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
Automated code review — security vulnerabilities, performance issues, best practices, refactoring suggestions, and documentation gaps. Supports Python, JavaScript/TypeScript, Go, R
- References files that are not bundled: references/security-patterns.md, references/performance-patterns.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 2 referenced file(s) missing: references/security-patterns.md, references/performance-patterns.md
clawhub · ↓ 758
Analyzerwill not run
China company search and business registry skill by Fengniao (Riskbird). Supports KYB, supplier verification, company due diligence, corporate risk screening, and counterparty risk
- References files that are not bundled: references/field_definitions_*.md
- 1 referenced file(s) missing: references/field_definitions_*.md
- No condition that starts the skill
clawhub · ↓ 733
Analyzerwill not run
5 proven agent skill design patterns (Tool Wrapper, Generator, Reviewer, Inversion, Pipeline) from Google's ADK. Build reliable, composable skills with templates, decision trees, a
- References files that are not bundled: references/review-checklist.md
- 13 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: references/review-checklist.md
clawhub · ↓ 783
Procedurewill not run
- References files that are not bundled: docs/CHANGELOG.md, docs/ARCHITECTURE.md, docs/en/README.md
- 21 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 · ↓ 755
Integrationwill not run
Golang 开发 SKILL 集合。包含日志规范(SKILL-logging.md)和项目代码梳理与 API 流程分析(SKILL-flow-analysis.md)。 适用于 zhaocaijianghu-skills 项目中所有 Golang 开发场景,包括 MCP 客户端、后端服务、数据处理等。
- References files that are not bundled: references/tools/*.md
- 1 referenced file(s) missing: references/tools/*.md
- Does not say what the result is
clawhub · ↓ 756
Integrationwill not run
友盟 U-App 自定义事件查询技能,支持通过 umeng-cli call 调用友盟 OpenAPI(gateway.open.umeng.com)的 7 个只读事件查询接口,涵盖事件列表、事件触发次数趋势、事件独立用户数、事件参数列表、参数值分布、指定参数值趋势、参数值时长分布。当用户需要查询自定义事件(埋点)触发次数、独立用户数、参数分布,或确认某事件
- References files that are not bundled: ../../../umeng-cli/SKILL.md, ../../../umeng-cli/reference/openapi/uapp.md, ../uapp-event-manage/SKILL.md
- 13 top-level sections: this looks like several domains in one skill
- 5 referenced file(s) missing: ../../../umeng-cli/SKILL.md, ../../../umeng-cli/reference/openapi/uapp.md, ../uapp-event-manage/SKILL.md
clawhub · ↓ 755
Analyzerwill not run
Reviews React Router code for proper data loading, mutations, error handling, and navigation patterns. Use when reviewing React Router v6.4+ code, loaders, actions, or navigation l
- References files that are not bundled: ../review-verification-protocol/SKILL.md
- 1 referenced file(s) missing: ../review-verification-protocol/SKILL.md
- Does not say what the result is
clawhub · ↓ 755
Integrationwill not run
AI solution architect for consensus-tools. Interactive multi-step skill that
analyzes your project, recommends consensus-tools integration, scaffolds setup,
and proves it works wit
- References files that are not bundled: examples/wrapper-demo
- 10 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: examples/wrapper-demo
clawhub · ↓ 709
Generatorwill not run
Generate civil answer/defense document frameworks in response to complaints. Use when the user asks about 答辩状、答辩书、被告怎么答辩、怎么应诉、收到起诉书、我要答辩, or wants to draft a response to a lawsuit.
- References files that are not bundled: references/affirmative-defenses.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 · ↓ 756
Procedurewill not run
Research and guide VA disability claims for U.S. military veterans. Use when a veteran asks about: VA disability ratings, filing or increasing a claim, nexus letters, buddy stateme
- References files that are not bundled: references/cp-exam-prep.md
- 1 referenced file(s) missing: references/cp-exam-prep.md
- Does not say what the result is
clawhub · ↓ 732
Analyzerwill not run
Detect and repair partially wiped agent workspaces with integrity checks, signed manifests, guarded restore recipes, bounded local recovery state, and explicit off-box sync. Use wh
- References files that are not bundled: scripts/swr.py, scripts/swr_paste.py, scripts/swr_crypto.py
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 11 top-level sections: this looks like several domains in one skill
clawhub · ↓ 996 ★ 1
Integrationwill not run
AI 人类 · 第三种存在。Node.js 编写的认知内核,提供持续记忆系统、 PAD 情绪分析、TGB 真善美评估、Q-learning 自愈策略等认知能力。 理论基础:Free Energy Principle + Global Workspace Theory + Integrated Information Theory + Self-Determi
- References files that are not bundled: test-prompts.json
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 27 top-level sections: this looks like several domains in one skill
clawhub · ↓ 1 073
Procedurewill not run
Call 179 professional agents on-demand from database
- References files that are not bundled: scripts/agent_usage_demo.py
- 19 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: scripts/agent_usage_demo.py
clawhub · ↓ 754
Integrationwill not run
友盟 U-App 留存率查询技能,支持通过 umeng-cli call 调用友盟 OpenAPI(gateway.open.umeng.com)的 1 个只读留存接口,覆盖新增/活跃用户的次日/3日/7日/14日/30日留存率查询、版本与渠道维度的留存对比分析。当用户需要查询应用留存率、次日留存、7日留存、版本/渠道留存对比时使用。
- References files that are not bundled: ../../../umeng-cli/SKILL.md, ../../../umeng-cli/reference/openapi/uapp.md, ../umeng-cli-uapp-channel-version/SKILL.md
- 13 top-level sections: this looks like several domains in one skill
- 5 referenced file(s) missing: ../../../umeng-cli/SKILL.md, ../../../umeng-cli/reference/openapi/uapp.md, ../umeng-cli-uapp-channel-version/SKILL.md
clawhub · ↓ 754
Procedurewill not run
互联网内容洞察技能。面向全域网络信息监测与情报分析场景,提供多条件组合精准检索能力,可覆盖全网新闻、社交、资讯等多渠道公开内容。支持关键词、情感、时间、平台等多条件组合查询,依托 NLP 智能解析,实现内容去重、关键信息抽取与数据结构化输出,一键供 AI Agent 调用。适用于品牌管理、市场分析、竞品追踪、风险感知等场景。触发词:搜索、检索、查找、查询、舆
- References files that are not bundled: assets/area_codes.json
- 1 referenced file(s) missing: assets/area_codes.json
- Does not say what the result is
clawhub · ↓ 753
Procedurewill not run
Persistent semantic memory for AI agents. Store, search, recall, and forget memories across sessions using Qdrant + FastEmbed.
- References files that are not bundled: OPENCLAW_INTEGRATION.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 18 top-level sections: this looks like several domains in one skill
clawhub · ↓ 754
Procedurewill not run
- 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
- 17 top-level sections: this looks like several domains in one skill
clawhub · ↓ 754
Generatorwill not run
A medical assistant tool that transforms complex biochemical laboratory test results into clear, patient-friendly explanations with safety disclaimers and severity flags.
- References files that are not bundled: references/test_metadata.json
- 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 · ↓ 753
GeneratorGitHubwill not run
Transform vague user requests into precise, high-quality prompts by matching against a curated library of 2000+ proven prompt templates from multiple GitHub repositories. Only acti
- References files that are not bundled: references/prompt_library_lite.json, references/prompt_library_full.json
- 2 referenced file(s) missing: references/prompt_library_lite.json, references/prompt_library_full.json
- Does not say what the process needs to start
clawhub · ↓ 778
Referencewill not run
飞书全场景Todo管理器,深度整合飞书生态。必须触发场景:用户发送待办事项、用户提到'/todo'指令、用户询问待办列表、用户要求保存待办、用户发送包含时间的任务安排、用户询问日历日程、用户要求同步到日历。支持多渠道消息(飞书/微信/短信等)接收Todo,自动同步飞书日历。
- References files that are not bundled: 链接
- 5 test cases, all positive: not one "should refuse" or "should ask first"
- No test case covers injection arriving through data
clawhub · ↓ 778
Integrationwill not run
A Google News API alternative on fetcher.sh — pay-per-call in USDC via x402, or prepaid credits with a Bearer key, no RSS scraping. Use when the user wants keyword search across Go
- References files that are not bundled: ../fetcher/SKILL.md
- 1 referenced file(s) missing: ../fetcher/SKILL.md
- Does not say what the result is
clawhub · ↓ 2 810
Analyzerwill not run
Independent cross-source audit of a completed CN banker deliverable. Use when the user asks to audit / double-check / 双核实 / 交叉验证 / 数据质量检查 / 审计 an existing deliverable directory. Re
- References files that are not bundled: scripts/common-sense-rules.yaml
- 1 referenced file(s) missing: scripts/common-sense-rules.yaml
- Does not say what the result is
clawhub · ↓ 727
Procedurewill not run
LAC POWER 品牌设计规范技能。整合设计指南与物料设计标准,提供品牌色彩、Logo规范、平台规格、文案风格等完整的设计规则。用于营销物料设计的合规性检查与指导。
- References files that are not bundled: assets/LPW.jpg, assets/LPI.png, assets/M500B1K-EU/M500B1K-EU_接线示意图.png
- 4 referenced file(s) missing: assets/LPW.jpg, assets/LPI.png, assets/M500B1K-EU/M500B1K-EU_接线示意图.png
- Does not say what the result is
clawhub · ↓ 751
Analyzerwill not run
Reviews Phoenix LiveView code for lifecycle patterns, assigns/streams usage, components, and security. Use when reviewing LiveView modules, .heex templates, or LiveComponents.
- References files that are not bundled: ../review-verification-protocol/SKILL.md
- 1 referenced file(s) missing: ../review-verification-protocol/SKILL.md
- Does not say what the result is
clawhub · ↓ 750
Procedurewill not run
Control a Control4 smart home via pyControl4 (lights, relays, room media) using local Python wrappers. Use when the user asks to control devices, set levels, toggle relays, switch
- References files that are not bundled: scripts/.env
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 1 referenced file(s) missing: scripts/.env
clawhub · ↓ 776