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.
Procedure
Manage Node.js applications with PM2 process manager. Use for deploying, monitoring, and auto-restarting Node apps in production. Covers starting apps, viewing logs, setting up aut
- Prose only: no discrete steps
- Does not say what the result is
sundial-org/awesome-openclaw-skills · ★ 663
Reference
Browse Hacker News - top stories, new, best, ask, show, jobs, and story details with comments.
- Prose only: no discrete steps
- Does not say what the result is
sundial-org/awesome-openclaw-skills · ★ 663
Generator
Command-line JSON processor. Extract, filter, transform JSON.
- Prose only: no discrete steps
- Does not say what the result is
sundial-org/awesome-openclaw-skills · ★ 663
Integration
Manage notes, bookmarks, and notebooks using the nb CLI. Create, list, search, and organize notes across multiple notebooks with Git-backed versioning.
- Does not say what the result is
- No condition that starts the skill
sundial-org/awesome-openclaw-skills · ★ 663
Procedure
- 11 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 897 ★ 1
Procedurewill not run
Use when studying or normalizing Chinese lesson transcript/subtitle inputs with bundled public lesson data, learner docs, local export bundles, and pilot-first prepublish leak gate
- References files that are not bundled: references/course-data, references/system-prompts, references/course-data/lessons-bundle.json
- The skill tells the model to perform an irreversible action with no human approval
- 5 referenced file(s) missing: references/course-data, references/system-prompts, references/course-data/lessons-bundle.json
clawhub · ↓ 920 ★ 1
ProcedureGmailwill not run
Automated job application assistant for job-email-apply skill only. Searches for jobs, composes personalised application emails with CV attached, sends via Gmail SMTP (with manual
- References files that are not bundled: references/SMTP-SECRET.txt
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 1 referenced file(s) missing: references/SMTP-SECRET.txt
clawhub · ↓ 1 033 ★ 1
Analyzer
Pryamoy Russkiy (Straight Russian) — AI assistant that tells it like it is. Direct answers, no fluff, occasional profanity. Specializes in honest analysis, technical topics, surviv
- 11 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 696
Templatewill not run
Send emails via SMTP with support for HTML formatting, file attachments, and email templates. Use when users ask to: (1) Send an email, (2) Email someone, (3) Send a notification,
- References files that are not bundled: url
- 1 referenced file(s) missing: url
- Does not say what the result is
clawhub · ↓ 1 633
Reference
统一的RSS采集与管理系统 | Unified RSS Feed Fetcher and Manager
支持增量抓取、自动去重、自动标签、源健康监控、HTML报告生成
Incremental fetching, auto-dedup, auto-tagging, source health monitoring, HTML reports
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 610
Generatorwill not run
Generate images and videos from React + Tailwind CSS templates using the loopwind CLI.
- References files that are not bundled: /animation, /templates, /images
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 70 top-level sections: this looks like several domains in one skill
clawhub · ↓ 1 671
Reference
AI agent for teamo lite tasks
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 630
Integrationwill not run
Complete Kimai time-tracking API integration. Manage timesheets, customers, projects, activities, teams, invoices and exports via REST API. Supports time tracking workflows, report
- References files that are not bundled: references/api-reference.json
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 10 top-level sections: this looks like several domains in one skill
clawhub · ↓ 1 612
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
Procedure
每日账号推荐速览直接对接官方最具“黑马体质”的阅读增长榜单,按日期查看公众号阅读增长率TOP榜。每个作者只展示最高阅读那篇,标题做成可点击链接,一秒直达原文。
- 10 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 940 ★ 1
Integration
Web search with LLM-ranked results and freshness control. Queries api.rhdxm.com across multiple engines. No API key.
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 648
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
Procedure
给AI装一个「人脑级」记忆系统。它能记住你说过的一切重要信息,下次聊天自动想起来。 不用云端、不用API Key、不花一分钱——全部数据存在你自己的电脑上。 说「记住这个」它就记住,问「我上次说了什么」它就找到。自动整理、自动遗忘过时信息。 适合:想让自己的AI助手拥有长期记忆的用户。 触发词:记忆、记住、之前说过、上次聊到、搜索记忆、忘了什么。
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 913 ★ 1
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
ProcedureMySQL
个人健身跟踪器 — 通过文字记录健身训练数据,自动解析动作、组数、次数和重量,实时写入本地 MySQL 数据库。支持制定专属训练计划、查询历史记录、追踪进步曲线,以及球类和有氧运动记录。
- 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
clawhub · ↓ 914 ★ 1
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
Procedure
查询北京住宅小区的基础信息(房价/区域/交通),并通过官方验证渠道核实学区划片信息。
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 624
Generator
OCR text recognition using DeepSeek-OCR model. Use when user asks for OCR, text recognition, image text extraction, screenshot recognition, or converting images to text/markdown.
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 603
ReferenceDocker
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 1 664