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.
Integration
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 1 608 ★ 4
ReferenceDiscord
Discord archive: search, sync freshness, DMs, channel slices, SQL counts, and Discrawl repo work.
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 1 774 ★ 5
Analyzer
Determines when elderly people living alone have no interaction or visitors for extended periods, and actively pushes care reminders to family members, suitable for remote care sce
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 001 ★ 5
IntegrationPostgreSQLGitHub
Use the Fly.io flyctl CLI for deploying and operating apps on Fly.io. Default to read-only diagnostics (status/logs/config/releases). Only perform state-changing operations (deploy
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 3 424 ★ 1
Proceduremissing files
Publication-ready scientific figures from one command — 27 chart types (bar, slope, volcano, grouped bar, scatter, heatmap, forest plot, KM survival curve (Kaplan-Meier, ROC, violi
- References files that are not bundled: scripts/journal/*.json, templates/README.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 24 top-level sections: this looks like several domains in one skill
clawhub · ↓ 3 151 ★ 3
Reference
Personal knowledge base for capturing and retrieving information about people,
places, restaurants, games, tech, events, media, ideas, and organizations.
Use when: user mentions a
- 10 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
- Does not say what the result is
clawhub · ↓ 3 499 ★ 1
Integration
Deploy smart contracts and bridge assets to Abstract (ZK Stack L2). Use when an agent needs to deploy contracts on Abstract, bridge ETH/tokens to Abstract, trade/swap tokens, check
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 403 ★ 2
Integration
A text-based calendar and scheduling application. Use strictly for CLI-based calendar management.
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 3 460 ★ 1
Proceduremissing files
equal-data-skill 金融数据服务- 提供覆盖A股5000+家上市公司的行情、财报、基本面、重大事件追踪(高管增减持, 重大合同, 股东变动,大宗交易, 限售解禁,定向增发,分红送转, 业绩预告)等多维度数据、股东分析、基金持仓与变动统计、知名机构动向追踪(包含 国家队,外资,私募基金,公募基金,信托,保险,证券等)、知名牛散持仓数据、资讯、公告
- References files that are not bundled: <reference/特色策略/全部策略列表.md>, <reference/特色策略/具体的策略详情.md>, <reference/特色策略/策略持仓信息.md>
- 10 top-level sections: this looks like several domains in one skill
- 90 referenced file(s) missing: <reference/特色策略/全部策略列表.md>, <reference/特色策略/具体的策略详情.md>, <reference/特色策略/策略持仓信息.md>
clawhub · ↓ 2 952 ★ 2
Reference
Stream recent logs from systemd journal
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 3 425 ★ 1
ReferenceSlack
Hybrid memory strategy combining OpenClaw's built-in vector memory with Graphiti temporal knowledge graph. Use when you need to recall past context, answer temporal questions ("whe
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 3 391 ★ 1
Proceduremissing files
Spawn isolated sub-agents representing distinct worldviews (Elon, Capitalist, Monkey) to debate decisions from multiple angles. Expose blind spots by forcing genuine disagreement o
- References files that are not bundled: assets/index-template.md
- 12 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: assets/index-template.md
clawhub · ↓ 3 495 ★ 1
Reference
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 4 012 ★ 1
IntegrationStripeNotionmissing files
Podio API integration with managed OAuth. Manage workspaces, apps, items, tasks, and comments.
Use this skill when users want to read, create, update, or delete Podio items, manage
- 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 · ↓ 2 634 ★ 2
Proceduremissing files
Unified knowledge capture and retrieval for URLs, video/article/paper extracts, social posts, and agent research outputs. Use when saving anything worth re-finding later, summarizi
- References files that are not bundled: scripts/know
- 1 referenced file(s) missing: scripts/know
- Does not say what the result is
clawhub · ↓ 3 336 ★ 1
Analyzer
Detects fire and smoke in video scenes. Supports both video stream and image analysis. Suitable for fire early warning scenarios such as security surveillance, forest fire preventi
- 1 steps
- Does not say what the result is
clawhub · ↓ 2 334 ★ 4
Procedure
Simple test skill that calls a GET endpoint to fetch a daily post. No authentication required.
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 3 883 ★ 1
Analyzer
Detects quality issues in camera footage such as black/white screens, color cast, stripes, noise, and blurriness. Suitable for security surveillance and camera self-check scenarios
- 1 steps
- Does not say what the result is
clawhub · ↓ 2 048 ★ 4
Procedure
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 2 355 ★ 2
ProcedureDocker
Set up and maintain Raspberry Pi avoiding common hardware and configuration pitfalls.
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 405 ★ 2
ProcedureDiscordTelegram
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 6 428
Proceduremissing files
- References files that are not bundled: path/to/table1.png
- 1 referenced file(s) missing: path/to/table1.png
- Does not say what the result is
clawhub · ↓ 803 ★ 10
ProcedurePlaywright
Revolut web automation via Playwright: login/logout, list accounts, and fetch transactions.
- The skill tells the model to perform an irreversible action with no human approval
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 481 ★ 2
IntegrationAWSmissing files
Secure key management for AI agents. Use when handling private keys, API secrets, wallet credentials, or when building systems that need agent-controlled funds. Covers secure stora
- References files that are not bundled: examples/secret_manager.py, examples/sanitizer.py, examples/validator.py
- 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 · ↓ 2 396 ★ 2
Integration
AI Agent Collaborative Art Platform - 512x512 shared canvas
- 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
- Does not say what the result is
clawhub · ↓ 3 441 ★ 1