Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Generate Xiaohongshu (小红书/RED) content optimized for the platform's CES algorithm. Use when: (1) creating xiaohongshu/小红书 posts, (2) writing Chinese social media content for RED, (3) generating content with xiaohongshu SEO optimization, (4) planning xiaohongshu content calendars. Supports diary-style, tutorial, review, and list formats with proper AI content labeling.
Generate, review, and publish social media content through MCP with AgentAuth and workspace token authentication.
代码审查能力，调用CodeReviewer专家进行安全、性能、风格全面审查，输出问题列表和改进建议
>-
issue-to-pr — Automatically fix GitHub issues end-to-end: reads the issue, analyzes repository code, implements a fix, and submits a pull request. Use when the user provides a GitHub issue URL, mentions fixing a GitHub issue, or uses the /fix-issue command. Supports URLs in the format https://github.com/{owner}/{repo}/issues/{number}.
Drives the BillClaw local bookkeeping CLI against SQLite (db/expenses.db) via scripts/main.py JSON subcommands—add/query transactions, delete and category-merge with preview+confirm, user-defined categories, reports with chart PNGs, CSV export, and a local Flask dashboard. Use when the user tracks 记账/收支/账本, manages 分类, asks for 报表 or charts, wants to open the Web 看板, exports CSV, or mentions BillClaw or running main.py (root shim) / scripts/main.py.
梳理某个 Skill、脚本或工作流需要的权限，并提出最小权限替代方案。；use for permissions, least-privilege, security workflows；do not use for 绕过系统安全控制, 生成提权方法.
从评论、评价和反馈中提炼卖点、痛点、反对意见与应删除的话术。；use for reviews, voice-of-customer, marketing workflows；do not use for 造假好评, 泄露用户身份.
从剪贴板读取审稿意见、导师批注或评审反馈，生成逐条回复、修改计划与优先级建议。
在执行 shell 方案前检查危险模式，如 pipe-to-shell、覆盖式删除、危险重定向或混淆执行。；use for shell, security, command-review workflows；do not use for 提供攻击性命令, 帮用户绕过限制.
Convert a syllabus, exam scope, or course notes into a revision calendar
Turn scattered notes, metrics, and unfinished tasks into a weekly operating
汇总本周完成、阻塞、经验教训与下周计划，形成管理层版和执行版摘要。；use for weekly-review, planning, retrospective workflows；do not use for 杜撰完成项, 替代工时系统.
Push decisions to Arbiter Zebu for async human review. Use when you need human input on plans, architectural choices, or approval before proceeding.
>
Upload many files to S3 with automatic organization by first-character prefixes.
Not a code generator — an entire dev team. You write the vision, it ships the code. Autonomous builds, PRs, reviews, and merges across multiple repos. Point it at any JS/TS project and a product vision. It plans features, writes code, verifies builds, creates PRs, reviews diffs, and merges — autonomously. Manages multiple repos as one product. Use when you want to ship code without writing it. AI code generation, autonomous development, workflow automation, multi-repo orchestration, TypeScript, JavaScript, GitHub, OpenAI, Anthropic, Claude, GPT, LLM, devtools, CI/CD, pull requests, code review.
Self-improving code reviewer that learns your codebase over time. Analyzes git history, spots patterns, identifies risk — and gets smarter every run.
Build, curate, score, and maintain high-quality information source lists for AI, technology, business, or any topic. Use when the user asks to create a skill for trusted sources, make a watchlist of people/sites/accounts to follow, filter noisy sources into a smaller high-signal set, turn a link dump into a reusable monitoring system, or design a repeatable workflow for tracking official accounts, researchers, critics, and market signals.
Design, preview, and generate UI code using Google Stitch (via MCP). Helps developers choose the best UI by generating previews first, allowing iteration, and then exporting code.
vwu.ai 平台上的 gemini 模型调用技能。
vwu.ai 平台上的 veo 模型调用技能。
Upload any contract or legal document and get a structured risk analysis with flagged clauses, plain-language explanations, and negotiation suggestions.
>
>
Design and implement web animations that feel natural and purposeful. Use this skill proactively whenever the user asks questions about animations, motion, easing, timing, duration, springs, transitions, or animation performance. This includes questions about how to animate specific UI elements, which easing to use, animation best practices, or accessibility considerations for motion. Triggers on: easing, ease-out, ease-in, ease-in-out, cubic-bezier, bounce, spring physics, keyframes, transform, opacity, fade, slide, scale, hover effects, microinteractions, Framer Motion, React Spring, GSAP, CSS transitions, entrance/exit animations, page transitions, stagger, will-change, GPU acceleration, prefers-reduced-motion, modal/dropdown/tooltip/popover/drawer animations, gesture animations, drag interactions, button press feel, feels janky, make it smooth.
AI短剧内容基因检测。零依赖可用：AI直接分析版权疑似、年龄分级违规、小说魔改程度，输出结构化风险图谱。可选配 Python 环境启用三重相似度算法（n-gram / 编辑距离 / TF-IDF）提升精度。结果仅供内容审核参考，不构成法律意见。
门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，输出审核结论与原因（原始 JSON + 自然语言结论）。
重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。
Render custom Aavegotchi 3D images from arbitrary trait and wearable combinations. Use when the user describes a synthetic or hypothetical gotchi look in plain language, asks for an outfit preview, headshot, or full-body image, and is not asking for an existing onchain token by tokenId or inventory URL.
This skill should be used when working with memory-lancedb-pro, a production-grade long-term memory MCP plugin for OpenClaw AI agents. Use when installing, configuring, or using any feature of memory-lancedb-pro including Smart Extraction, hybrid retrieval, memory lifecycle management, multi-scope isolation, self-improvement governance, or any MCP memory tools (memory_recall, memory_store, memory_forget, memory_update, memory_stats, memory_list, self_improvement_log, self_improvement_extract_skill, self_improvement_review).
Comprehensive bug audit for Node.js web projects. Activate when user asks to audit, review, check bugs, find vulnerabilities, or do security/quality review on a project. Works by dissecting the project's actual code to build project-specific check matrices, then exhaustively verifying each item — not by running a generic checklist. Supports games, data tools, WeChat apps, API services, bots, and dashboards.
Three-tier code quality defense: L1 quick scan, L2 deep audit (via bug-audit), L3 cross-validation with adversarial testing. 三级代码质量防线。
Game development quality gates and mandatory checks. Activate when building, reviewing, debugging, or deploying any game project (H5/Canvas/WebGL/Phaser/Three.js/2D/3D). Covers state cleanup, lifecycle management, input handling, audio, persistence, networking, anti-cheat, and performance. Use as pre-deploy checklist or when diagnosing game-specific bugs (state leaks, phantom timers, buff conflicts, memory growth, touch issues).
38 battle-tested iOS development rules covering accessibility, navigation, architecture, dark mode, localization, App Review guidelines, and more. Targets the mistakes LLMs actually make when generating Swift/SwiftUI code.
Expand a structured brief in `content-production/inbox/` into a reusable long-form markdown article draft, then run a local writer / critic / judge quality loop with a constrained humanization pass. Use when Codex needs a stage-1 article draft plus reusable writing sidecars for downstream `generate-image` and `wechat-formatter`.
Sync a local `wechat-report` result into Feishu Bitable after the user has reviewed the report and confirmed the sync.
Generate article companion images for the content factory pipeline. Use when Codex needs article images, infographic cards, inline visuals, or a PNG exported from an article markdown draft before preview or publishing.
Render article markdown into WeChat-style HTML as an independent executor. Use when Codex needs公众号排版预览, WeChat HTML output, or a publishable HTML artifact generated from an article markdown draft.
Launch a local WeChat article workbench for Markdown import, WeChat HTML preview, theme tuning, image selection, and optional draft push. Use when Codex needs a browser-based preview and manual QA layer before publishing.
Collaboratively design, evaluate, iterate on, and recommend a final launch candidate for a target prompt under the principle of “human-gated, agent-executed” workflow.
Prepare Claw skills for public release. Use when publishing skills to GitHub or ClawdHub - covers security audit, portability, documentation, git hygiene. Triggers: publish skill, release skill, audit skill, skill checklist, prepare skill for release.
Assemble modular ads from Supabase components and deploy to Facebook Ads Manager via the Marketing API. Supports preview, single/batch deploy, and status tracking. Uses ad_components table for A/B testing at scale.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Manage Linear issues, projects, and cycles via GraphQL. Use when triaging backlogs, creating tasks from conversation, checking sprint progress, or running team reviews. Requires LINEAR_API_KEY.
Use when evaluating, testing, and optimizing an agent architecture or multi-agent system. Best for reviewing planning, routing, memory, tool use, reliability, observability, cost, and system-level failure modes.
Balance tracking, order overview, and market data across exchanges using OpenMM.
Scan OpenClaw skill folders for security red flags before installing or publishing. Detects data exfiltration, credential theft, prompt injection, destructive commands, obfuscation, privilege escalation, and supply chain risks. Use when: evaluating a skill from ClawHub before install, auditing your own skills before publishing, or reviewing any SKILL.md for safety. NOT for: general code review or vulnerability scanning of non-skill codebases.
Use OpenAI Codex CLI for coding tasks. Triggers: codex, code review, fix CI, refactor code, implement feature, coding agent, gpt-5-codex. Enables Clawdbot to delegate coding work to Codex CLI as a subagent or direct tool.
Triage tenant maintenance requests by severity, assign priority, identify the right contractor type, estimate costs, and generate work orders. Use when a tenant reports a maintenance issue, when reviewing open work orders, or when assessing property condition. Follows Massachusetts habitability requirements (105 CMR 410).