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
Public-safe Mac multi-instance deployment skill for generic OpenClaw-style workspace layout, boundary notes, sample config, and pack validation.
- References files that are not bundled: references/instances.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 1 referenced file(s) missing: references/instances.md
clawhub · ↓ 830
Analyzerwill not run
Quick BI-SmartQ skill with multiple data analysis capabilities:
1. **File Q&A**: Upload Excel/CSV files for intelligent analysis via Quick BI API
2. **Dataset Q&A**: Natural langua
- References files that are not bundled: path, ..., references/common/copy_skill_config_zh.png
- 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
clawhub · ↓ 940
Analyzerwill not run
Comprehensive BubbleTea TUI code review for terminal applications. Use when reviewing charmbracelet/bubbletea, lipgloss, bubbles, or Wish SSH code; optionally reviews each area con
- References files that are not bundled: ../review-verification-protocol/SKILL.md, ../go-code-review/SKILL.md, ../bubbletea-code-review/SKILL.md
- 13 top-level sections: this looks like several domains in one skill
- 5 referenced file(s) missing: ../review-verification-protocol/SKILL.md, ../go-code-review/SKILL.md, ../bubbletea-code-review/SKILL.md
clawhub · ↓ 852
IntegrationWordwill not run
专业级智能 PPT 全生命周期创作与增强套件。支持通过 yoo-ai API 自动生成、编辑与美化 PPT。当需要执行以下任务时使用此 Skill:(1) 【多源生成】:将简单主题、结构化大纲、本地文件(.docx, .txt)或 AI 编码项目(架构分析)转化为专业 PPT;(2) 【专家流】:需要“先审阅大纲、后生成内容”的高质量创作流程,支持对大纲进行
- References files that are not bundled: 链接
- 1 referenced file(s) missing: 链接
- Does not say what the result is
clawhub · ↓ 852
Generatorwill not run
WeChat Official Account article writing assistant. Guides users through a complete multi-phase workflow: smart entry detection, requirements clarification, market research, deep di
- References files that are not bundled: references/ai-review-articles/, references/ai-opinion-articles/
- 2 referenced file(s) missing: references/ai-review-articles/, references/ai-opinion-articles/
- Does not say what the result is
clawhub · ↓ 852
Analyzerwill not run
Route user tasks to the most relevant skills using a layered taxonomy, risk model, and minimum-necessary-loading strategy. Use when deciding which skill to load, when multiple skil
- References files that are not bundled: references/routing-decisions.jsonl
- 20 top-level sections: this looks like several domains in one skill
- The skill tells the model to perform an irreversible action with no human approval
clawhub · ↓ 806
Procedurewill not run
Use this skill when the user wants to design, scope, or refine a Buddhist, spiritual, or cyber-chanting AI product. It is especially useful for local-first ritual companions, merit
- References files that are not bundled: assets/meritloop-hero.svg, assets/meritloop-storyboard.svg, assets/meritloop-languages.svg
- 3 referenced file(s) missing: assets/meritloop-hero.svg, assets/meritloop-storyboard.svg, assets/meritloop-languages.svg
- Does not say what the process needs to start
clawhub · ↓ 829
Analyzerwill not run
Run a structured adversarial multi-agent review loop on any significant document. Spawns parallel Opus reviewers with different critical lenses, collects structured redlines, then
- References files that are not bundled: references/model-notes.md
- The response is described with custom markup (4 tags): a typed call is more reliable
- 1 referenced file(s) missing: references/model-notes.md
clawhub · ↓ 853
IntegrationStripeNotionwill not run
Google Apps Script API integration with managed OAuth. Manage Apps Script projects, deployments, versions, and execute script functions.
Use this skill when users want to create or
- References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.md
- 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 · ↓ 973
Integrationwill not run
友盟小程序推广链接管理技能,支持通过 umeng-cli call 调用友盟 OpenAPI(gateway.open.umeng.com)的 2 个推广接口(1 个写入 + 1 个只读),与旧 uapp-campaign 能力完全等价的 CLI 化。覆盖推广链接创建、活动/渠道清单查询。当用户需要为小程序创建推广链接、查询推广活动列表或推广渠道列表时使用。
- References files that are not bundled: ../../../umeng-cli/SKILL.md, scripts/campaign.py
- 16 top-level sections: this looks like several domains in one skill
- 2 referenced file(s) missing: ../../../umeng-cli/SKILL.md, scripts/campaign.py
clawhub · ↓ 850
Integrationwill not run
友盟应用性能监控(U-APM)数据查询技能,支持通过 umeng-cli call 调用友盟 APM OpenAPI(apm.openapi.umeng.com)的 8 个只读查询接口,涵盖今日/历史稳定性、启动性能、网络性能、原生页面、H5 页面、分钟级网络与稳定性数据。当用户需要查询应用崩溃率、启动耗时、网络请求性能、页面加载性能或分钟级实时数据时使用。
- References files that are not bundled: ../../../umeng-cli/SKILL.md, ../../../umeng-cli/reference/openapi/uapm.md
- 11 top-level sections: this looks like several domains in one skill
- 2 referenced file(s) missing: ../../../umeng-cli/SKILL.md, ../../../umeng-cli/reference/openapi/uapm.md
clawhub · ↓ 850
Referencewill not run
Fetch, aggregate, and rank AI/tech news from multiple sources listed in `workspace/source.md`. Use when the user asks to get AI news, tech news digest, aggregate news, latest news
- References files that are not bundled: URL
- 1 referenced file(s) missing: URL
- Does not say what the process needs to start
clawhub · ↓ 851
ProcedurePostgreSQLwill not run
为 IOC(智能运营中心)生成智能巡检报告。自动分析设备状态、报警记录、能耗数据,生成专业的巡检日报/周报。支持连接 PostgreSQL 数据库读取实时数据,输出 Markdown/HTML 报告。适用于物业管理、商业综合体、工业园区等场景。
- References files that are not bundled: scripts/analyze.py, references/ioc-knowledge.md, references/db-schema.md
- 3 referenced file(s) missing: scripts/analyze.py, references/ioc-knowledge.md, references/db-schema.md
- Does not say what the result is
clawhub · ↓ 827
GeneratorGitHubwill not run
Expert README writing skill for open source projects. Use this skill whenever the user wants to write, improve, or review a README for any open source repository. Triggers include:
- References files that are not bundled: CONTRIBUTING.md, LICENSE
- 2 referenced file(s) missing: CONTRIBUTING.md, LICENSE
- Does not say what the result is
clawhub · ↓ 804
Analyzerwill not run
Automatically detects and heals locked OpenClaw session files. Use when you see "session file locked" errors or models failing due to lock timeouts. Clears stale locks and recovers
- References files that are not bundled: references/lock-recovery.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 1 referenced file(s) missing: references/lock-recovery.md
clawhub · ↓ 782
Procedurewill not run
A comprehensive operating system for AI Product Management. Use this skill when planning, prototyping, evaluating, or launching AI-native products. It provides agentic workflows fo
- References files that are not bundled: scripts/pm_feedback_loop.py
- 1 referenced file(s) missing: scripts/pm_feedback_loop.py
- Does not say what the result is
clawhub · ↓ 875
Referencewill not run
AI 科技新闻日报生成器。自动抓取最新 AI 行业动态,生成结构化中文日报。支持自定义关注领域、关键词过滤和多种输出格式。Use when user asks for AI news digest, tech news summary, or daily AI industry update.
- References files that are not bundled: {url}
- 1 referenced file(s) missing: {url}
- Does not say what the result is
clawhub · ↓ 849
Procedurewill not run
- References files that are not bundled: docs/block_layout.md
- 1 referenced file(s) missing: docs/block_layout.md
- Does not say what the result is
clawhub · ↓ 848
GeneratorTelegramwill not run
Teamgram Server architecture guide for building Telegram-compatible backends. Use when designing service topology, implementing MTProto services, or self-hosting Teamgram. Covers s
- References files that are not bundled: specs/architecture.md, specs/dependencies-and-runtime.md, references/tuning.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 · ↓ 825
Analyzerwill not run
Act as a strategic consultant to analyze companies and identify competitive moats using Xiao Jing(肖璟)'s "5 Factors + 4 Relations" framework in his book How to Quickly Understand an
- References files that are not bundled: references/01_factors_detailed.md, references/02_relations_detailed.md
- 2 referenced file(s) missing: references/01_factors_detailed.md, references/02_relations_detailed.md
- Does not say what the result is
clawhub · ↓ 802
Analyzerwill not run
Use when you want to set up, maintain, or review a Claude Code style layered memory workflow, including `CLAUDE.md` rules, session memory, durable memory, and promotion of stable l
- References files that are not bundled: testing-policy.md
- 12 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: testing-policy.md
clawhub · ↓ 847
Generatorwill not run
Create detailed creative briefs for KOL and influencer partnerships covering product positioning, dos and don'ts, deliverables, and timeline expectations. Use when onboarding TikTo
- References files that are not bundled: references/output-template.md, assets/brief-quality-checklist.md, references/positioning-angles-guide.md
- 4 referenced file(s) missing: references/output-template.md, assets/brief-quality-checklist.md, references/positioning-angles-guide.md
- Does not say what the result is
clawhub · ↓ 874
GeneratorCloudflarewill not run
Build, deploy, and design micro apps and websites on Cloudflare Workers. Scaffolds from templates (React Router + Hono, Next.js, Astro, Remix), deploys, sets up custom domains, pro
- References files that are not bundled: scripts/provision-*.sh
- 14 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: scripts/provision-*.sh
clawhub · ↓ 823
Generatorwill not run
Build ORBCAFE chat and copilot experiences with AgentPanel, StdChat, CopilotChat, ChatMessage typing flow, and AgentUICardHooks using official examples patterns. Use for full-page
- References files that are not bundled: examples/app/chat/ChatExampleClient.tsx, examples/app/copilot/CopilotExampleClient.tsx
- 2 referenced file(s) missing: examples/app/chat/ChatExampleClient.tsx, examples/app/copilot/CopilotExampleClient.tsx
- No condition that starts the skill
clawhub · ↓ 800
Procedurewill not run
Research the architecture of a codebase or system. Reads source code, finds external context, explains design decisions, and produces ELK diagrams. Use when asked to understand, ex
- References files that are not bundled: system-overview.svg, request-flow.svg
- 2 referenced file(s) missing: system-overview.svg, request-flow.svg
- Does not say what the result is
clawhub · ↓ 934