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
alignment
Use this skill whenever the design has more than one element on the page — every layout, every form, every table, every page header, every card. Trigger when designing a layout, picking a grid, fixing a UI that "looks off," debating left vs. center alignment for body text, or auditing why a design feels disorderly. Alignment is one of the most foundational principles in 'Universal Principles of Design' (Lidwell, Holden, Butler 2003) — every visible element's edge or center should fall on a shared axis with at least one other element. Misalignment by even a few pixels reads as disorder.
alignment-text-and-numerics
Use this skill when designing text-alignment and numeric-alignment decisions — choosing between left, right, center, and justified text; right-aligning numeric columns in tables; aligning labels relative to inputs; handling decimal alignment for currency. Trigger when laying out body content, designing tables with mixed types, or fixing alignment issues in dense data displays. Sub-aspect of `alignment`; read that first.
alignment-grid-systems
Use this skill when designing or evaluating a grid system — picking column counts, gutter widths, breakpoints, baseline grids, or modular grids. Trigger when designing a new layout system, when an existing layout feels disorderly, when picking responsive breakpoints, or when reviewing a design that "doesn't sit on a grid." Sub-aspect of `alignment`; read that first.
mapping
Apply the principle of Mapping — designing the relationship between controls and their effects so the connection between input and output is immediately obvious. Use when designing controls (knobs, switches, buttons, sliders, gestures), arranging them in space relative to what they affect, or diagnosing user confusion about which control does what. Strong mappings exploit physical analogies (up = more), spatial correspondence (the left burner control is on the left), and cultural conventions (red = stop). Poor mappings force the user to memorize arbitrary pairings, generating slips and errors that compound over time.
mapping-natural
Apply natural mapping — the strongest form of mapping, in which the spatial position, motion, or shape of a control directly corresponds to what it affects. Use when designing physical control panels, in-screen controls that affect specific regions of a UI, chart legends, multi-target remote controls, vehicle dashboards, or any situation where the user must connect "this control" to "that affected thing." A natural mapping is one a first-time user can predict without instruction. When the form factor allows it, natural mapping is essentially free correctness.
mapping-cultural
Apply cultural mapping — using shared conventions (icons, colors, gestures, metaphors) to convey what a control does when natural spatial mapping isn't available. Use when designing icon-based UIs, choosing colors for status indicators, picking gestures for touch interfaces, or selecting metaphors to make abstract operations concrete (the trash can, the gear, the magnifying glass). Cultural mappings are weaker than spatial ones — they require prior learning — but they're the workhorse of icon-driven interfaces. The risk is assuming a convention is universal when it's actually domain-specific.
interaction-router
Use this skill whenever a design task involves what users *can do* and what happens when they do it — affordances, feedback, errors, undo, confirmation, target sizing, keyboard handling, modal vs. non-modal decisions, destructive actions, validation. Trigger when the user mentions buttons, forms, validation, error states, loading states, drag-and-drop, undo, confirmation dialogs, keyboard shortcuts, target sizes, "users keep deleting things," misclicks, or "should this be a popover or a dialog." Framework-agnostic. Routes the model to the right interaction principle in this plugin.
forgiveness
Use this skill whenever a design lets users do something they might regret — delete, send, publish, charge, transfer, archive, overwrite, irrecoverably commit. Trigger when designing destructive actions, undo systems, confirmation dialogs, soft-delete recovery, draft-saving, transaction reversal, "are you sure?" patterns, or any flow where a wrong move costs the user time, data, money, or trust. Trigger when the user mentions "users keep deleting things," "we get support tickets about lost data," "is this dangerous?", or when reviewing destructive UI. Forgiveness is one of the central principles in 'Universal Principles of Design' (Lidwell, Holden, Butler 2003) and one of Nielsen's 10 heuristics ("user control and freedom").
forgiveness-undo-and-soft-delete
Use this skill when designing reversibility — undo systems, soft delete, archive-with-recovery, version history, "Undo Send" patterns, and any mechanism that lets a user step back from an action they regret. Trigger when designing destructive actions you want to be safe rather than friction-heavy, when picking between confirmation dialogs and undo toasts, when defining recovery windows, or when planning version-history features. Sub-aspect of `forgiveness`; read that first.
forgiveness-confirmation-and-prevention
Use this skill when the user must commit to an irreversible or high-stakes action and reversibility isn't enough — confirmation dialogs, type-to-confirm patterns, password re-entry, two-step authentication for destructive actions, and structural prevention that makes the wrong action impossible. Trigger when designing destructive flows for genuinely-irreversible commitments, when reviewing confirmation fatigue, or when picking between a single confirm dialog and a multi-step verification. Sub-aspect of `forgiveness`; read that first.
fitts-law
Use this skill whenever the question involves how easy it is to *hit* an interactive target — buttons, links, form controls, drag handles, scrollbars, mobile tap targets, anything the user must move a pointer or finger to. Trigger when sizing buttons, designing toolbars, picking a hit-area for icon buttons, designing for touch screens, debugging "users keep mis-clicking," or arguing about button density vs. usability. Trigger when the user mentions touch targets, target size, "fat fingers," pointer accuracy, edge gestures, or accessibility around motor impairments. Routes to sub-aspect skills for touch targets, screen edges, and pointer acceleration.
fitts-law-touch-targets
Use this skill when designing for touch — phones, tablets, kiosks, in-car displays, smart-TV remotes, anything where the input is a finger or thumb rather than a precise pointer. Trigger when sizing buttons for mobile, debugging "users keep mistapping," designing a mobile bottom-nav, picking icon sizes for a phone toolbar, or reviewing whether a desktop UI is touch-friendly. Sub-aspect of `fitts-law`; read that first if you haven't already.
fitts-law-screen-edges
Use this skill when designing for the edges and corners of the screen — where the cursor cannot overshoot, making them effectively infinite-sized targets along one axis. Trigger when designing global navigation, system menus, sticky headers, fixed sidebars, full-bleed CTAs, or anywhere you can put the most-frequent or hardest-to-find actions. Trigger when reviewing an app that has wasteful margins on every side and asks the user to aim for tiny targets in the middle. Sub-aspect of `fitts-law`; read that first if you haven't already.
fitts-law-pointer-acceleration
Use this skill when the question involves cursor speed, pointer acceleration curves, or interaction with input devices that vary in precision (mouse, trackpad, stylus, touchscreen, eye-tracking). Trigger when designing for varied input devices, building drag interactions, designing scrubbers / sliders / handles, or analyzing why a UI feels "fiddly." Sub-aspect of `fitts-law`; read that first if you haven't already.
feedback-loop
Use this skill whenever a user takes an action and the system must communicate that the action was received, is in progress, succeeded, or failed. Trigger when designing button states, form submission, file uploads, payment flows, real-time UI updates, loading states, error states, success confirmations, or any moment when the user is waiting for the system to do something. Trigger when the user mentions "feels broken," "doesn't seem to work," "users keep clicking again," or any symptom of feedback gaps. Feedback Loop is one of the foundational principles in 'Universal Principles of Design' (Lidwell, Holden, Butler 2003) — and one of the principles whose absence most reliably damages a product's perceived quality.
feedback-loop-states-and-latency
Use this skill when designing the visible states an interactive element passes through (idle / pending / success / error) and matching feedback timing to the user's perceptual thresholds. Trigger when designing button states, form-submit flows, file-upload progress, loading screens, or any interaction whose response time is variable. Sub-aspect of `feedback-loop`; read that first.
feedback-loop-positive-vs-negative
Use this skill when designing system architecture or product mechanics that involve feedback loops at a higher level than UI state — recommendation engines, gamification, growth mechanics, engagement systems, or any system where one user action affects subsequent actions in compounding or stabilizing ways. Trigger when designing growth loops, retention features, or system dynamics; when reviewing a feature for unintended consequences; when discussing engagement vs. wellbeing tradeoffs. Sub-aspect of `feedback-loop`; read that first.
expectation-effect
Apply the Expectation Effect — the principle that prior expectations measurably change a person's perception of a product or experience. Use when shaping the framing of new features, designing onboarding, choosing visual cues that signal premium vs. budget, or diagnosing why two functionally identical features feel different to users. Expectations are set by visual cues (premium materials, polished typography), language (precise, confident copy), social proof, price, and prior brand exposure. Setting expectations too high creates disappointment; too low and the product reads as mediocre. The skill is calibrating what to promise.