热门技能
当前社区里最受关注、增长最快的技能。
meta-upload
dreammis
使用 sau CLI 登录 Facebook Page，发布视频或图文、设置北京时间排期、查询原作品并删除。
hupu-upload
dreammis
使用 social-auto-upload 的 sau hupu 登录虎扑并发布视频，可指定封面。Use when 用户要向虎扑发布视频或检查虎扑账号状态。
alipay-upload
dreammis
使用 social-auto-upload 的 sau alipay 登录支付宝生活号并发布视频。Use when 用户要向支付宝生活号发布视频或检查创作账号状态。
ip-as-logo
s1dashu
Generate highly simplified personified IP mascot logos with Flat-first geometry, rounded heavy forms, two IP colors plus one background color by default, and continuous-gradient neo-skeuomorphic micro-volume. Use when creating an animal, creature, robot, ghost, plant, object, or other character as a minimal square logo or app-icon artwork, including when the agent should infer three product-relevant directions and propose six independent candidates for approval.
template-selector
jamditis
Choose the correct CLAUDE.md or LESSONS.md template for journalism projects. Use when starting a new project, setting up documentation, or unsure which template category fits best. Provides decision trees and selection guidance for 6 journalism-focused template types.
security-review
mastra-ai
Security-focused code review checklist for identifying vulnerabilities
customer-support-agent
mastra-ai
Authoring playbook for building agents that triage and reply to customer messages — support tickets, email inquiries, chat questions, refund requests, or product issues. Use this when the user wants an agent that handles inbound customer questions, drafts replies, escalates hard cases, summarizes tickets, or follows a support playbook.
severe-weather
mastra-ai
Use when conditions include storms, flooding, heat waves, or other hazards.
coding-agent
mastra-ai
Authoring playbook for building agents that write, edit, review, or refactor code. Use this when the user asks for an agent that writes scripts, generates code, reviews pull requests, refactors a codebase, fixes bugs, implements features, writes tests, or works with programming languages such as Python, TypeScript, JavaScript, Go, Rust, SQL, or shell.
content-writer-agent
mastra-ai
Authoring playbook for building agents that draft written content — blog posts, marketing copy, social media posts, newsletters, product descriptions, landing pages, or ad copy. Use this when the user wants an agent that writes, drafts, or rewrites text for publication or marketing.
factory-triage
mastra-ai
Triage a Factory work item's issue — trace history, understand architecture, diagnose root cause, then advance the stage
triage-issue
mastra-ai
First-contact triage for a GitHub issue
research-agent
mastra-ai
Authoring playbook for building agents that search, read, and synthesize information into a report. Use this when the user wants an agent to research a topic, summarize sources, compare options, do competitive analysis, monitor news, generate briefs, or pull together a citation-backed report from the web or internal documents.
Command Development
anthropics
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
provider-cost-comparison
langwatch
Prices your real LangWatch usage mix against other model providers. Exports your actual token mix per model, including the cache read and write split, fetches current price cards, and reprices the same month of usage under each candidate, with the cache sensitivity stated. Use when someone asks whether a cheaper provider or model would actually save money on your workload.
cmux
manaflow-ai
End-user control of cmux topology and routing (windows, workspaces, panes/surfaces, focus, moves, reorder, identify, trigger flash). Use when automation needs deterministic placement and navigation in a multi-pane cmux layout.
literature-review
IncarnaMind
Writes a literature review across the User's Documents on the Question's topic, synthesised by theme rather than one Document after another, showing where the Documents agree and disagree and what they leave out, with every claim cited. Use when the User asks for a literature review, a review of related work, a state-of-the-art overview or a synthesis of several Documents.
summarise-document
IncarnaMind
Writes a structured summary of one Document, or of each Document in the Question's Search scope, with sections that suit the kind of Document (a paper's claims, method and limitations; an agreement's parties, term and obligations) and each point with a Citation. Use when the User asks to summarise, digest or give an overview of a paper, report, contract or other Document.
mind-to-report
IncarnaMind
Turns the User's Mind, meaning the Notes, Questions and earlier Answers above the Question, into a structured report draft with a title, a summary, sections and a conclusion, keeping their Citations and inventing no sources. Use when the User asks to write up, draft a report, compile or turn their notes or this Mind into a document.
factory-complete-issue
mastra-ai
Mark a GitHub issue as done and update its status labels
docs-diagrams
mastra-ai
Convert existing docs diagram images to Mermaid, and author new Mermaid diagrams for Mastra docs. Use when replacing an Excalidraw or PNG/JPG/SVG diagram with Mermaid, when a docs page needs a new diagram, when a diagram renders wrong in light or dark mode, or when auditing which docs images should become Mermaid. Triggers on: convert diagram, Excalidraw, mermaid, flowchart, diagram image, diagram styling, diagram looks wrong.
label-core-bugs
mastra-ai
Review open mastra-ai/mastra GitHub issues, identify direct @mastra/core bugs, and apply the @mastra/core label. Use when auditing issues for core ownership, labeling direct core bugs, or periodically reconciling the @mastra/core issue label.
factory-rereview
mastra-ai
Re-review a pull request after a push — reconcile the previous review against the new commits, look for new defects the push introduced, then a fresh pass over the whole PR, and finish with a verdict on the PR
translate
ZJU-REAL
"Translate text accurately — preserve formatting, handle plurals, and adapt tone per locale."