技能雷达 · GITHUB

值得安装的 Agent Skills。

汇总公开仓库中已验证的 Skills。安装前先看清它能做什么、包内包含什么、热度如何，以及来源是否可靠。

目录范围: 已验证
Skills: 5,771
仓库: 824
最近同步: 2026年9月8日

5,771 Skills

gpt-image-2

面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用：(A) Garden 本地模式，通过 OpenAI 兼容接口直接出图并落盘；(B) Host-Native 模式，把本 Skill 当作提示词工程指引，把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图；(C) Advisor 模式，宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板，覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。

安装量: 1
GitHub Stars: 1.2万
最近更新: 7月12日

查看详情 →

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

安装量: 1
GitHub Stars: 3419
最近更新: 9月4日

Complete terms in LICENSE.txt2 文件

查看详情 →

web-design-guidelines

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

安装量: 1
GitHub Stars: 5852
最近更新: 6月23日

查看详情 →

uniwind

Uniwind — Tailwind CSS v4 styling for React Native. Use when adding, building, or debugging components in a React Native project that uses Uniwind classNames. Covers setup, Metro config, global.css, theming, className props, accent- color props, platform/data/state/responsive variants, CSS variables, custom utilities, withUniwind for third-party components, cn/tailwind-merge, tailwind-variants, safe area utilities, ScopedVariables, LayoutDirection, gradients, fonts, React Navigation, UI kits, diagnostics, troubleshooting, and Uniwind Pro features. Does not cover NativeWind migration.

安装量: 1
GitHub Stars: 1698
最近更新: 9月4日

查看详情 →

platform-docs-get

Official Salesforce documentation retrieval skill. Use when you need authoritative Salesforce docs from developer.salesforce.com, help.salesforce.com, architect.salesforce.com, admin.salesforce.com, or lightningdesignsystem.com, especially when pages are JS-heavy, shell-rendered, or hard to extract with naive fetching. Use to ground answers in official Salesforce sources instead of third-party blogs or summaries. TRIGGER when: user asks for official Salesforce documentation, Apex or API reference, LWC docs, Agentforce docs, setup or help articles, or any doc from a Salesforce-owned domain. DO NOT TRIGGER when: user is asking for a code change, deployment task, or anything not requiring documentation retrieval — use the appropriate sf- skill instead.

安装量: 1
GitHub Stars: 966
最近更新: 9月5日

Apache-2.06 文件

查看详情 →

platform-metadata-retrieve

ALWAYS USE THIS SKILL to retrieve metadata from an org to your local project using the sf project retrieve start command. Supports multiple retrieval modes: retrieve all remote changes, retrieve by source directory, retrieve by metadata type with wildcards, retrieve by manifest (package.xml), or retrieve by package name. Use when the user asks to retrieve, pull, sync, or download metadata, Apex classes, custom objects, or org changes. Supports source format (default) or metadata format (ZIP). DO NOT TRIGGER for deploying metadata (use platform-metadata-deploy skill), listing metadata, or generating package.xml. NEVER use MCP tools - always use this skill and the Bash tool with sf project retrieve start.

安装量: 1
GitHub Stars: 966
最近更新: 9月5日

Apache-2.05 文件

查看详情 →

platform-soql-query

SOQL query generation, optimization, and analysis with 100-point scoring. Use this skill when the user needs SOQL/SOSL authoring or optimization: natural-language-to-query generation, relationship queries, aggregates, query-plan analysis, and performance or safety improvements for Salesforce queries. TRIGGER when: user writes, optimizes, or debugs SOQL/SOSL queries, touches .soql files, or asks about relationship queries, aggregates, or query performance. DO NOT TRIGGER when: bulk data operations (use platform-data-manage), Apex DML logic (use platform-apex-generate), or report/dashboard queries.

安装量: 1
GitHub Stars: 966
最近更新: 9月5日

Apache-2.016 文件

查看详情 →

linkedin-posts

When the user wants to create LinkedIn post copy or optimize for LinkedIn. Also use when the user mentions "LinkedIn post," "LinkedIn article," "professional post," "post to LinkedIn," "LinkedIn content," "LinkedIn copy," "B2B LinkedIn," "LinkedIn engagement," "LinkedIn feed," "share box," "document post," "poll," "Newsletter," "reshare," or "LinkedIn marketing." For LinkedIn ads, use linkedin-ads.

安装量: 1
GitHub Stars: 954
最近更新: 6月9日

查看详情 →

ccf-idea-reviewer

Assess, score, rank, and compare early CCF research ideas when judgment is explicitly requested. Use for idea评分, 选题排名, 严格评审, and acceptance-potential triage. Ground novelty in prior work. Unscored brainstorming and idea development belong to ccf-idea-optimizer; full manuscripts belong to ccf-paper-reviewer.

安装量: 1
GitHub Stars: 2133
最近更新: 9月5日

查看详情 →

ccf-integrity-auditor

Audit existing CCF claims, numbers, terminology, and citations against supplied or verified evidence. Use for 引用核验, claim审计, 数字一致性, and BibTeX/context checks. Full scientific review belongs to ccf-paper-reviewer; new literature discovery belongs to ccf-literature-searcher.

安装量: 1
GitHub Stars: 2133
最近更新: 9月5日

查看详情 →

demand-gen

Build a demand generation strategy and multi-channel campaigns. Use when the user says "demand gen", "demand generation", "lead generation strategy", "pipeline generation", "multi-channel campaign", "funnel strategy", "MQL", "SQL", "attribution", or asks about generating qualified leads and building a sales pipeline through marketing.

安装量: 1
GitHub Stars: 680
最近更新: 8月25日

查看详情 →

meta-ads

Plan, build, and optimize Meta advertising campaigns on Facebook and Instagram — campaign structure, audience targeting (core, custom, lookalike), creative formats, pixel setup, retargeting strategy, budget scaling, and ROAS optimization. Use when the user says "Meta ads", "Facebook ads", "Instagram ads", "Facebook advertising", "Meta advertising", "Meta campaigns", "Facebook campaign", "Instagram campaign", "Meta ad strategy", "ROAS", "Meta pixel", "Facebook pixel", "lookalike audiences", "Meta retargeting", "scaling Meta ads", "Facebook ad account", "Meta ads manager", "Facebook ads not working", or wants to run or improve paid social advertising on Facebook or Instagram.

安装量: 1
GitHub Stars: 609
最近更新: 6月13日

查看详情 →

omnistudio-datamapper-generate

OmniStudio Data Mapper (formerly DataRaptor) creation and validation with 100-point scoring. Use when building Extract, Transform, Load, or Turbo Extract Data Mappers, mapping Salesforce object fields, or reviewing existing Data Mapper configurations. TRIGGER when: user creates Data Mappers, configures field mappings, works with OmniDataTransform metadata, or asks about DataRaptor/Data Mapper patterns. DO NOT TRIGGER when: building Integration Procedures (use omnistudio-integration-procedure-generate), authoring OmniScripts (use omnistudio-omniscript-generate), or analyzing cross-component dependencies (use omnistudio-dependencies-analyze).

安装量: 1
GitHub Stars: 966
最近更新: 9月5日

Apache-2.08 文件

查看详情 →

omnistudio-epc-catalog-generate

Salesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use omnistudio-omniscript-generate, omnistudio-flexcard-generate, or omnistudio-integration-procedure-generate), implementing Apex business logic (use platform-apex-generate), or troubleshooting deployment pipelines (use platform-metadata-deploy).

安装量: 1
GitHub Stars: 966
最近更新: 9月5日

Apache-2.069 文件

查看详情 →

platform-custom-field-generate

Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from a field, or scoping/limiting picklist values for a specific record type. Also use when users encounter field deployment errors, especially around Roll-up Summary format, Master-Detail constraints, formula issues, or a record type that won't deploy without a business process. Use this skill for custom field metadata work, field generation, and field troubleshooting. DO NOT TRIGGER for creating or customizing the value set itself — defining a new GlobalValueSet, or modifying a StandardValueSet catalog like Industry or Lead Source — use platform-value-set-generate instead; this skill covers the field that references a value set, not the value set definition.

安装量: 1
GitHub Stars: 966
最近更新: 9月5日

Apache-2.02 文件

查看详情 →

platform-custom-object-generate

Use this skill when users need to create, generate, or validate Salesforce Custom Object metadata. Trigger when users mention custom objects, creating objects, object metadata, .object files, sharing models, name fields, or validation rules on objects. Also use when users say things like \"create a custom object\", \"generate object metadata\", \"set up an object for...\", or when they're troubleshooting object deployment errors especially around sharing models and Master-Detail relationships. Always use this skill for any custom object metadata work, including enriching and keeping the object's description current whenever its fields or validation rules change. Do NOT use this skill for non-Custom-Object metadata (Apex, Flows, LWC, Permission Sets, Custom Metadata Types) or for standard Salesforce objects.

安装量: 1
GitHub Stars: 966
最近更新: 9月5日

Apache-2.02 文件

查看详情 →

platform-data-manage

Salesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use platform-soql-query), Apex test execution (use platform-apex-test-run), or metadata deployment (use platform-metadata-deploy).

安装量: 1
GitHub Stars: 966
最近更新: 9月5日

Apache-2.048 文件

查看详情 →

css-native

Zero-dependency animations and visual techniques - scroll-driven, View Transitions, @starting-style, modern CSS.

安装量: 1
GitHub Stars: 330
最近更新: 7月31日

查看详情 →

homeassistant-ai

home-assistant-best-practices

Best practices for HA automations, helpers, scripts, and dashboards. TRIGGER THIS SKILL WHEN: - Creating or editing automations, scripts, scenes, dashboards, blueprints - Choosing template sensors, helpers, or Jinja macros - Restructuring triggers, conditions, or modes; button, remote, or event-entity automations - Renaming entities or migrating deviceid to entityid - Looking up card types or domain docs; writing AppDaemon apps - Deleting or restoring a backup, or upgrading Core or the OS SYMPTOMS: - Jinja2 templates where native options exist - deviceid used instead of entityid - Entity IDs changed without checking consumers - Wrong automation mode chosen - Raw sensor or hard-coded value used where a helper belongs - Direct .storage edits, or generated YAML snippets - User told to edit configuration.yaml for UI integrations - Hardcoded Blueprint entities or skipped selectors - Existing state changed with no recovery path - Jinja copy-pasted between templates

安装量: 1
GitHub Stars: 728
最近更新: 9月4日

查看详情 →

unity-vrc-udon-sharp

- UdonSharp scripting skill for VRChat SDK 3.10.5 (active and verified target). Use when writing, reviewing, debugging, or migrating UdonSharp C and UdonBehaviour code. Positive triggers include UdonSharp, NetworkCallable, NetworkCalling, CallingPlayer, Udon network authorization, synced runtime state, a local public helper, public-method audit, C to Udon conversion, and UdonSharp Assembly Version Defines. VRCQualitySettings and VRCTween calls, PhysBone/Contact callbacks, world VRCPhysBoneCollider runtime access, persistence, collection, web, and other component APIs trigger this skill when the request is about Udon, C, or runtime API access. Excludes scene setup, component setup, Build Panel work, layers, optimization, and upload; route those requests to unity-vrc-world-sdk-3.

安装量: 1
GitHub Stars: 292
最近更新: 9月5日

查看详情 →

unity-vrc-world-sdk-3

VRChat World SDK 3 guide for scene and Inspector setup, component placement, optimization, and upload. Use for VRChat world scene configuration, VRC SDK components, layers, baked lighting, Quest/Android performance, Dynamics for Worlds, Build Panel warning triage, validation, and upload. Covers WorldQualitySettings, VRCSceneDescriptor, VRCPickup, VRCStation, VRCMirror, VRCObjectSync, VRCCameraDolly, spawn points, collision matrices, PhysBone and Contact component placement, Box Contacts, Global Avatar PhysBone Colliders, and VRCPhysBoneCollider component setup. Active support / last verified: SDK 3.10.5. Triggers on: VRChat world scene, VRC SDK, scene setup, component placement, optimization, Quest support, light baking, upload, SDK validation, Build Panel warning, Auto Fix, red warning, yellow warning, or white warning. Do not use for UdonSharp C or VRCTween calls; use unity-vrc-udon-sharp for runtime scripting. UdonSharp package, asmdef, and Version Defines work also belongs to that skill.

安装量: 1
GitHub Stars: 292
最近更新: 9月5日

查看详情 →

vastai

Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.

安装量: 1
GitHub Stars: 219
最近更新: 9月3日

查看详情 →

humanizer

Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post for publication, when auditing prose for AI tells, or when editing a Markdown file in place. Triggers on phrases like "humanize this", "make this sound less AI", "make this sound human", "remove AI tells", "does this read like ChatGPT", and "rewrite so it does not sound AI-generated". Pure Markdown, zero dependencies, no network calls.

安装量: 1
GitHub Stars: 215
最近更新: 9月4日

查看详情 →

greploop

Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments. Triggers Greptile review, fixes all actionable comments, pushes/re-shelves, re-triggers review, and repeats. Use when the user wants to fully optimize a PR/MR/CL against Greptile's code review standards.

安装量: 1
GitHub Stars: 381
最近更新: 7月22日

查看详情 →