GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
recognition-recents-and-suggestions
Use this skill when designing surfaces that accelerate repeat tasks through recents, frequently-used items, and contextual suggestions. Trigger when designing pickers used repeatedly, command palettes, navigation that should adapt to user behavior, or any surface where a returning user shouldn't have to retype their frequent destinations. Sub-aspect of `recognition-over-recall`; read that first.
recognition-pickers-and-palettes
Use this skill when designing pickers, dropdowns, comboboxes, autocompletes, command palettes, or any UI that lets the user select from a known set. Trigger when picking between a free-text field and a select; when designing a command palette; when reviewing why users keep typing wrong values into autocomplete inputs. Sub-aspect of `recognition-over-recall`; read that first.
recognition-over-recall
Use this skill whenever the user must locate or choose something from many possibilities — pickers, command palettes, navigation menus, autocompletes, recents lists, search results, settings panels. Trigger when designing inputs that ask the user to "type the right thing," when picking between dropdowns and search-first interfaces, when reviewing why users keep typing wrong values into autocomplete fields. Recognition Over Recall is one of the foundational principles in 'Universal Principles of Design' (Lidwell, Holden, Butler 2003) and one of Nielsen's 10 heuristics — recognizing options is far easier than recalling them from memory.
progressive-disclosure
Use this skill whenever a design has *more* available than the user needs to see at this moment — settings panels with advanced options, forms with optional fields, dashboards with drill-down detail, navigation with deep IA, dialogs with "More options" affordances, marketing pages with FAQ accordions. Trigger when designing or fixing surfaces that feel "overwhelming," when stakeholders argue about whether to expose every option up front, when novice and expert users have different tolerance for the same surface, or when reviewing a UI cluttered with rarely-used controls. Progressive disclosure is one of the foundational principles in 'Universal Principles of Design' (Lidwell, Holden, Butler 2003), originally formalized through the Xerox Star user-interface work in the 1970s.
progressive-disclosure-disclosure-affordances
Use this skill when picking the *mechanism* for revealing tucked content — accordion vs. modal vs. tab vs. separate page vs. tooltip. Trigger when designing the UI for "More options," picking between an inline accordion and a side sheet, deciding whether a wizard step should be a modal or a separate page, or reviewing whether existing disclosure affordances are doing their job. Sub-aspect of `progressive-disclosure`; read that first.
progressive-disclosure-defaults-and-tucking
Use this skill when deciding *what to surface* and *what to tuck* — the editorial choices behind progressive disclosure. Trigger when laying out a settings page, picking which form fields to show by default, deciding whether a section starts collapsed or open, or arguing about whether a feature deserves primary chrome or belongs in "Advanced." Sub-aspect of `progressive-disclosure`; read that first.
mimicry
Apply the principle of Mimicry — borrowing the form, behavior, or visual language of something familiar to make a new design recognizable. Use when introducing a novel feature whose function would be opaque without an analogy, choosing between metaphor and convention, designing for a category your users already know, or evaluating whether a "skeuomorphic" element helps or hurts. Mimicry comes in surface (visual resemblance), behavioral (acts like the source), and functional (does what the source does) forms. Used well, it accelerates learning; used badly, it carries forward limitations the new medium doesn't share.
mimicry-surface
Apply surface mimicry — making an interface element look like a familiar physical object to communicate its purpose at a glance. Use when introducing a control or container that has no native UI vocabulary, designing a niche product that benefits from a recognizable visual reference (a journal that looks like a journal, a wallet that looks like a wallet), or evaluating whether visual skeuomorphism is communicating or just decorating. Surface mimicry is most useful for novice users in unfamiliar mediums; it becomes anachronistic as the source fades or as users learn the abstract conventions.
mimicry-behavioral
Apply behavioral mimicry — making an interface element behave like a familiar physical object so the user's physical-world intuitions transfer to the digital interaction. Use when designing gestures, animations, transitions, drag-and-drop, scroll behaviors, or any interaction where physical-world analogies could clarify the experience. Behavioral mimicry is more durable than visual skeuomorphism — physics-mimicking behaviors age well — but it requires deliberate calibration: too much physical fidelity slows the interaction down without communicating anything new.
mental-model
Use this skill whenever the design will be used by people who bring prior expectations — which is essentially every design. Trigger when designing onboarding, when picking metaphors (folders, channels, projects), when reviewing why users keep getting confused, when migrating from one product convention to another, or when the user mentions "users don't understand," "they keep doing X wrong," or "we're inventing something new." Mental Model is one of the foundational principles in 'Universal Principles of Design' (Lidwell, Holden, Butler 2003) and grounds most modern user-experience design.
mental-model-system-vs-interaction
Use this skill when distinguishing the two mental-model types — system models (how the user thinks the system works) and interaction models (how the user thinks they should use it). Trigger when designing onboarding (which model to teach), reviewing user confusion (which model is wrong), or building documentation (which model to explain). Sub-aspect of `mental-model`; read that first.
mental-model-mismatch-and-onboarding
Use this skill when designing onboarding, when diagnosing why users keep getting confused, when migrating users from one product convention to another, or when the system genuinely differs from familiar comparable products. Trigger when the user mentions "users don't get it," "we keep getting the same support tickets," or "this is a new pattern they need to learn." Sub-aspect of `mental-model`; read that first.
iconic-resemblance
Apply iconic resemblance — designing or choosing icons that visually look like what they represent. Use when picking icons for actions or objects with strong visual referents (camera, clock, lock, calendar), evaluating whether a custom icon is communicating, or testing whether your icon set actually conveys meaning to your audience. Resemblance is the strongest form of icon recognition because it requires no prior learning; it fails when the function has no visual referent or when the audience doesn't recognize the object being depicted.
iconic-representation
Apply iconic representation — using simplified visual symbols to communicate function, status, or category at a glance. Use when designing icon sets, choosing between icon and text labels, evaluating whether to lean on existing iconography (resemblance to a known object) or invent symbolic icons (arbitrary forms with assigned meanings), or auditing whether your icons are actually communicating. Three kinds: similar (icons that look like what they represent), example (icons that depict an object associated with the function), and arbitrary/symbolic (forms with no inherent meaning, like the hamburger menu).
iconic-arbitrary-and-symbolic
Apply arbitrary and symbolic icon design — using forms with no inherent meaning that depend on convention to communicate (the hamburger menu, the kebab menu, the AI sparkle, app brand-mark icons). Use when a function has no clear visual referent, when working within a domain that has its own icon vocabulary, when establishing or following a convention, or when evaluating whether a convention is strong enough to support icon-only treatment. Arbitrary icons require prior learning to work; the skill is calibrating when to follow a convention vs. when to label.
hicks-law
Use this skill whenever a design has many options the user must choose among — menus, navigation, pickers, plan tiers, settings panels, action toolbars, lists of templates, anything that asks "which one?" Trigger when the user is laying out a navigation menu, designing a settings page, picking the structure of a wizard, building a country/timezone/currency picker, designing a pricing table, or reviewing a UI where users hesitate over which control to use. Trigger when there's debate about "should we add another option?" — Hick's Law is the principle that costs the option a price. Routes to sub-aspect skills for menus, defaults, and pricing.
hicks-law-pricing
Use this skill when designing pricing tables, plan pickers, tier selectors, or any conversion surface where the choice itself is the conversion event. Trigger when laying out 3-tier or 4-tier pricing, when arguing about whether to add a fourth plan, when designing the "Choose your plan" step of onboarding, or when fixing low conversion on a pricing page. Pricing pages are a special Hick's Law case: the decision is the entire purpose of the page, and decision fatigue equals lost revenue. Sub-aspect of `hicks-law`; read that first if you haven't already.
hicks-law-menus
Use this skill when designing menus, dropdowns, navigation, command palettes, or any interface where the user picks from a list. Trigger when the menu has more than ~7 items, when navigation feels overwhelming, when designing a cmd-K palette, when picking what goes in a "More" overflow, or when arguing about whether to add another menu item. Sub-aspect of `hicks-law`; read that first if you haven't already.