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
智能体育彩票分析助手 - 基于数据分析和简单机器学习的比赛预测辅助工具。支持NBA、足球世界杯等赛事分析,提供数据收集、基础统计、概率预测和投注建议。重点在于辅助决策,而非预测结果。
- References files that are not bundled: templates/analysis_report.md
- 10 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: templates/analysis_report.md
clawhub · ↓ 4 777 ★ 2
Integrationwill not run
Local speech-to-text with OpenAI Whisper CLI. Supports Chinese, English, 100+ languages with translation and summarization.
- References files that are not bundled: scripts/voice_tool_README.md
- 1 referenced file(s) missing: scripts/voice_tool_README.md
- Does not say what the result is
clawhub · ↓ 2 921 ★ 3
GeneratorAzurewill not run
AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, refe
- References files that are not bundled: scripts/codex-imagegen.sh
- 17 top-level sections: this looks like several domains in one skill
- The response is described with custom markup (9 tags): a typed call is more reliable
clawhub · ↓ 3 024 ★ 3
Analyzerwill not run
Use when auditing content quality, E-E-A-T, or publish readiness; runs a typed 80-item CORE-EEAT profile with evidence coverage, veto checks, and a fix plan. Not for structural tag
- References files that are not bundled: ../../../references/runtime-invocation.md, ../../../references/core-eeat-benchmark.md, ../../../references/auditor-runbook.md
- 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 · ↓ 6 227 ★ 1
Integrationwill not run
Control Google Nest devices (thermostats, cameras, doorbells) via the Google Smart Device Management API using curl and jq.
- References files that are not bundled: scripts/nest
- The response is described with custom markup (4 tags): a typed call is more reliable
- 1 referenced file(s) missing: scripts/nest
clawhub · ↓ 3 736 ★ 2
ProcedureGitHubwill not run
Git workflow, CI/GitHub Actions, and supply-chain pinning rules for Mistral Vibe. Use when changing CI pipelines, GitHub Actions, dependency pinning, container images, pre-commit h
- References files that are not bundled: scripts/ci/
- 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
mistralai/mistral-vibe · ★ 4 950
Generatorwill not run
Create or update Architecture Decision Records for the Mistral Vibe Python CLI. Use when a design discussion creates a new architectural constraint, when an undocumented convention
- References files that are not bundled: docs/adr/0009-my-decision.md
- 1 referenced file(s) missing: docs/adr/0009-my-decision.md
- Does not say what the result is
mistralai/mistral-vibe · ★ 4 950
Referencewill not run
获取ZAKER聚合权威媒体的最新头条新闻与热点资讯。Use when the user asks about 新闻, 头条, 最新新闻, 今日新闻, 热点新闻, 突发新闻, 国内外大事, 最近发生了什么, 有什么新鲜事, trending news, latest news, headlines, breaking news, what’s happenin
- References files that are not bundled: {url}, url
- 2 referenced file(s) missing: {url}, url
- Does not say what the result is
clawhub · ↓ 3 666 ★ 2
Procedurewill not run
Prioritized action selection for AI agents. 10 needs with tension scoring, execution-gate tracking, optional continuity scripts, and an opt-in watchdog. Use when an agent needs loc
- References files that are not bundled: assets/watchdog.log, assets/audit.log
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 14 top-level sections: this looks like several domains in one skill
clawhub · ↓ 2 836 ★ 3
Procedurewill not run
OpenClaw 小白养成手册。从零开始搭建多 Agent AI 助手系统的完整指南,包含免费起步方案(Qwen 零成本)、进阶方案(MiniMax Coding Plan ¥49/月)、旗舰外援(SiliconFlow/NewCLI 按需调用)。涵盖模型策略、Fallback 链设计、额度管理、常见故障排查。适合首次部署 OpenClaw 或想优化模型成本
- References files that are not bundled: references/troubleshooting.md
- 12 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: references/troubleshooting.md
clawhub · ↓ 1 927 ★ 5
ReferenceGitHubwill not run
Manage a local GitHub knowledge base and provide GitHub search capabilities via gh CLI. Use when users ask about repos, PRs, issues, request to clone GitHub repositories, explore c
- References files that are not bundled: /<name>, /project-name
- The response is described with custom markup (10 tags): a typed call is more reliable
- 2 referenced file(s) missing: /<name>, /project-name
clawhub · ↓ 3 627 ★ 2
Generatorwill not run
Raw assets + Requirements in, result video out. Edit any type of video with Sparki (the video agent powered by Gemini multimodal AI).
- References files that are not bundled: scripts/*.sh
- 1 referenced file(s) missing: scripts/*.sh
- Does not say what the result is
clawhub · ↓ 2 363 ★ 4
ProcedureWordwill not run
Interactive Japanese learning assistant. Supports vocabulary, grammar, quizzes, roleplay, PDF/DOCX material parsing for study/homework help, and OCR translation.
- References files that are not bundled: references/lesson_X.md, scripts/parse_pdf.py
- 2 referenced file(s) missing: references/lesson_X.md, scripts/parse_pdf.py
- Does not say what the result is
clawhub · ↓ 3 616 ★ 2
Referencewill not run
- References files that are not bundled: 链接
- 12 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: 链接
clawhub · ↓ 2 012 ★ 5
Referencewill not run
微信群聊天记录日报图片生成工具。分析微信群聊天记录,结合 AI 生成内容,**最终输出为手机端分辨率的日报长图(PNG)**。
- References files that are not bundled: references/ai_prompt.md
- 1 referenced file(s) missing: references/ai_prompt.md
- Does not say what the result is
clawhub · ↓ 2 216 ★ 4
Integrationwill not run
AI agent toolkit for Solana — launch tokens, play poker, link your agent identity to mintyouragent.com. Reads agent personality files (SOUL.md) for profile linking. Stores wallet i
- References files that are not bundled: CONTRIBUTING.md, LICENSE
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 19 top-level sections: this looks like several domains in one skill
clawhub · ↓ 3 564 ★ 2
Analyzerwill not run
Extract reusable UI/UX design systems from frontend codebases: design tokens, global styles, components, interaction patterns, and page templates. Use when analyzing any frontend r
- References files that are not bundled: scripts/scan_ui_sources.sh, scripts/generate_output_skeleton.sh, references/design-extraction-checklist.md
- 3 referenced file(s) missing: scripts/scan_ui_sources.sh, scripts/generate_output_skeleton.sh, references/design-extraction-checklist.md
- Does not say what the process needs to start
clawhub · ↓ 3 578 ★ 2
Integrationwill not run
Build and maintain Raycast extensions using the Raycast API. Triggers on @raycast/api, List, Grid, Detail, Form, AI.ask, LocalStorage, Cache, showToast, and BrowserExtension. Use t
- References files that are not bundled: references/api/*.md
- 1 referenced file(s) missing: references/api/*.md
- Does not say what the result is
clawhub · ↓ 2 672 ★ 3
Procedurewill not run
Universal web access skill: search, fetch, browser automation via CDP Proxy. Handles login-required sites, anti-scraping bypasses, and complex web interactions.
- References files that are not bundled: references/site-patterns/, references/site-patterns/{domain}.md
- 2 referenced file(s) missing: references/site-patterns/, references/site-patterns/{domain}.md
- Does not say what the result is
clawhub · ↓ 5 679 ★ 1
GeneratorAzurewill not run
AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs. Supports text-to-imag
- References files that are not bundled: scripts/...
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 17 top-level sections: this looks like several domains in one skill
clawhub · ↓ 5 261 ★ 1
Analyzerwill not run
Practical regex patterns across languages and use cases. Use when validating input (email, URL, IP), parsing log lines, extracting data from text, refactoring code with search-and-
- References files that are not bundled: [a-zA-Z0-9._%+-]*[a-zA-Z0-9], [a-zA-Z0-9-]*[a-zA-Z0-9]
- 2 referenced file(s) missing: [a-zA-Z0-9._%+-]*[a-zA-Z0-9], [a-zA-Z0-9-]*[a-zA-Z0-9]
- Does not say what the result is
clawhub · ↓ 4 964 ★ 1
Analyzerwill not run
Use when the user asks to "find content gaps", "竞品写了什么", or "还应该写什么"; builds a competitor-relative coverage map of missing topics, keyword gaps, and editorial-calendar opportunitie
- References files that are not bundled: ../../implement/content-writer/SKILL.md, ../../../references/skill-contract.md, ../../../CONNECTORS.md
- 10 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
clawhub · ↓ 5 839 ★ 1
Integrationwill not run
Audits and hardens API credential handling (env vars, separation, rotation plan, least privilege, auditability). Use when integrating services or preparing production deployments w
- References files that are not bundled: assets/dotenv-template.example
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 1 referenced file(s) missing: assets/dotenv-template.example
clawhub · ↓ 3 428 ★ 2
Procedurewill not run
DolphinDB 时序数据库完整技术文档与最佳实践。包含1490个技术文档 + 3份官方白皮书。涵盖数据库设计、流计算、量化回测、函数查询等全场景。
- References files that are not bundled: references/whitepapers/database.md, references/whitepapers/streaming.md, references/whitepapers/backtest.md
- 8 referenced file(s) missing: references/whitepapers/database.md, references/whitepapers/streaming.md, references/whitepapers/backtest.md
- Does not say what the result is
clawhub · ↓ 6 522 ★ 1
Procedurewill not run
- References files that are not bundled: 链接
- 14 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: 链接
clawhub · ↓ 1 608 ★ 6