What exactly is broken in popular skills: references to files that are not bundled, actions taken without human approval, processes with no stopping condition. Everything here is measured from the skill text rather than judged by a model, so every line can be checked.
Analyzerwill not run
Health check knowledge base for broken links, missing frontmatter, tag inconsistencies, and coverage gaps. Use when user says "audit KB", "check frontmatter", "find broken links",
- References files that are not bundled: scripts/check_links.py
- 1 referenced file(s) missing: scripts/check_links.py
- Does not say what the result is
clawhub · ↓ 1 647
Referencewill not run
Import notes from Logseq pages into the slipbox. Use when user pastes a Logseq page with properties and bulleted notes. Parses page-level properties, extracts each bullet as an ind
- References files that are not bundled: url
- 1 referenced file(s) missing: url
- Does not say what the result is
clawhub · ↓ 1 606
Analyzerwill not run
User behavior correction skill. Triggered by "fix:" prefix feedback (e.g., "fix: why didn't you commit?").
Analyzes the mistake, improves the relevant prompt (skill/rule/agent/memo
- References files that are not bundled: ../fa/SKILL.md
- 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 (12 tags): a typed call is more reliable
clawhub · ↓ 2 404
ReferenceTelegramwill not run
面向中文用户的小红书舆情巡检技能。按关键词抓取搜索结果,判断登录墙/验证码/空结果状态,输出结构化笔记、热度/风险/竞品信号和现场截图。使用前需配置 XHS_COOKIE 与消息接收渠道(如 Telegram、企业微信)。适用于品牌口碑监控、竞品观察、热点追踪与内容研究。
- References files that are not bundled: 真实URL, URL
- 2 referenced file(s) missing: 真实URL, URL
- Does not say what the result is
clawhub · ↓ 915 ★ 1
Procedurewill not run
- References files that are not bundled: examples/run_real_discussion.py
- 15 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: examples/run_real_discussion.py
clawhub · ↓ 891 ★ 1
Referencewill not run
多Agent加密货币量化交易系统 — 基于 TradingAgents 多Agent框架 + Binance 执行层。 支持:技术分析、消息分析、多Agent辩论、自动化交易信号生成、Binance 现货下单。 适用场景:研究量化策略、自动交易Bot开发、加密货币组合分析。
- References files that are not bundled: scripts/hourly_contrarian_strategy.pine
- 12 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: scripts/hourly_contrarian_strategy.pine
clawhub · ↓ 910 ★ 1
Procedurewill not run
为中文长篇小说、连载网文、章节样稿、已有草稿续写提供一套完整且内聚的创作流程:分流新建/续写/救稿任务,维护 plan/ 与 memory/ 记忆系统,在写正文前先学习指定题材的文风笔触,再按节奏持续产出章节,并在同一技能内完成文风校准、题材适配、连载维护与必要的创作研究。适用于用户要求写小说、开书、搭大纲、出样章、分章节连载、继续写下一章、修大纲救稿、想让
- References files that are not bundled: scripts/init-novel.ps1
- 19 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: scripts/init-novel.ps1
clawhub · ↓ 987 ★ 1
Integrationwill not run
Standardized WeChat official account writing workflow integrating wechat-publisher, wechat-toolkit, wechat-mp-writer-skill and other skills. Provides complete workflow from materia
- References files that are not bundled: 图片路径
- 14 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: 图片路径
clawhub · ↓ 862 ★ 1
Procedurewill not run
飞书消息与群管理 Skill。发送消息、建群、置顶、加急、撤回、群菜单/Tab/公告等 25+ 项 IM 能力。当需要通过飞书发送消息、管理群聊、操作群成员或配置群功能时使用此 Skill。
- References files that are not bundled: url
- 1 referenced file(s) missing: url
- Does not say what the result is
clawhub · ↓ 1 589
Generatorwill not run
Helps non-technical users create their own Skills through natural conversation. Triggers when users say "I want to create a Skill", "turn this workflow into a Skill", "I want you t
- References files that are not bundled: references/quality_checklist.md, references/preview_test.md
- 2 referenced file(s) missing: references/quality_checklist.md, references/preview_test.md
- Does not say what the process needs to start
clawhub · ↓ 880 ★ 1
IntegrationGitHubwill not run
Router for the Cargo CLI skill bundle — load first for anything Cargo, and whenever a task spans two Cargo domains. Explains what each skill owns, declarative workspace-as-code (ca
- References files that are not bundled: ../cargo-quickstart/SKILL.md, ../README.md, ../cargo-project/SKILL.md
- 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 (27 tags): a typed call is more reliable
clawhub · ↓ 3 155
Referencewill not run
- 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}
clawhub · ↓ 874 ★ 1
Analyzerwill not run
Detect and map data silos in construction organizations. Identify disconnected data sources and integration opportunities
- References files that are not bundled: ../erp-integration-analysis/SKILL.md, ../../Chapter-1.1/data-evolution-analysis/SKILL.md, ../../Chapter-4.2/etl-pipeline/SKILL.md
- 3 referenced file(s) missing: ../erp-integration-analysis/SKILL.md, ../../Chapter-1.1/data-evolution-analysis/SKILL.md, ../../Chapter-4.2/etl-pipeline/SKILL.md
- Does not say what the result is
clawhub · ↓ 1 594
Generatorwill not run
Generate polished 1080×1920 TikTok/Reels/Shorts video ads from product clips and images. Three viral styles: Clean, Meme, UGC. Python + ffmpeg, no cloud required.
- References files that are not bundled: examples/config_example.json
- 1 referenced file(s) missing: examples/config_example.json
- No condition that starts the skill
clawhub · ↓ 893 ★ 1
Analyzerwill not run
使用本 skill 自带的 fetch.py 和 analyze.py,对 A 股个股做短期趋势分析。 Use this skill whenever the user asks to analyze A-share stocks, ETFs (like A500/159339), check short-term trend (bullish/bearis
- References files that are not bundled: scripts/analyze_data.md
- The response is described with custom markup (3 tags): a typed call is more reliable
- 1 referenced file(s) missing: scripts/analyze_data.md
clawhub · ↓ 892 ★ 1
Referencewill not run
- References files that are not bundled: references/openclaw-integration.md, scripts/activator.sh, scripts/error-detector.sh
- 17 top-level sections: this looks like several domains in one skill
- 5 referenced file(s) missing: references/openclaw-integration.md, scripts/activator.sh, scripts/error-detector.sh
clawhub · ↓ 1 622
Analyzerwill not run
深度多步网页研究。迭代搜索、页面抓取、综合分析,生成带引用的 Markdown 报告。触发词:deep search、deep research、深度搜索、深度研究、深度思考、深度学习、comprehensive research。
- References files that are not bundled: URL
- 1 referenced file(s) missing: URL
- Does not say what the process needs to start
clawhub · ↓ 1 657
Integrationwill not run
Integrates Dub Links API endpoints to create, update, delete, retrieve, list, count, and run bulk operations on short links. Use when the user asks for "dub links api", "create lin
- References files that are not bundled: references/openapi-spec.json
- 1 referenced file(s) missing: references/openapi-spec.json
- Does not say what the process needs to start
clawhub · ↓ 1 611
Analyzerwill not run
- References files that are not bundled: VIDEO_DETECTION.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 1 referenced file(s) missing: VIDEO_DETECTION.md
clawhub · ↓ 1 586
Procedurewill not run
Manage Grid bots (spot/contract/coin-margined) and DCA Martingale bots (Spot DCA 现货马丁 / Contract DCA 合约马丁) on OKX. Covers create, stop, amend, monitor P&L, TP/SL, margin/investment
- References files that are not bundled: ../_shared/preflight.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 13 top-level sections: this looks like several domains in one skill
clawhub · ↓ 1 559
IntegrationMirowill not run
Miro CLI tool for board/team/org management via command line. Use when querying boards, exporting data, viewing teams/organizations, or automating Miro workflows from the terminal.
- References files that are not bundled: references/miro-cli-commands.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 12 top-level sections: this looks like several domains in one skill
clawhub · ↓ 902 ★ 1
Generatorwill not run
Build or initialize team-style project context directories for context engineering. Use when the user says “构建/初始化项目上下文”, “针对该项目构建上下文”, **or** in English phrases like “build/initia
- References files that are not bundled: references/entrypoints.md
- 10 top-level sections: this looks like several domains in one skill
- The response is described with custom markup (30 tags): a typed call is more reliable
clawhub · ↓ 879 ★ 1
Integrationwill not run
Felo SuperAgent API: AI conversation with real-time SSE streaming on a persistent LiveDoc canvas. Use when users want SuperAgent chat, continuous conversation, logo/branding design
- References files that are not bundled: url
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 13 top-level sections: this looks like several domains in one skill
clawhub · ↓ 1 616
AnalyzerObsidianwill not run
LLM-maintained knowledge wiki for Obsidian vaults. The LLM does the bookkeeping, you do the curation. Three sub-skills: ingest sources into the wiki, query and synthesize answers,
- References files that are not bundled: skills/llmwiki-ingest/SKILL.md, skills/llmwiki-query/SKILL.md, skills/llmwiki-health/SKILL.md
- 4 referenced file(s) missing: skills/llmwiki-ingest/SKILL.md, skills/llmwiki-query/SKILL.md, skills/llmwiki-health/SKILL.md
- Does not say what the result is
clawhub · ↓ 1 592
Analyzerwill not run
Agent Skills (SKILL.md) builder, auditor, and improver for cross-platform LLM agents.
Use for "skeall", "build a skill", "create skill", "improve skill", "audit skill",
"skill revi
- References files that are not bundled: path
- 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
clawhub · ↓ 1 588