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

company-research

F process
Generatorwill not run

Multi-source company research tool that generates structured due-diligence reports. Use when the user asks to research, look up, or investigate a company — including questions abou

  • References files that are not bundled: URL
  • 1 referenced file(s) missing: URL
  • Does not say what the result is
clawhub · ↓ 1 312

huo15-openclaw-ppt

F process
Referencewill not run

基于 design tokens 的 PPT 生成技能。内置 21 套生产级审美方案(Apple 发布会 / Apple.com / Apple macOS 26 Liquid Glass 玻璃 / 原研哉极简 / 中国水墨 / 国风故宫 / 赛博朋克绚彩 / 梵高油画 / 达芬奇手稿 / 小红书时尚奶油胶片 / 莫兰迪高级灰 / 孟菲斯 80s / 包豪斯

  • References files that are not bundled: examples/previews/*.png, templates/helpers.py::_set_run_spacing, templates/helpers.py
  • 16 top-level sections: this looks like several domains in one skill
  • 3 referenced file(s) missing: examples/previews/*.png, templates/helpers.py::_set_run_spacing, templates/helpers.py
clawhub · ↓ 1 372

dex-quant-skill

F process
Generatorwill not run

加密货币量化交易 AI Skill。用自然语言描述交易规则 → 生成策略脚本 → 服务器回测 → 参数优化 → 实时监控。 支持 Binance/Hyperliquid 全币种,6 种优化算法(genetic/bayesian/grid/random/annealing/pso),异步进度推送。 Use when user asks to: 推荐策略, 有什

  • References files that are not bundled: path
  • 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 · ↓ 1 374

jd-triage

F process
Analyzerwill not run

Career decision system for job seekers. Scores a job description on two independent dimensions — how much you want it (5 weighted axes against your stored criteria) and how likely

  • References files that are not bundled: assets/presets/*.yaml
  • Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 1 referenced file(s) missing: assets/presets/*.yaml
clawhub · ↓ 951 ★ 1

autoglm-toolkit

F process
Generatorwill not run

AutoGLM AI agent toolkit powered by Zhipu AI. Includes browser automation, deep research, web search, image generation, image search, and web page content extraction. Perfect for

  • References files that are not bundled: image_url
  • 1 referenced file(s) missing: image_url
  • No condition that starts the skill
clawhub · ↓ 1 347
Procedurewill not run

Headful Chromium with VNC/noVNC operator UI and Chrome CDP exports (cookies, screenshots, outerHTML).

  • References files that are not bundled: templates/x11vnc.service.j2, templates/novnc.service.j2
  • 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 · ↓ 746 ★ 1

time-anchor

F process
Referencewill not run

Offload date math to code — get current date, days/weeks until goal dates, and month-end info. Use whenever you need to reason about relative dates or calculate "how many days unti

  • References files that are not bundled: README.md
  • 1 referenced file(s) missing: README.md
  • Does not say what the result is
clawhub · ↓ 744 ★ 1

whop-digital-store

F process
Procedurewill not run

  • References files that are not bundled: /?t=settings&s=advanced, scripts/whop_store_manager.py, scripts/license_generator.py
  • 3 referenced file(s) missing: /?t=settings&s=advanced, scripts/whop_store_manager.py, scripts/license_generator.py
  • No condition that starts the skill
clawhub · ↓ 1 391

story-setup

F process
Procedurewill not run

网文写作工具集基础设施部署与检查。为 Claude Code / OpenCode / Codex / Google Antigravity / ZCode / OpenClaw / Reasonix 提供内置适配;Web AI / 通用 Agent 可走 skills + AGENTS.md 文件模式。触发方式:/story-setup、$story-se

  • References files that are not bundled: references/diagnostics.md, scripts/merge-claude-settings.py, scripts/merge-codex-hooks.py
  • 10 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 · ↓ 1 578

leio-sdlc

F process
Procedurewill not run

强制指令:执行 Software Development Life Cycle (SDLC)。所有的代码修改、Bug 修复和功能实现,必须且只能通过启动本技能中的 orchestrator.py 来完成。严禁主 Agent (你) 绕过本技能直接去操作源码工作区。

  • References files that are not bundled: scripts/orchestrator.py
  • 1 referenced file(s) missing: scripts/orchestrator.py
  • Does not say what the result is
clawhub · ↓ 1 388
Procedurewill not run

此技能作为数字伙伴使用用户的任何问题都可以触发;基于双环架构(两大循环:主循环符号思维 + 次循环行为感知,加超然最外圈)的AGI进化模型,通过意向性分析、人格映射、元认知检测和错误智慧库实现持续自我演进;当用户需要智能对话、人格定制、复杂问题求解或从错误中学习时使用

  • References files that are not bundled: LICENSE, scripts/test_phase3.py, scripts/toolnode
  • 14 top-level sections: this looks like several domains in one skill
  • 8 referenced file(s) missing: LICENSE, scripts/test_phase3.py, scripts/toolnode
clawhub · ↓ 1 517
AnalyzerGitHubwill not run

Keep an OpenClaw agent's non-sensitive context (selected memory, MD files, notes, and custom skills) under version control in a separate Git repository for remote review/tweaks. Us

  • References files that are not bundled: references/.env
  • 1 referenced file(s) missing: references/.env
  • Does not say what the result is
clawhub · ↓ 1 322
Generatorwill not run

Generate Leaf templates for FOSMVVM WebApps. Create full-page views and HTML-over-the-wire fragments that render ViewModels.

  • References files that are not bundled: ../../docs/FOSMVVMArchitecture.md, {baseDir}/references/FOSMVVMArchitecture.md, ../fosmvvm-viewmodel-generator/SKILL.md
  • 16 top-level sections: this looks like several domains in one skill
  • 6 referenced file(s) missing: ../../docs/FOSMVVMArchitecture.md, {baseDir}/references/FOSMVVMArchitecture.md, ../fosmvvm-viewmodel-generator/SKILL.md
clawhub · ↓ 1 343

project-execution

F process
Analyzerwill not run

Executes implementation plans with progress tracking, checkpoint validation, and quality gates. Use after planning is complete and tasks are ready to implement

  • References files that are not bundled: references/mission-report.md
  • 14 top-level sections: this looks like several domains in one skill
  • 1 referenced file(s) missing: references/mission-report.md
clawhub · ↓ 1 681

gws-sheets-read

F process
ReferenceGoogle Sheetswill not run

Google Sheets: Read values from a spreadsheet.

  • References files that are not bundled: ../gws-shared/SKILL.md, ../gws-sheets/SKILL.md
  • 2 referenced file(s) missing: ../gws-shared/SKILL.md, ../gws-sheets/SKILL.md
  • Does not say what the result is
clawhub · ↓ 1 339

posthog

F process
IntegrationStripeNotionwill not run

PostHog API integration with managed authentication. Product analytics, feature flags, session recordings, experiments, and more. Use this skill when users want to query analytics

  • 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 · ↓ 1 456

use-dingding

F process
Integrationwill not run

Interact with DingTalk enterprise workspace using the dws CLI. Required: dws CLI, DWS_CLIENT_ID, DWS_CLIENT_SECRET. Use for: contacts, chat, calendar, todo, approvals, attendance,

  • References files that are not bundled: references/products/*.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 · ↓ 739 ★ 1

insight-engine

F process
ProcedureNotionwill not run

Logs/metrics → Python statistics → LLM interpretation → Notion reports. Use when: generating daily/weekly/monthly operational insights from AI system logs, producing data-driven No

  • References files that are not bundled: scripts/config/analyst.yaml.example
  • 1 referenced file(s) missing: scripts/config/analyst.yaml.example
  • Does not say what the result is
clawhub · ↓ 1 315

granola-mcp

F process
IntegrationStripeNotionwill not run

Granola MCP integration with managed authentication. Use this skill when users want to search meeting content, get meeting summaries, find action items, or retrieve transcripts fro

  • 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 · ↓ 1 482
Integrationwill not run

Interactive guide for integrating MobTech FlyVerify (SecVerify) into Android projects with 5-step workflow. Use when user says "我要在app中增加一键登录", "秒验集成", "FlyVerify集成", "Android一键登录"

  • References files that are not bundled: assets/FlyVerify_Config_Template.xlsx
  • 1 referenced file(s) missing: assets/FlyVerify_Config_Template.xlsx
  • Does not say what the result is
clawhub · ↓ 738 ★ 1

Pacman Hedera

F process
Procedurewill not run

Autonomous AI agent for DeFi on Hedera — natural language trading, portfolio management, Power Law BTC rebalancing, HCS signal publishing, limit orders, staking, NFTs, and multi-ac

  • 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
  • 55 top-level sections: this looks like several domains in one skill
clawhub · ↓ 737 ★ 1

venn

F process
IntegrationNotionSlackwill not run

Search, describe, and execute enterprise tools (Jira, Salesforce, Gmail, Slack, Google Calendar, Google Drive, GitHub, Notion, Box, etc.) via the Venn tool-router REST API. Use whe

  • 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 · ↓ 1 311
GeneratorObsidianwill not run

Build structured brainstorming notes from a seed zettel by retrieving linked notes, preprocessing each note with subagents for relevance extraction, drafting with cited evidence, a

  • References files that are not bundled: scripts/search.py
  • The skill tells the model to perform an irreversible action with no human approval
  • 1 referenced file(s) missing: scripts/search.py
clawhub · ↓ 1 333
Procedurewill not run

Query weather and provide outfit recommendations. When information is insufficient, ask about destination, date, and clothing preferences. Uses free weather APIs.

  • References files that are not bundled: URL
  • 1 referenced file(s) missing: URL
  • Does not say what the process needs to start
clawhub · ↓ 762 ★ 1

meta-skill

F process
Generatorwill not run

Trajectory compiler that converts real OpenClaw session traces (or raw_trajectory_log) into a parameterized, reusable Skill via 4 stages: trace interception → DAG abstraction → sch

  • References files that are not bundled: references/schema.json, references/plan.json, references/run-flow.md
  • 4 referenced file(s) missing: references/schema.json, references/plan.json, references/run-flow.md
  • 1 steps
clawhub · ↓ 1 310