技能排行榜
本周新增技能
探索「本周新增技能」中的技能，使用前请查看详情页的来源与审核说明。
展示 30 项 · 候选 480 项
对比前 4 项- 01
khan-explainer
Use when the user wants a Khan Academy style explainer video, a blackboard or whiteboard lesson, a hand-drawn chalk-talk animation, a short narrated video that teaches a concept ("explain X in a video", "explainer video", "teach X in 30 seconds"), or a tutorial that draws hand-written arrows, circles and captions over product screenshots ("draw over the UI", "annotated walkthrough"), or clips cut from a YouTube video or podcast where the speaker's real audio plays under a blackboard drawn to it ("khanify this video", "clip this with the Khan visual"), especially when it must be free, local, and use no paid APIs or keys. macOS only.
@haiderfarooq3视频62使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 36/100
- 质量
- 59/100
- 新鲜度
- 99/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 02
grill
分轮追问用户的计划、决定或想法，直到重要未知暴露出来，再动手执行。适用于任何领域，不限于写代码。当用户想理清思路、给想法做压力测试，或者说出这些话时使用：拷打我、追问我、帮我想清楚、帮我理一理、挑挑毛病、有什么没想到的、grill me、stress-test this、poke holes in this、interview me。
@nagi-studio编程79使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 38/100
- 质量
- 54/100
- 新鲜度
- 99/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 03
architect
技术选型（tech stack）：需求清楚之后，比较两三套方案并推荐一套。用于新项目选框架、数据库、托管和部署方式，或用户问「用什么技术做」「怎么部署」、which stack、how to host。
@nagi-studioDevops79使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 38/100
- 质量
- 54/100
- 新鲜度
- 99/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 04
doc-pipeline
Chain document operations into reusable pipelines
@claude-office-skillsAutomation506使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 54/100
- 质量
- 45/100
- 新鲜度
- 0/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 05
agent-microservices-architect
Specialist subagent: Expert microservices architect for distributed system design, service decomposition, and resilience patterns
@travisjneuman设计100使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 40/100
- 质量
- 55/100
- 新鲜度
- 100/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 06
agent-macos-developer
Specialist subagent: Expert macOS native developer for AppKit, Catalyst, and macOS-specific features
@travisjneuman编程100使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 40/100
- 质量
- 55/100
- 新鲜度
- 100/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 07
agent-kotlin-expert
Specialist subagent: Kotlin Multiplatform, Compose Multiplatform, coroutines, Ktor, and JVM ecosystem specialist. Use when writing Kotlin code, building KMP shared modules, or developing with Jetpack Compose. Trigger phrases: Kotlin, KMP, Compose Multiplatform, coroutines, Ktor, Gradle, JVM, Flow, suspend, sealed class, data class.
@travisjneuman编程100使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 40/100
- 质量
- 61/100
- 新鲜度
- 100/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 08
agent-i18n-specialist
Specialist subagent: Expert internationalization specialist for multi-language support and localization
@travisjneumanOther100使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 40/100
- 质量
- 55/100
- 新鲜度
- 100/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 09
agent-graphql-architect
Specialist subagent: Expert GraphQL architect for API design, schema development, and performance optimization
@travisjneuman设计100使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 40/100
- 质量
- 55/100
- 新鲜度
- 100/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 10
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
@youdotcom-ossCreative87使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 39/100
- 质量
- 59/100
- 新鲜度
- 98/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 11
paywalls
When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," "in-app pricing," "free users won't upgrade," "trial to paid conversion," or "how do I get users to pay." Use this for any in-product moment where you're asking users to upgrade. Distinct from public pricing pages (see cro) — this focuses on in-product upgrade moments where the user has already experienced value. For pricing decisions, see pricing.
@coreyhaines31Automation54,079使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 95/100
- 质量
- 92/100
- 新鲜度
- 100/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 12
marketing-psychology
When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' 'consumer behavior,' 'anchoring,' 'social proof,' 'scarcity,' 'loss aversion,' 'framing,' or 'nudge.' Use this whenever someone wants to understand or leverage how people think and make decisions in a marketing context. For applying psychology to specific pages, see cro; for pricing tactics, see pricing; for copy framing, see copywriting.
@coreyhaines31Business54,079使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 95/100
- 质量
- 92/100
- 新鲜度
- 100/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 13
sitrep
Use when the user brings several updates at once — "quick catch-up", a list of things that happened, news touching the plan, people, time and money together. Sorts each update to the skill that writes it, shows the routing for a yes, then works through each one in the next turn. Writes only the log itself.
@skyf0xxOther26使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 29/100
- 质量
- 56/100
- 新鲜度
- 96/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 14
recon
Use when the plan hangs on something the user does not know yet — a date, a rule, a person's position, a price, whether a door is open. Turns each unknown into a question with a reason, a way to find out and a date to know by, and records the answer when it comes in. Writes to the goal's intel key.
@skyf0xxOther26使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 29/100
- 质量
- 56/100
- 新鲜度
- 96/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 15
options
Use when there is more than one real way to reach the goal and the user has not picked one — before committing to a plan, or when the current approach has stalled. Builds up to three distinct courses of action, each with why it could win, what could sink it and how others would react, then compares them so one can be chosen. Writes to the goal's courses key.
@skyf0xxOther26使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 29/100
- 质量
- 56/100
- 新鲜度
- 96/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 16
intake
Use for new-goal intake — the active goal is still a stub (its only success criterion is the placeholder "define success criteria") or the user wants to re-open the definition of what they are after. Runs a guided conversation that pins down the goal statement, pressure-tests what "done" means by working backwards, drafts success criteria marked control or influence, sets a deadline, and names the first people involved. Offers a quick take or a deep dive.
@skyf0xxOther26使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 29/100
- 质量
- 56/100
- 新鲜度
- 96/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 17
elicit
Use at a natural pause, or when the user asks for a deeper critique or names a method (socratic, first principles, pre-mortem, red team), to pressure-test the most recent piece of work — a draft, plan, decision or set of criteria — by running a chosen elicitation method against it. Offers a short menu of methods drawn from a catalog, runs the chosen ones, and hands back an improved version.
@skyf0xx编程26使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 29/100
- 质量
- 56/100
- 新鲜度
- 96/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 18
matplotlib-data-visualization
Chart design and data storytelling guidelines for matplotlib. Use when creating visualizations that need to communicate a clear message, tell a story with data, or follow best practices for readability and design. Focuses on visualization principles rather than matplotlib API syntax.
@pavelzw设计25使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 28/100
- 质量
- 55/100
- 新鲜度
- 88/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 19
target-audience
Define a brand's target audience with deep personas, psychographics, and ICP (Ideal Customer Profile). Use when the user says "target audience", "ideal customer", "customer persona", "audience persona", "ICP", "who is our customer", "define our audience", "audience research", "buyer persona", "who should we be targeting", "audience profile", "customer profile", "who buys this", or needs to understand their audience more deeply before investing in brand or marketing work.
@skyf0xxMarketing26使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 29/100
- 质量
- 56/100
- 新鲜度
- 96/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 20
rebranding
Plan and execute a brand transformation — from diagnosis to new brand definition to rollout. Use when the user says "rebrand", "rebranding", "brand refresh", "update the brand", "modernize the brand", "our brand is outdated", "we've outgrown our brand", "the brand needs to change", "brand transformation", "pivot the brand", "we're changing the brand", "the old brand doesn't fit anymore", or when a brand has evolved in direction, audience, or market position and needs its identity to catch up.
@skyf0xxOther26使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 29/100
- 质量
- 56/100
- 新鲜度
- 96/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 21
brand-voice
Define a brand's verbal identity — tone, voice, writing style, vocabulary, and messaging rules. Use when the user says "brand voice", "tone of voice", "how should we write", "writing guidelines", "copy style guide", "brand language", "verbal identity", "how should the brand sound", "tone guide", "our copy doesn't sound right", "copywriter guidelines", "voice and tone", or when onboarding a copywriter or content team. Also use when the user has a brand strategy and wants to define how the brand communicates.
@skyf0xxOther26使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 29/100
- 质量
- 56/100
- 新鲜度
- 96/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 22
brand-strategy
Full brand strategy workflow for agencies and brand consultants. Acts as a senior brand strategist — collects client information through a structured questionnaire, then generates a complete, polished brand strategy report. Use this skill whenever a user says "brand strategy", "create a brand report", "build brand strategy for my client", "brand questionnaire", "I have a new branding client", "help me do brand strategy", "brand identity strategy", "write a brand strategy document", or shares a client brief and wants a strategy output. Also triggers when a user uploads or pastes a completed brand questionnaire and asks to turn it into a report. Always use this skill for any brand strategy task — even casual mentions like "I need to do strategy for this brand" or "client filled the form, make the report".
@skyf0xxOther26使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 29/100
- 质量
- 56/100
- 新鲜度
- 96/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 23
brand-story
Craft a brand's origin story, founder narrative, and "why we exist" statement. Use when the user says "brand story", "origin story", "founder story", "why we exist", "about us", "our story", "company narrative", "brand narrative", "write our about page", "tell our story", "founding story", "brand history", or wants to articulate the deeper purpose and human story behind the brand. Also use when the About Us page feels generic or corporate and needs a rewrite.
@skyf0xxOther26使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 29/100
- 质量
- 56/100
- 新鲜度
- 96/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 24
writing
文章を書く時の心得。ソースコードのコメント、PR概要欄、ドキュメント、wikiのどこに書く時も変わらない、解釈のブレを起こさない文の書き方と、強調記号とカッコ書きの扱いを定める。 ソースコードのコメント、PR概要欄、ドキュメント、wikiの文章を書く時、直す時、レビューする時に読み込む。
@shokaiOther30使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 30/100
- 质量
- 50/100
- 新鲜度
- 97/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 25
software-test
ソフトウェアテストを書く時の心得。何をtestし、何をtestしないかの判断基準と、アクセス権限のtestの書き方、落ちたtestの直し方、fixtureの仮名を定める。 testを書く時、足すか決める時、落ちたtestを直す時、レビューする時に読み込む。
@shokai编程30使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 30/100
- 质量
- 50/100
- 新鲜度
- 97/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 26
understanding-ladder
Pick the output format that makes an explanation easiest to understand, following Karpathy's understanding ladder — (1) plain controlled text, (2) diagram, (3) interactive HTML page, (4) 3Blue1Brown-style explainer video. Classify the content (definition/steps, process/causality, parameter→outcome, unfolding derivation), recommend the lowest rung that fully answers, then produce it. Works in English and Chinese. Use when the user says "explain this clearly", "help me understand", "draw a diagram", "make it interactive", "make an explainer video", "what's the best way to explain X", "understanding ladder", "Karpathy ladder", or 「讲清楚」「帮我理解」「画个图」「做个交互页」「做个讲解视频」「用哪种方式讲最好懂」「理解阶梯」; also when explaining a non-trivial concept, mechanism, algorithm, or an AI agent's output.
@ChangWenC视频21使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 27/100
- 质量
- 55/100
- 新鲜度
- 90/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 27查看详情
收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 54/100
- 质量
- 45/100
- 新鲜度
- 0/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 28
discord-bot
Discord bot development - community management, moderation, notifications, and AI integration
@claude-office-skills编程503使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 54/100
- 质量
- 45/100
- 新鲜度
- 0/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 29
kb
Portable OKF knowledge bundle for coding-agent memory and LLM wikis. Use when the user wants to start a wiki, ingest a source, document a repository, query project knowledge with citations, lint for drift, or visualize connections; whenever a repo has a knowledge/ bundle that should inform the task; and when another kb-* skill needs the shared spec, glossary, templates, or trust model.
@stjbrownAi Knowledge41使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 33/100
- 质量
- 56/100
- 新鲜度
- 0/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
- 30
plain-chinese
用简明中文写解释、步骤和总结：一句一事、一词一义、主动句、不铺垫，内容一点不删。写中文的技术解释、操作步骤、学习笔记、报告，或者解释 AI/agent 的产出时使用。用户说「说人话」「写清楚点」「太绕了」「看不懂」「简明中文」「用 STE 的写法」「改得好懂一点」时也使用。受 ASD-STE100 启发，不是它的中文版。
@ChangWenCOther21使用前请审核查看详情收录日期
排名依据
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
- 人气
- 27/100
- 质量
- 49/100
- 新鲜度
- 90/100
- Agent 结果证据
- 0/100
- 证据置信度
- 0/100
- 安装准备度
- 90/100
基于最多 480 个目录候选生成，并非全站排名。Star 属于仓库；评分不代表安全保证或运行验证。
榜单如何排序
仅展示最近 7 天收录的技能，按收录时间从新到旧排列。这是本站收录日期，不是仓库创建日期。
各项信号采用 0–100 分，仅辅助判断；排序遵循本榜单规则，不由单项分数决定。
近 30 天快照数据