Skill reviews

Test-Driven Development for coding and bug fixing. cycle - Red→Green→Refactor cycle, defining expected behavior, bug-fix TDD, anti-patterns, run - test execution workflow (environm

• Prose only: no discrete steps
• Does not say what the result is

当用户需要按关键词批量下载图片、从 Bing 或多个图片来源收集候选、保存图片到本地目录、避免重复下载，或希望复用当前仓库里的现成图片下载流程时使用。遇到类似“帮我按关键词下载 10 张图片”“批量抓取 Bing 图片并保存到本地”“从多个来源收集图片候选再下载”“需要下载摘要和保存目录”这类请求时，应主动使用这个 skill。

• 11 top-level sections: this looks like several domains in one skill
• 4 test cases, all positive: not one "should refuse" or "should ask first"
• No test case covers injection arriving through data

Manage a Jellyfin/Plex + *Arr media server stack — check status, add content, monitor downloads, diagnose issues, restart services.

• Does not say what the result is
• No condition that starts the skill

将B站视频字幕转换为带截图的Notion学习笔记。 当用户需要从B站视频提取字幕、分析内容并创建Notion学习笔记时，必须使用此技能。 支持BV号、完整URL输入，自动下载CC字幕，智能处理内容，生成带截图标记的结构化学习笔记。 适用于学习、研究、知识整理等场景。

• References files that are not bundled: assets/screenshot_hh_mm_ss.jpg
• 11 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: assets/screenshot_hh_mm_ss.jpg

Build and publish a Quartz-hosted Korean web-novel serial (draft→cover→webp→episode md→lint→publish). Uses Nano Banana Pro + ffmpeg.

• The response is described with custom markup (9 tags): a typed call is more reliable
• Does not say what the result is
• No condition that starts the skill

Agent AI Autonom Proactiv v5.0 pentru OpenClaw. Workflow automat cu cercetare, analiză, planificare și execuție. Feedback loop cu timeout 6 minute, conexiuni între task-uri și învă

• 12 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Get real-time crypto buy/sell activity from Smart Money wallets, KOL influencer wallets, and personally followed wallets via GMGN API — alpha signals, whale tracking, meme token co

• References files that are not bundled: ../../docs/workflow-token-research.md, ../../docs/workflow-smart-money-profile.md, ../../docs/workflow-daily-brief.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 18 top-level sections: this looks like several domains in one skill

Analyze any crypto wallet by address — holdings, realized/unrealized P&L, win rate, trading history, performance stats, specific token balance, and tokens created by a developer wa

• References files that are not bundled: ../../docs/workflow-wallet-analysis.md, ../../docs/workflow-smart-money-profile.md
• 14 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (8 tags): a typed call is more reliable

MCP server that gives AI agents the ability to make payments, manage budgets, and handle billing -- directly from Claude Desktop, Cursor, Cline, or any MCP-compatible agent runtime

• Does not say what the result is
• No condition that starts the skill

RSS 订阅 + AI 汇总分析 + 飞书推送。 定时拉取新文章，AI 生成每日资讯汇总报告（热门话题、关键趋势、推荐阅读），推送到飞书。 当用户提到"RSS"、"订阅"、"RSS阅读器"、"文章订阅"、"资讯订阅"、"资讯汇总"时使用此 Skill。 首次使用自动添加 18 个精选订阅源（中文 + 国外 AI + 科技媒体）。

• 16 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

OpenClaw 安全漏洞检查与配置审计工具。用于检测当前 OpenClaw 版本存在的已知安全漏洞、公网访问安全风险，对比当前版本与最新版本的差异，获取漏洞详情、风险评估、配置审计和升级建议。使用场景：(1) 用户询问"检查一下我的 OpenClaw 版本有什么安全漏洞"，(2) 用户说"检查 OpenClaw 安全问题"，(3) 用户想了解当前版本的漏洞

• Does not say what the result is
• No condition that starts the skill

case.dev — a legal AI platform with encrypted document vaults, OCR, audio transcription, and legal search. This skill installs the casedev CLI and provides sub-skills for each capa

• Prose only: no discrete steps
• Does not say what the result is

Query Claude API usage and cost reports from the command line. Secure macOS Keychain storage for Admin API key. Table/JSON output.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (10 tags): a typed call is more reliable
• Does not say what the result is

Book videographer services through Lokuli MCP. Use when user needs to find and book videographer. Triggers on requests like "book a videographer", "find videographer near me", or a

• Prose only: no discrete steps
• Does not say what the result is

Book appliance-repair services through Lokuli MCP. Use when user needs to find and book appliance-repair. Triggers on requests like "book a appliance-repair", "find appliance-repai

• Prose only: no discrete steps
• Does not say what the result is

Use when OpenClaw needs to join a hosted Aqua from URL + invite code, read mirror-backed or live Aqua state, inspect runtime status, or run local/hosted Aqua join, context, pulse,

• References files that are not bundled: scripts/check-clawhub-release.sh, scripts/install-openclaw-heartbeat-cron.sh, scripts/install-aquaclaw-hosted-pulse-service.sh
• The skill tells the model to perform an irreversible action with no human approval
• 18 referenced file(s) missing: scripts/check-clawhub-release.sh, scripts/install-openclaw-heartbeat-cron.sh, scripts/install-aquaclaw-hosted-pulse-service.sh

Assess construction data quality using completeness, accuracy, consistency, timeliness, and validity metrics. Automated validation with regex patterns, thresholds, and reporting.

• References files that are not bundled: df
• 10 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: df

掘金量化Python SDK - 事件驱动量化平台，支持A股、期货、期权、ETF、可转债回测与实盘交易。

• 25 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Use Cloudflare Browser Rendering REST APIs to extract rendered webpage content as Markdown or crawl whole sites asynchronously. Use when normal web_fetch is insufficient because pa

• References files that are not bundled: references/*.md
• 1 referenced file(s) missing: references/*.md
• Says nothing while it works

Performance-optimized strategies for editing Feishu (Lark) documents via OpenClaw's feishu_doc tool. Use when: (1) modifying existing Feishu documents, (2) inserting images at spec

• References files that are not bundled: url
• 12 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: url

AI 领域系统学习体系。管理知识图谱、深度学习笔记、实战复盘和关联网络。触发场景：学习计划、知识图谱更新、深度研究某个 AI 主题、实战复盘总结、调研后沉淀知识、每周学习回顾。当用户说'学了什么'、'总结一下'、'沉淀知识'、'复盘'、'更新图谱'、'深入研究'、'写笔记'、'学习回顾'、'review what I learned'、'update kno

• References files that are not bundled: 相对路径
• 10 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: 相对路径

Natural language task and project management. Use when the user talks about things they need to do, projects they're working on, tasks, deadlines, or asks for a project overview /

• References files that are not bundled: {rel_path}, templates/dashboard/*.html, scripts/*.py
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill

Book fitness services through Lokuli MCP. Use when user needs to find and book fitness. Triggers on requests like "book a fitness", "find fitness near me", or any fitness service r

• Prose only: no discrete steps
• Does not say what the result is

分析真实项目并生成或修订安全、可验证的 GitHub Actions workflow；当用户要求创建 CI、测试矩阵、构建、Release、部署、缓存、Secrets、OIDC、PR 自动化或排查 workflow 配置时使用

• Does not say what the result is
• No condition that starts the skill

编程错误消息翻译专家 — 将英文错误消息翻译成中文，解释原因并提供修复方案

• Does not say what the result is
• No condition that starts the skill