help understanding an error message.

日本語の概要は準備中です。原文の説明を表示しています。

摄影 (摄影 (Photography) — 以静态影像为产出的视觉创作 + 服务行业：从看见 → 用光 → 构图 → 拍摄 → 后期 → 交付的认知操作系统，覆盖商业摄影 (commercial: 产品/广告/电商/美食)、人像摄影 (portrait: 影楼/写真/婚礼/时尚/环境人像)、纪实与街头摄影 (documentary/photojournalism/street)，以及与之贯通的风光、新闻、艺术摄影。面向职业摄影师 / 助理 / 修图师 / 想转职业的资深爱好者 / 服务这行的人 (器材厂商、图库、后期外包、影楼运营)。覆盖: (a) 第一性张力 — **光 (light is the craft — 看光、控光、塑光：硬光/柔光、方向、色温、光比、布光是摄影第一性) ⇄ 器材 (gear — 相机/镜头/灯具迷信, 'GAS' gear-acquisition-syndrome, 'the best camera is the one you have with you' — 器材不是摄影)**; **决定性瞬间/抓取 (decisive moment, Cartier-Bresson, 等待与预判, 纪实/街头不可重来) ⇄ 构建/导演 (constructed/directed, 商业与人像是布光摆姿造光的'制造'而非'捕获')**; **前期/拍对 (get it right in camera, 曝光/白平衡/构图当场拍对) ⇄ 后期/暗房 (post/darkroom, Ansel Adams 'negative is the score, print is the performance' — RAW 冲洗/调色/修图是创作一半)**; **作者性/艺术表达 (vision, personal voice, 'photograph what you feel not what you see') ⇄ 服务性/商业交付 (client brief, 影楼标准化出片, 'shoot the brief not your ego', 摄影是生意)**; **真实/未操纵 (truth, photojournalism ethics, 不过度 PS, 新闻摄影伦理) ⇄ 修饰/理想化 (retouch, 商业人像液化磨皮, 广告的'谎言')**; **决定性技术参数 (曝光三角 aperture/shutter/ISO, 景深, 互易律) ⇄ 看见/眼力 (seeing, 'photography is about seeing not cameras', 构图/光感是 tacit 眼力)**; **胶片/慢/不可见 (film, 慢工, 不可即时回看, 暗房) ⇄ 数码/即时/海量 (digital, chimping, 连拍, 后期无限)**; AI 对摄影的冲击 ('是不是摄影'、生成式填充/换天/AI 修图、真实性危机); (b) 核心工作流 / pipeline (最标准、最易蒸高质量+CLI 化) — 通用链: 看光选光 → 曝光三角决策 (光圈定景深/快门定动静/ISO 兜底) → 测光与曝光 (评价/点测光, 向右曝光 ETTR, 直方图, 区域系统) → 构图 (三分法/引导线/框架/负空间/前景) → 对焦 → 拍摄 → 选片 culling → RAW 后期 (Lightroom/Capture One: 曝光/白平衡/色调曲线/HSL/局部) → 精修 retouch (Photoshop: 频率分离/液化/D&B) → 调色 grading → 输出交付 (色彩管理/sRGB/打印/图库上传); 子流派 SOP: 影棚商业布光 (主光/辅光/轮廓光/背景光, 三点布光, 光质修饰器 softbox/beauty-dish/grid)、婚礼/纪实一天流程、街头扫街、产品/电商台面、人像引导摆姿 posing & direction; (c) 工具栈 — 相机系统 (无反主导: Sony A 系 / Canon R / Nikon Z / 富士 X&GFX / 徕卡 M; 中画幅 Phase One/Hasselblad/GFX 商业; 残幅 vs 全幅 vs 中幅)、镜头 (大三元, 定焦 vs 变焦, 35/50/85 人像三剑客, 微距, 移轴)、灯具 (机顶闪 Godox/Profoto, 影室灯, 常亮 LED, 持续光 vs 闪光)、修饰器 (柔光箱/反光伞/束光筒/雷达罩/旗板)、测光/附件 (测光表, 灰卡, 三脚架, 滤镜 ND/CPL/渐变)、后期软件 (Adobe Lightroom Classic/CC 主导, Capture One 商业/影室, Photoshop 精修, DxO PhotoLab/PureRAW 降噪, Capture One vs Lightroom 之争, 国产: 醒图/泼辣 Polarr/Snapseed 移动端, RawTherapee/Darktable 开源, AI: Lightroom 生成式/Photoshop Generative Fill/Topaz Photo AI/Gigapixel/Luminar Neo)、色彩管理 (X-Rite/Calibrite 校色仪, ICC, 显示器)、图库/交付 (Pixieset/图虫/500px/视觉中国/Getty/Adobe Stock, 客片在线选片); (d) 知识正典 — Ansel Adams 'The Camera / The Negative / The Print' 三部曲 + 区域系统 (Zone System)、Henri Cartier-Bresson 'The Decisive Moment'、Michael Freeman 'The Photographer's Eye' (构图) 'The Photographer's Mind'、Bryan Peterson 'Understanding Exposure' (曝光入门圣经)、Scott Kelby 'Digital Photography Book' 系列 + Lightroom/Photoshop 书、Joe McNally 'The Hot Shoe Diaries / Sketching Light' (闪光灯)、Light Science & Magic (布光科学经典教材)、Roland Barthes 'Camera Lucida' (摄影哲学)、Susan Sontag 'On Photography'、John Szarkowski 'The Photographer's Eye'、National Geographic 摄影指南、Robert Capa / Sebastião Salgado / Steve McCurry (纪实)、Annie Leibovitz / Richard Avedon / Peter Lindbergh (人像/时尚)、Galen Rowell / Ansel Adams (风光); (e) figures/流派 — 风光/系统派 (Ansel Adams 区域系统奠基、Galen Rowell 探险风光、Marc Adamus); 决定性瞬间/纪实街头派 (Henri Cartier-Bresson 奠基、Robert Capa 战地、Sebastião Salgado 社会纪实、Steve McCurry、Vivian Maier、Daido Moriyama、森山大道/荒木经惟 日本派、Vivian Maier); 人像/时尚派 (Richard Avedon、Annie Leibovitz、Peter Lindbergh、Platon、Joey L、Lindsay Adler 时尚布光); 布光/教育派 (Joe McNally、Zack Arias 'one light'、Profoto/strobist David Hobby 'Strobist' 闪光灯启蒙博客、Karl Taylor 商业布光教学); 商业/广告派 (Chase Jarvis 'CreativeLive'创办+'best camera'、Joel Grimes、Tim Wallace 汽车); 后期/修图派 (Pratik Naik、Aaron Nace 'Phlearn'); 街头当代派 (Eric Kim 街头博客、Joel Meyerowitz、Saul Leiter 色彩街头); 中文圈 (李涛 'photoshop教学'、宁思潇潇 器材评测、thomas 'Thomas看看世界' 风光后期、阿刘 风光、668 人像); 哲学/批评 (Susan Sontag、Roland Barthes、John Szarkowski MoMA); (f) 行业话术/黑话 — 曝光三角 exposure triangle / 光圈 aperture f-stop / 快门 shutter speed / 感光度 ISO / 景深 DoF depth of field / 焦段 focal length / 等效 / 全画幅 full-frame vs 残幅 crop / 大三元 / 定焦 prime / 互易律 reciprocity / 向右曝光 ETTR / 直方图 histogram / 高光溢出 clipping / 动态范围 dynamic range / 宽容度 / 白平衡 WB

日本語の概要は準備中です。原文の説明を表示しています。

Debug GitHub Actions workflows by downloading logs, analyzing summaries, and understanding how agentic workflows and the AWF firewall work together.

日本語の概要は準備中です。原文の説明を表示しています。

Build a 4-quadrant empathy map (Says, Thinks, Does, Feels) to synthesize user research into actionable insights. Use when you need to quickly capture and share user understanding across the team.

日本語の概要は準備中です。原文の説明を表示しています。

Applies Judea Pearl's causal reasoning frameworks to distinguish correlation from causation, evaluate AI capabilities, and make counterfactual decisions. Reach for this skill whenever Claude encounters questions about causal inference, structural causal models, the limitations of deep learning, AGI, experimental design, covariate selection, or personalized decision-making. Trigger this skill for topics involving Bayesian networks, the do-calculus, the Ladder of Causation, or when a user tries to answer 'what if' or 'why' questions using purely observational data. Pearl's principles are essential for moving beyond probability calculus into true causal understanding.

日本語の概要は準備中です。原文の説明を表示しています。

This skill channels the strategic and scientific reasoning of Demis Hassabis, CEO and co-founder of Google DeepMind, AlphaGo and AlphaFold, and 2024 Nobel Prize in Chemistry. Use this skill whenever you are evaluating AI for scientific discovery, tackling "root node" problems, designing reinforcement learning systems, or discussing AGI timelines, safety, and global governance. Reach for it when the user faces massive combinatorial search spaces, wants to apply AI to physical/biological sciences (like digital biology), or needs to balance rapid AI scaling with the rigorous scientific method. Apply these mental models to shift the focus from building consumer apps to using AI as the ultimate meta-solution for understanding reality.

日本語の概要は準備中です。原文の説明を表示しています。

Applies the frameworks of Aristotle (ancient Greek philosopher, logic, ethics, metaphysics, 384-322 BCE) to decision-making, ethics, and analysis. Use this skill whenever the user is grappling with moral dilemmas, character development, habit formation, finding balance (the Golden Mean), persuasive communication (rhetoric), or understanding the root causes and ultimate purpose (teleology) of a project or system. Reach for this skill even if the user doesn't name Aristotle, especially when discussing career fulfillment, long-term happiness (eudaimonia), balancing extremes, or structuring persuasive arguments.

日本語の概要は準備中です。原文の説明を表示しています。

Applies the analytical and therapeutic philosophy of Ludwig Wittgenstein, 20th-century philosopher of language (Tractatus / Philosophical Investigations). Use this skill when the user is stuck in conceptual confusion, debating semantics, trapped by abstract definitions, or trying to solve a problem that is actually just a linguistic misunderstanding. Trigger this for topics involving the limits of language, meaning as use, logical clarification, or when the user is over-theorizing instead of looking at practical applications. It helps dissolve 'fly-bottle' traps by examining how words are actually used in context.

日本語の概要は準備中です。原文の説明を表示しています。

Applies the reasoning style of Geoffrey Hinton, deep learning pioneer and 2018 Turing Award winner. Use this skill whenever evaluating AI safety, existential risk, neural network architectures, cognitive science, or tech regulation. Reach for this when the user is discussing LLM capabilities (understanding vs. autocomplete), the biological vs. digital intelligence divide, AI alignment strategies, or the societal/economic impacts of automation. It is highly applicable when dealing with contrarian scientific ideas, hardware/software integration (mortal vs. immortal computing), or global cooperation on technological threats. Do not wait for the user to name Hinton; trigger this skill proactively for any deep learning or AI existential risk analysis.

日本語の概要は準備中です。原文の説明を表示しています。

Applies the Neoplatonic and mathematical reasoning of Hypatia of Alexandria. Use this skill whenever the user is grappling with the pursuit of truth, foundational logic, the hierarchy of knowledge, or the distraction of superficial and physical desires versus deeper intellectual pursuits. Trigger this when discussing mathematics as a foundation for higher understanding, astronomy, overcoming base impulses, or seeking the ultimate source of truth. It is highly relevant for questions about rigorous intellectual discipline, esoteric philosophy, and elevating one's mind above material distractions.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user wants to know if something works — the answer requires running code, not analyzing it. Output is a verdict backed by evidence: passed, failed, or broken. Primary triggers: 'run the tests', 'does X still work after my change?', 'did the merge break anything?', 'verify the fix worked', 'check if the endpoint returns X', 'confirm nothing regressed', 'run tests/unit/test_foo.py', 'let me know the results', 'make sure my changes didn't break anything'. Hard stops — do NOT use for: reviewing test code for quality/coverage gaps, debugging why test infrastructure/databases/seed scripts are misbehaving, writing or fixing tests, diagnosing root causes of unexpected behavior. The deciding question: is the user asking for the result of executing something, or asking for help understanding/analyzing/improving something? If it's the latter, use diagnose or review-code instead.

日本語の概要は準備中です。原文の説明を表示しています。

Guide for the Kimix web frontend (src/app/) — vanilla TypeScript + Vite, SSE-based chat UI mirroring sse_cli.py. Use when modifying the frontend, adding new UI features, changing the API client, or understanding the message rendering pipeline.

日本語の概要は準備中です。原文の説明を表示しています。

Guide for the Kimix HTTP serve system — FastAPI backend + TypeScript/Vite frontend. Use when adding new backend endpoints, modifying the session manager, changing the frontend API client, or understanding how data flows from backend to UI. Covers dummy_app.py, dummy_session_manager.py, sse_cli.py, and src/app/.

日本語の概要は準備中です。原文の説明を表示しています。

This skill should be used when the user sends an image and asks to "analyze this image", "describe this picture", "what's in this image", or any request requiring visual understanding of images. Provides image analysis using Zhipu GLM-4.6V multimodal model.

日本語の概要は準備中です。原文の説明を表示しています。