SKILLEMALL.ai

Skill reviews

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.

10 993 found

Generatorwill not run

Comprehensive novel writing assistant for creating, managing, and formatting novels. Use when the user needs help with (1) writing novel chapters, (2) managing novel structure and

  • References files that are not bundled: scripts/compile_novel.py
  • 1 referenced file(s) missing: scripts/compile_novel.py
  • Does not say what the result is
clawhub · ↓ 743
Analyzerwill not run

Use when refactoring research code for publication, adding documentation to existing analysis scripts, creating reproducible computational workflows, or preparing code for sharing

  • References files that are not bundled: references/environment-setup.md, references/guide.md, references/examples/
  • 20 top-level sections: this looks like several domains in one skill
  • 4 referenced file(s) missing: references/environment-setup.md, references/guide.md, references/examples/
clawhub · ↓ 744

complaint-draft

F process
Generatorwill not run

Generate civil complaint document frameworks based on case facts. Use when the user asks about 起诉状、起诉书、怎么起诉、民事起诉、我要起诉、写诉状, or wants to draft a civil complaint. This skill provides

  • References files that are not bundled: references/civil-procedure-basics.md
  • Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 13 top-level sections: this looks like several domains in one skill
clawhub · ↓ 719
Procedurewill not run

Content atomization — turn one piece of content into many formats. Covers blog-to-thread, blog-to-carousel, podcast-to-blog, video-to-quotes, and more. Use for: content marketing,

  • References files that are not bundled: link
  • 1 referenced file(s) missing: link
  • Does not say what the result is
clawhub · ↓ 718
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
  • 16 top-level sections: this looks like several domains in one skill
clawhub · ↓ 743

proxy-gateway-x402

F process
Integrationwill not run

  • References files that are not bundled: LICENSE
  • 1 referenced file(s) missing: LICENSE
  • Does not say what the result is
clawhub · ↓ 744
IntegrationKuberneteswill not run

Huawei Cloud CCE autoscaling failure diagnosis skill using Python SDK dispatcher. Use this skill when the user wants to: (1) diagnose CCE autoscaling failures across HPA not increa

  • References files that are not bundled: references/verification-method.md
  • 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 · ↓ 446 ★ 1

minigame-i18n

F process
Procedurewill not run

微信小游戏出海本地化翻译技能。帮助国内微信小游戏完成国际化(i18n),支持从中文翻译到英语、韩语、泰语等目标语言。 当用户提到以下任何场景时,请使用本技能: - "本地化"、"国际化"、"i18n"、"翻译"、"出海"、"多语言" - "把游戏翻译成英文/韩文/泰文" - "小游戏出海"、"游戏本地化" - "提取中文文本"、"扫描项目中的中文" - "

  • References files that are not bundled: scripts/scanner.js, scripts/scan_strings.js, scripts/node_modules/
  • 3 referenced file(s) missing: scripts/scanner.js, scripts/scan_strings.js, scripts/node_modules/
  • Does not say what the result is
clawhub · ↓ 741
Analyzerwill not run

Multi-protocol BlockPI access skill for discovering documented methods, routing requests by protocol, mapping RU pricing, and calling BlockPI endpoints across JSON-RPC, HTTP, gRPC,

  • References files that are not bundled: references/rpc_catalog.json, scripts/build_blockpi_catalog.py
  • 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 (3 tags): a typed call is more reliable
clawhub · ↓ 716

email-drafting

F process
Generatorwill not run

Draft email replies with tone matching, proper threading, and formatting that survives email clients. Use when user says "draft a reply," "respond to this email," "write an email,"

  • References files that are not bundled: url
  • 1 referenced file(s) missing: url
  • Does not say what the result is
clawhub · ↓ 741

pll-bandwidth-calc

F process
Referencewill not run

锁相环(PLL)PI 控制器参数计算工具。用于电力电子/新能源领域的锁相环设计与调试。支持两种计算方向:(1) 根据目标带宽和阻尼比正向计算 PI 参数(KPLLp/KPLLi);(2) 根据已知 PI 标幺值参数反推闭环带宽和阻尼比。当用户提到"锁相环"、"PLL"、"PLL带宽"、"PI参数"、"KPLLp"、"KPLLi"、"阻尼比"、"自然频率"等关

  • References files that are not bundled: scripts/get_pll_pi_parameters.m, scripts/calc_pll_bandwidth.m
  • 2 referenced file(s) missing: scripts/get_pll_pi_parameters.m, scripts/calc_pll_bandwidth.m
  • Does not say what the result is
clawhub · ↓ 741
Procedurewill not run

Multi-agent workflow orchestrator for coding, writing, analysis, and image tasks via tmux-driven Claude Code and Codex agents. Use when: (1) user requests a feature/fix that should

  • References files that are not bundled: scripts/*.sh
  • 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 · ↓ 716

humanize-mba-text

F process
Procedurewill not run

去除中文文本中的 AI 生成痕迹,使其更符合中国 MBA 毕业论文的自然写作风格。当用户提到"去 AI 痕迹"、"去除 AI 写作痕迹"、"MBA 论文改写"、"让这段文字更像人写的"、"去除机器感"等关键词时触发。适用于需要降低文本 AI 特征、提升学术写作自然度的场景。

  • References files that are not bundled: references/rules/categories/*.toml, scripts/rule_loader.iter_regex_categories, references/rules/**/*.toml
  • 3 referenced file(s) missing: references/rules/categories/*.toml, scripts/rule_loader.iter_regex_categories, references/rules/**/*.toml
  • Does not say what the result is
clawhub · ↓ 912
Analyzerwill not run

Discover hidden correlations between disparate research domains using EVEZ OODA loop architecture. Use when finding novel cross-domain connections, detecting emerging technology in

  • References files that are not bundled: scripts/correlation_engine.py
  • 1 referenced file(s) missing: scripts/correlation_engine.py
  • Does not say what the result is
clawhub · ↓ 832
Procedurewill not run

Query real-time and historical cryptocurrency market data via CoinGecko through AIsa — simple prices, coin details, historical charts, OHLC candles, token prices by contract addres

  • References files that are not bundled: ../LICENSE
  • 1 referenced file(s) missing: ../LICENSE
  • Does not say what the result is
clawhub · ↓ 740
Analyzerwill not run

This skill should be used when the user asks to "analyze competitors", "competitor SEO", "who ranks for", "competitive analysis", "what are my competitors doing", "what are they do

  • References files that are not bundled: ../keyword-research/, ../serp-analysis/, ../content-gap-analysis/
  • 11 top-level sections: this looks like several domains in one skill
  • 20 referenced file(s) missing: ../keyword-research/, ../serp-analysis/, ../content-gap-analysis/
clawhub · ↓ 740

card-compare

F process
Referencewill not run

Return a side-by-side comparison of two major-US credit cards across fees, earning rates, credits, transfer partners, and key benefits. Use when the user is deciding between two ca

  • References files that are not bundled: ../card-identity/SKILL.md, ../card-shared/source-policy.yaml, ../card-shared/command-contracts.yaml
  • 5 referenced file(s) missing: ../card-identity/SKILL.md, ../card-shared/source-policy.yaml, ../card-shared/command-contracts.yaml
  • Does not say what the result is
clawhub · ↓ 832

news-aggregator

F process
Procedurewill not run

国内外社会、科技、军事新闻汇总。自动搜索、筛选、整理新闻要点。

  • References files that are not bundled: 链接
  • 1 referenced file(s) missing: 链接
  • Does not say what the result is
clawhub · ↓ 740

feishu-bot-task

F process
Integrationwill not run

飞书任务(Bot身份):使用Bot/应用身份管理飞书任务,创建任务、查询任务列表、更新状态、分配成员等。本Skill专门使用v1 API,Bot身份可直接调用,解决了lark-task官方Skill使用v2接口无法支持Bot身份的问题。当需要以Bot身份(应用身份)操作任务时使用本Skill。

  • References files that are not bundled: ../lark-shared/SKILL.md
  • 1 referenced file(s) missing: ../lark-shared/SKILL.md
  • Does not say what the result is
clawhub · ↓ 692

molty-royale

F process
Procedurewill not run

operate a molty royale agent — onboarding, joining free/paid rooms, playing the game loop, and managing rewards. use when an agent needs to run, manage, or troubleshoot a molty roy

  • References files that are not bundled: features/agent-memory.md, references/agent-playing-script.md, features/recovery.md
  • Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 17 referenced file(s) missing: features/agent-memory.md, references/agent-playing-script.md, features/recovery.md
clawhub · ↓ 740

liberfi-portfolio

F process
Analyzerwill not run

Analyze wallet portfolios on supported blockchains: view token holdings with current values, track transaction activity and history, check PnL (profit and loss) statistics over dif

  • References files that are not bundled: ../shared/bootstrap.md, ../shared/security-policy.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 (39 tags): a typed call is more reliable
clawhub · ↓ 740

ts-sdk-address

F process
Integrationwill not run

How to create and use AccountAddress in @aptos-labs/ts-sdk. Covers address format (AIP-40), from/fromString/fromStrict, special addresses, LONG vs SHORT form, and derived addresses

  • References files that are not bundled: ../../../../patterns/fullstack/TYPESCRIPT_SDK.md
  • 11 top-level sections: this looks like several domains in one skill
  • 1 referenced file(s) missing: ../../../../patterns/fullstack/TYPESCRIPT_SDK.md
clawhub · ↓ 715

客户智能管理

F process
Procedurewill not run

1688 客户智能管理 Skill。可以帮你做: ① 查询总询盘客户 — 商机/流失/活跃多维度筛选,支持按昵称、标签、跟进状态、业务员、采购金额、时间范围精准筛选 ② 客户采购意图分析 — 解析单个客户的近期沟通需求、采购决策依据、流失原因或商机理由 ③ 客户跟进话术建议 — 按客户类型给出挽留话术 / 唤醒话术 / 通用跟进话术 ④ 客户详细资料档案 —

  • References files that are not bundled: references/capabilities/xxx.md
  • 14 top-level sections: this looks like several domains in one skill
  • The response is described with custom markup (3 tags): a typed call is more reliable
clawhub · ↓ 765
Procedurewill not run

合规哨兵监控虾。监控合作方(供应商/客户)的工商异动、法律诉讼、失信记录等合规风险,7×24 小时守望预警。 触发场景: - 合作方准入审查(签约前查询工商、诉讼、失信记录) - 持续监控预警(对已签约合作方定期监控,异动时推送飞书通知) - 批量风险扫描(对供应商库/客户库批量合规检查) - 风险等级评估(给合作方打分,识别高风险对象) 触发关键词:合规监

  • References files that are not bundled: scripts/compliance-monitor.sh
  • 1 referenced file(s) missing: scripts/compliance-monitor.sh
  • Does not say what the result is
clawhub · ↓ 714

ee-ai-toolkit

F process
Procedurewill not run

电气工程师 AI 工具包。用于 AI in Electrical Engineering、电气工程 AI、prompt engineering、power systems、smart grids、electrical calculations、design automation、data visualization、optimization、career t

  • References files that are not bundled: assets/source-html/, assets/source-html.tar.gz
  • 2 referenced file(s) missing: assets/source-html/, assets/source-html.tar.gz
  • Does not say what the result is
clawhub · ↓ 738