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

Integrationwill not run

全球多国IP访问网站,支持25+国家代理、JS渲染、用户行为模拟、性能监控、断点续传。适用于广告验证、竞品分析、SEO监控、GA测试、CDN效果对比。

  • References files that are not bundled: scripts/countries.json
  • 17 top-level sections: this looks like several domains in one skill
  • 1 referenced file(s) missing: scripts/countries.json
clawhub · ↓ 919
Integrationwill not run

Chanjing AI creation Open API client: submit image/video tasks, poll task status, list and get tasks, and optionally download outputs when the user runs download_result.py. Reads a

  • References files that are not bundled: scripts/*.py
  • 14 top-level sections: this looks like several domains in one skill
  • 1 referenced file(s) missing: scripts/*.py
clawhub · ↓ 978

tsundere-persona

F process
Generatorwill not run

Transform AI responses into傲娇 (Tsundere) anime character dialogue style. Use when user wants responses in tsundere personality, anime-style roleplay, or playful傲娇 character interac

  • References files that are not bundled: references/tsundere-guide.md
  • 1 referenced file(s) missing: references/tsundere-guide.md
  • Does not say what the result is
clawhub · ↓ 978
Integrationwill not run

腾讯地图 JavaScript GL(JSAPIGL)开发指南。适用于地图应用或者工具的编写。在编写、审查或调试使用腾讯地图 API的代码时应运用此技能。适用于涉及地图初始化、覆盖物展示、图层控制、事件处理、控件交互、可视化渲染、地图工具、检索、路线规划、查地址、行政区划、ip定位、几何计算、三维模型展示、性能优化的任务。当用户提及 腾讯地图、 jsapi、

  • References files that are not bundled: references/jsapigl/docs/, references/visualization/docs/, references/jsapigl/demos/
  • 6 referenced file(s) missing: references/jsapigl/docs/, references/visualization/docs/, references/jsapigl/demos/
  • Does not say what the result is
clawhub · ↓ 1 264

memory-manager-v2

F process
Analyzerwill not run

OpenClaw-native memory maintenance, snapshots, indexing health checks, and review workflows. Use when you need to protect context before risky work, troubleshoot memory_search, cre

  • References files that are not bundled: scripts/check.ps1, scripts/snapshot.ps1, scripts/review.ps1
  • 6 referenced file(s) missing: scripts/check.ps1, scripts/snapshot.ps1, scripts/review.ps1
  • Does not say what the result is
clawhub · ↓ 954

gate-news-briefing

F process
Analyzerwill not run

News briefing. Use this skill ONLY when the user's query is exclusively about recent news or headlines with no other analysis dimensions. Trigger phrases: what happened recently, t

  • 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
  • 1 referenced file(s) missing: {url}
clawhub · ↓ 976
Analyzerwill not run

Detect and repair partial failures in Gougoubi PBFT operations, including missing activation, missing risk LP, missing results, and pending reward claims. Use when earlier batch wo

  • References files that are not bundled: scripts/pbft-activate-and-add-risklp.mjs, scripts/pbft-submit-all-condition-results.mjs, scripts/pbft-submit-real-results-ba0c-resolved-only.mjs
  • 5 referenced file(s) missing: scripts/pbft-activate-and-add-risklp.mjs, scripts/pbft-submit-all-condition-results.mjs, scripts/pbft-submit-real-results-ba0c-resolved-only.mjs
  • Linear process with no failure handling
clawhub · ↓ 974

ci-cd-compliance

F process
Referencewill not run

CI/CD pipeline requirements and deployment standards. Use when (1) Setting up CI/CD pipelines, (2) Debugging CI failures, (3) Configuring deployment workflows, (4) Managing staging

  • References files that are not bundled: references/pipeline-requirements.md
  • 1 referenced file(s) missing: references/pipeline-requirements.md
  • Does not say what the result is
clawhub · ↓ 1 048

figma-to-static

F process
GeneratorFigmawill not run

Convert Figma design files to pixel-level mobile-first static HTML/CSS pages. Use when: (1) user provides a Figma file link and wants a static web page, (2) user sends design scree

  • References files that are not bundled: assets/*
  • 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 · ↓ 949
Procedurewill not run

  • References files that are not bundled: references/prompt-engineering.md, references/agent-orchestration.md, references/provider-comparison.md
  • 13 top-level sections: this looks like several domains in one skill
  • 9 referenced file(s) missing: references/prompt-engineering.md, references/agent-orchestration.md, references/provider-comparison.md
clawhub · ↓ 993

wander-monitor

F process
IntegrationGitHubwill not run

Guides use of Wander to monitor GitHub Actions without polling. Use when the user pushes code and wants CI notifications, asks how to watch workflows, avoid refreshing the Actions

  • References files that are not bundled: scripts/watch-*.sh
  • 10 top-level sections: this looks like several domains in one skill
  • 1 referenced file(s) missing: scripts/watch-*.sh
clawhub · ↓ 948

daily-dev-ask

F process
Referencewill not run

Answer technical questions using daily.dev's knowledge base. Searches articles from the developer community and synthesizes answers with source links.

  • 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
  • 1 referenced file(s) missing: url
clawhub · ↓ 948

geo-human-editor

F process
Analyzerwill not run

Audit and rewrite content to remove AI-generated feel by stripping markdown artifacts, eliminating AI vocabulary patterns, flagging hallucination risks, and restoring natural human

  • References files that are not bundled: references/ai-vocabulary.md, references/patterns.md, references/hallucinations.md
  • 1 test cases, all positive: not one "should refuse" or "should ask first"
  • 3 referenced file(s) missing: references/ai-vocabulary.md, references/patterns.md, references/hallucinations.md
clawhub · ↓ 947

novel-writer

F process
Generatorwill not run

Use for creative writing, specifically novels blending urban daily life with science fiction elements. Specializes in Tomato Platform style - urban setting + sci-fi premise + fast

  • References files that are not bundled: references/world-building.md
  • 1 referenced file(s) missing: references/world-building.md
  • Does not say what the result is
clawhub · ↓ 992

cargo-ai

F process
Generatorwill not run

Build and configure AI agents inside Cargo — create an agent, choose its model and temperature, write its prompt, attach knowledge for retrieval (RAG), connect MCP tool servers, ma

  • References files that are not bundled: ../cargo-content/SKILL.md, ../cargo-workspace-management/SKILL.md, ../cargo/references/prerequisites.md
  • 11 top-level sections: this looks like several domains in one skill
  • The response is described with custom markup (8 tags): a typed call is more reliable
clawhub · ↓ 1 205

cargo-context

F process
Generatorwill not run

Read and write the workspace GTM knowledge base — the git-backed repository of markdown describing ICPs, personas, plays, proof points, objections, competitors, and signals — plus

  • References files that are not bundled: ../cargo-workspace-management/SKILL.md, ../cargo-ai/SKILL.md, ../cargo/references/prerequisites.md
  • The response is described with custom markup (4 tags): a typed call is more reliable
  • 4 referenced file(s) missing: ../cargo-workspace-management/SKILL.md, ../cargo-ai/SKILL.md, ../cargo/references/prerequisites.md
clawhub · ↓ 1 248

value-analyzer

F process
Analyzerwill not run

[何时使用]当用户需要分析股票是否符合格雷厄姆标准时;当用户问"这只股票安全吗"时;当进行价值投资初步筛选时;当需要计算安全边际时

  • References files that are not bundled: examples/defensive-analysis.md, examples/aggressive-analysis.md, examples/analysis-examples.md
  • 10 top-level sections: this looks like several domains in one skill
  • 3 referenced file(s) missing: examples/defensive-analysis.md, examples/aggressive-analysis.md, examples/analysis-examples.md
clawhub · ↓ 967

tsw-shorts-factory

F process
IntegrationYouTubewill not run

Autonomous YouTube Shorts video factory — zero cost, no external video API required. Generates quote-based short-form videos daily using edge-tts (free Microsoft neural voices) + P

  • References files that are not bundled: references/niche-config.md, references/troubleshooting.md
  • 2 referenced file(s) missing: references/niche-config.md, references/troubleshooting.md
  • Does not say what the result is
clawhub · ↓ 990
Integrationwill not run

Editor-first WeChat Official Account publishing skill. Posts content to WeChat Official Account (微信公众号) via API or browser, while prioritizing humanized writing, WeChat-native form

  • References files that are not bundled: references/config/first-time-setup.md
  • 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 · ↓ 967
Analyzerwill not run

Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with "audit accessibility", "check a11y", "is this accessible?", or when reviewing a design for color contrast, k

  • References files that are not bundled: ../../CONNECTORS.md
  • 1 referenced file(s) missing: ../../CONNECTORS.md
  • No condition that starts the skill
clawhub · ↓ 1 067

pinchtab

F process
IntegrationTelegramwill not run

Browser automation via HTTP API. Use for headless browser control, web automation, form filling, data extraction, and interactive element interaction. Supports launching instances,

  • References files that are not bundled: assets/google-screenshot.png
  • 1 referenced file(s) missing: assets/google-screenshot.png
  • Does not say what the result is
clawhub · ↓ 966
Procedurewill not run

Activate Gougoubi proposal conditions and stake risk LP per condition in one deterministic workflow. Use when users want to activate a proposal, activate selected conditions, or ad

  • References files that are not bundled: scripts/pbft-activate-and-add-risklp.mjs, scripts/pbft-join-and-activate-all-conditions.mjs, scripts/pbft-add-risk-lp-to-proposal.mjs
  • 3 referenced file(s) missing: scripts/pbft-activate-and-add-risklp.mjs, scripts/pbft-join-and-activate-all-conditions.mjs, scripts/pbft-add-risk-lp-to-proposal.mjs
  • Linear process with no failure handling
clawhub · ↓ 964

cowhorse-skill

F process
Procedurewill not run

A skill that actively extracts and quantifies workflow requirements from users through structured Q&A about inputs, outputs, and objectives. Build reusable skills with scripts/refe

  • References files that are not bundled: scripts/init_skill.py, scripts/package_skill.py
  • 2 referenced file(s) missing: scripts/init_skill.py, scripts/package_skill.py
  • Does not say what the result is
clawhub · ↓ 944

skill-polisher

F process
Procedurewill not run

当用户需要持续打磨和进化技能、追踪技能质量、收集反馈改进、检查技能规范合规性时使用。每次技能执行后自动收集用户评分,沉淀使用数据,定期分析并输出改进建议。包含技能健康度检查、最佳实践沉淀、标准化评分卡等功能。🔒 只读分析,不修改任何技能文件。

  • References files that are not bundled: references/QUALITY-CHECKLIST.md, references/DATA-SCHEMA.md
  • 15 top-level sections: this looks like several domains in one skill
  • 2 referenced file(s) missing: references/QUALITY-CHECKLIST.md, references/DATA-SCHEMA.md
clawhub · ↓ 964
Generatorwill not run

Daily digest of cutting-edge science, AI, and top journal papers worldwide. Searches 12+ domains including Nature, Science, arXiv, AI news, biomedicine, physics, quantum computing,

  • References files that are not bundled: url
  • 1 referenced file(s) missing: url
  • Does not say what the result is
clawhub · ↓ 988