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

uxr-observer

F process
Integrationwill not run

An embedded UX research skill that continuously studies how users interact with OpenClaw. It observes conversation patterns, task completions, friction points, and satisfaction lev

  • References files that are not bundled: references/analysis-framework.md
  • 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 · ↓ 969
Analyzerwill not run

Enables AI agents (e.g. OpenClaw) to understand and use Krump Verify for on-chain move verification against Story IP. Use when the user or agent needs to verify a dance move, pay v

  • References files that are not bundled: ../../../docs/BUILDING_WITH_EVVM_X402_STORY_AENEID.md, ../../DEPLOY.md, ../../../README.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 · ↓ 990

client-dashboard

F process
GeneratorExcelwill not run

Generates a client-facing executive KPI dashboard from QuickBooks Online data. Produces an Excel workbook with traffic-light scoring, 6-month trend sparklines, client-specific watc

  • References files that are not bundled: scripts/pipelines/client-dashboard.py
  • 14 top-level sections: this looks like several domains in one skill
  • 1 referenced file(s) missing: scripts/pipelines/client-dashboard.py
clawhub · ↓ 1 008
Procedurewill not run

  • References files that are not bundled: scripts/com.openclaw.heartbeat.plist
  • 13 top-level sections: this looks like several domains in one skill
  • 1 referenced file(s) missing: scripts/com.openclaw.heartbeat.plist
clawhub · ↓ 1 008

algo-builder

F process
Referencewill not run

  • References files that are not bundled: scripts/test_signal.py
  • 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 · ↓ 1 008

dcl-skill-auditor

F process
Analyzerwill not run

Scan any ClawHub skill before installing it. 534 out of 3,984 ClawHub skills contained critical vulnerabilities — credential theft, prompt injection, data exfiltration. Snyk Resear

  • References files that are not bundled: scripts/run.sh:17
  • 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 · ↓ 1 138

media-cluster

F process
Procedurewill not run

Crawls social media by search keyword (MediaCrawler: 小红书/抖音/微博/B站等), summarizes content and outputs report plus short voice summary. User gives one sentence only (e.g. “爬一下小红书关键词比特

  • References files that are not bundled: MediaCrawler/README.md
  • 10 top-level sections: this looks like several domains in one skill
  • 1 referenced file(s) missing: MediaCrawler/README.md
clawhub · ↓ 984
Referencewill not run

Submit real-world outcomes for Gougoubi conditions using deterministic evidence from condition skills and public market data. Use when users want resolved-only submission, full set

  • References files that are not bundled: scripts/pbft-submit-all-condition-results.mjs, scripts/pbft-submit-results-from-skills-once.mjs, scripts/pbft-submit-real-results-1605.mjs
  • 6 referenced file(s) missing: scripts/pbft-submit-all-condition-results.mjs, scripts/pbft-submit-results-from-skills-once.mjs, scripts/pbft-submit-real-results-1605.mjs
  • Says nothing while it works
clawhub · ↓ 1 007

skill-pilot

F process
Procedurewill not run

Adaptive skill scheduling engine with environment-aware routing, user preferences, and self-learning optimization. Use when: (1) auto-select best skill for task, (2) need environ

  • References files that are not bundled: references/environment-probe.md, references/strategy-guide.md
  • 12 top-level sections: this looks like several domains in one skill
  • 2 referenced file(s) missing: references/environment-probe.md, references/strategy-guide.md
clawhub · ↓ 1 006
Procedurewill not run

Gate CrossEx cross-exchange skill. Use when the user asks to trade or query positions across Gate, Binance, OKX, and Bybit simultaneously. Triggers on 'cross exchange', 'Binance or

  • References files that are not bundled: references/*.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 · ↓ 1 007
Procedurewill not run

基于文本描述或数据自动生成各类图表(趋势图、对比图、结构图等);当用户需要创建可视化图表、将数据转化为直观表达、生成分析报告插图时使用

  • References files that are not bundled: references/api_key.md
  • 1 referenced file(s) missing: references/api_key.md
  • Does not say what the result is
clawhub · ↓ 551 ★ 1

supplier-scorecard

F process
Procedurewill not run

Track and score supplier reliability, quality consistency, lead time accuracy, and communication to make sourcing decisions based on evidence. Use when comparing suppliers for the

  • References files that are not bundled: references/scoring-rubrics.md, assets/scorecard-quality-checklist.md, references/output-template.md
  • 4 referenced file(s) missing: references/scoring-rubrics.md, assets/scorecard-quality-checklist.md, references/output-template.md
  • Does not say what the result is
clawhub · ↓ 1 052
ProcedureTelegramWordwill not run

Telegram-based internal contract generation and eID intake workflow for Vietnamese operations. Use when setting up, migrating, or operating a bot that: (1) receives structured cont

  • References files that are not bundled: assets/windows/
  • 1 referenced file(s) missing: assets/windows/
  • Does not say what the result is
clawhub · ↓ 1 003
Integrationwill not run

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong..

  • References files that are not bundled: references/openclaw-integration.md, scripts/activator.sh, scripts/error-detector.sh
  • 18 top-level sections: this looks like several domains in one skill
  • 5 referenced file(s) missing: references/openclaw-integration.md, scripts/activator.sh, scripts/error-detector.sh
clawhub · ↓ 962

yuque

F process
Referencewill not run

Manage Yuque (语雀) knowledge base documents and repositories. Use when users need to interact with Yuque for document operations including reading documents, listing repositories, s

  • References files that are not bundled: references/examples.md, scripts/parse_yuque.py, scripts/search_yuque.py
  • 3 referenced file(s) missing: references/examples.md, scripts/parse_yuque.py, scripts/search_yuque.py
  • No condition that starts the skill
clawhub · ↓ 980
Procedurewill not run

Decentralized compute and data marketplace for AI agents with spot pricing | 去中心化 AI Agent 计算和数据市场,支持 Spot 动态定价

  • References files that are not bundled: examples/complete-demo.ts
  • 14 top-level sections: this looks like several domains in one skill
  • 1 referenced file(s) missing: examples/complete-demo.ts
clawhub · ↓ 1 001

brainmd

F process
Analyzerwill not run

Neuroplastic self-modifying runtime for AI agents. Creates a file-based 'brain' that learns from interactions: reflexes (fast-path responses), habits (learned patterns), weighted p

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

discord-dynasty

F process
IntegrationDiscordwill not run

Handles Discord task-center forum: create task posts, archive tasks by tag, and respect model tags. Supports six-ministries style channel template (司礼监+六部). Use when user says 新建任务

  • References files that are not bundled: ../OpenClaw配置与Discord参考.md
  • 1 referenced file(s) missing: ../OpenClaw配置与Discord参考.md
  • Does not say what the result is
clawhub · ↓ 978

ai-director

F process
Generatorwill not run

AI short drama generation - account management, script writing, video production. Integrated X2C billing for commercial deployment.

  • References files that are not bundled: references/AD-WRITER-GUIDE.md, references/X2C-OPEN-API.md
  • 2 referenced file(s) missing: references/AD-WRITER-GUIDE.md, references/X2C-OPEN-API.md
  • Does not say what the result is
clawhub · ↓ 975
Integrationwill not run

Integrate Shengwang products: ConvoAI voice agents, RTC audio/video, RTM messaging, Cloud Recording, and token generation. Use when the user mentions Shengwang, 声网, ConvoAI, RTC, R

  • References files that are not bundled: references/docs.txt
  • Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 1 referenced file(s) missing: references/docs.txt
clawhub · ↓ 997

memprocessor

F process
Procedurewill not run

  • References files that are not bundled: ../LICENSE
  • 1 referenced file(s) missing: ../LICENSE
  • Does not say what the result is
clawhub · ↓ 975

tilannlou

F process
ProcedureDockerwill not run

  • References files that are not bundled: config
  • 13 top-level sections: this looks like several domains in one skill
  • 1 referenced file(s) missing: config
clawhub · ↓ 976
Referencewill not run

Scans installed skills, suggests L0-L3 priority tiers, and auto-configures skill injection policy. Use when: setting up skill priorities, optimizing token budget, or migrating to t

  • References files that are not bundled: ../SKILL_PRIORITY_POLICY.md
  • 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 · ↓ 975

standard-readme

F process
Analyzerwill not run

Writes or audits READMEs against the Standard Readme spec. Use whenever the user asks to create, rewrite, improve, audit, or fix a README, or asks about README quality or structure

  • References files that are not bundled: assets/banner.png, CONTRIBUTING.md, LICENSE
  • Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 3 referenced file(s) missing: assets/banner.png, CONTRIBUTING.md, LICENSE
clawhub · ↓ 1 312

wurd

F process
Generatorwill not run

Compile markdown documents with plugin tags into editorial-quality HTML pages using Wurd. USE FOR: creating documents, adding plugins, configuring layout, writing custom plugins, d

  • References files that are not bundled: examples/my-doc/text.md
  • The response is described with custom markup (3 tags): a typed call is more reliable
  • 1 referenced file(s) missing: examples/my-doc/text.md
clawhub · ↓ 545 ★ 1