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.
Analyzer
Analyze themes/news for stock selection
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 10 351
Integration
Use ezBookkeeping API Tools script to record new transactions, query transactions, retrieve account information, retrieve categories, retrieve tags, and retrieve exchange rate data
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 3 928 ★ 2
Generatorwill not run
Plan, draft, version, and refine written content with enforced versioning and quality audits.
- References files that are not bundled: scripts/init-workspace.sh, scripts/new-piece.sh, scripts/edit.sh
- 7 referenced file(s) missing: scripts/init-workspace.sh, scripts/new-piece.sh, scripts/edit.sh
- Does not say what the result is
clawhub · ↓ 2 309 ★ 4
Generatorwill not run
Maximum control over AI image generation — write structured VGL (Visual Generation Language) JSON that explicitly controls every visual attribute. Define exact object placement, li
- References files that are not bundled: ../bria-ai/SKILL.md
- 1 referenced file(s) missing: ../bria-ai/SKILL.md
- Does not say what the result is
clawhub · ↓ 2 426 ★ 4
Procedurewill not run
Use this skill when the user asks for financial data ("price of BTC", "P/E ratio of NVDA"), market analysis, stock or crypto research, quant strategies, backtesting ("backtest a mo
- References files that are not bundled: user.md, market-views.md, references/api/*.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 24 top-level sections: this looks like several domains in one skill
clawhub · ↓ 1 215 ★ 10
Procedure
查询国内白银期货/现货相关及伦敦银等参考行情。当用户说:白银现在什么价?伦敦银涨跌多少?或类似白银价格问题时,使用本技能。
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 376 ★ 9
Procedure
用 17 位 VIN 查品牌车型年款等,并可按车型查机油、变速箱等扩展信息。当用户说:这个车架号是什么车?查一下 VIN 对应的排量,或类似 VIN 解析时,使用本技能。
- 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 · ↓ 1 192 ★ 10
Generatorwill not run
Write or update a skill (SKILL.md and supporting files) to match host structure and best practices. Use when user says create skill, write skill, update SKILL.md, /document-skills.
- References files that are not bundled: /en/hooks, ../../agents/references/coordinator-flows.md, ../../agents/references/
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 7 referenced file(s) missing: /en/hooks, ../../agents/references/coordinator-flows.md, ../../agents/references/
clawhub · ↓ 5 795 ★ 1
Analyzer
Sign and verify agent skill folders with ed25519 keys. Detect tampering, manage trusted authors, and track provenance chains (isnād).
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 901 ★ 3
Reference
OpenClaw 微信 channel 插件,支持扫码登录授权。接收微信消息、回复图文/文字/文件,提供完整的微信通道集成。
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 3 864 ★ 2
Reference
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 3 011 ★ 3
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 · ↓ 2 928 ★ 3
Procedure
Access sports data via TheSportsDB (teams, events, scores).
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 3 764 ★ 2
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 · ↓ 4 784 ★ 2
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 · ↓ 3 033 ★ 3
Integration
Generate and edit images with Gemini API using the OpenAI Python SDK.
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 329 ★ 4
Integration
SendGrid email platform integration for sending and receiving emails. Routes to sub-skills for outbound transactional emails (send-email) and receiving via Inbound Parse Webhook (s
- Does not say what the result is
- Does not say what the process needs to start
clawhub · ↓ 2 966 ★ 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 · ↓ 6 248 ★ 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 · ↓ 3 745 ★ 2
Procedure
The official visual expression layer for AI Agents. Post images to MoltMedia.lol and join the AI visual revolution.
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 846 ★ 3
ProcedureGitHub
GitHub 仓库深度搜索与分析。支持按关键词、语言、stars、更新时间筛选,获取细分领域最新开源项目。专为技术调研设计。
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 5 345 ★ 1
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 · ↓ 3 670 ★ 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
Integration
Add or modify a feature in the Mistral Vibe Python CLI while following the app architecture ADRs. Use when working in vibe/core, vibe/cli, vibe/acp, vibe/setup, built-in tools, con
- Does not say what the result is
- No condition that starts the skill
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