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.

29 209 found

Integration

Hugging Face Dataset Viewer

  • The response is described with custom markup (16 tags): a typed call is more reliable
  • Does not say what the result is
  • No condition that starts the skill
sickn33/agentic-awesome-skills · ★ 46 412
Analyzerwill not run

Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.

  • References files that are not bundled: scripts/run_claude.sh
  • 1 referenced file(s) missing: scripts/run_claude.sh
  • Does not say what the result is
sickn33/agentic-awesome-skills · ★ 46 412

cursor-delegate

F process
Integrationwill not run

Delegate coding tasks to the Cursor Agent CLI (`cursor-agent`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

  • References files that are not bundled: scripts/relay.mjs
  • 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
sickn33/agentic-awesome-skills · ★ 46 412

design-system

F process
Generatorwill not run

Mechanical implementation invariants for frontend design: token architecture, typography hierarchy, loading order, FOUT prevention, chrome stability, motion timing, color semantics

  • References files that are not bundled: ../design-spatial/SKILL.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
sickn33/agentic-awesome-skills · ★ 46 412

system-info

D process
Analyzer

Quick system diagnostics: CPU, memory, disk, uptime

  • Prose only: no discrete steps
  • Does not say what the result is
clawhub · ↓ 10 528 ★ 8
Procedure

Certify a deployed service with fresh evidence across source, CI, migrations, runtime health, readiness, and critical routes; use before declaring a release production-ready.

  • Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 12 top-level sections: this looks like several domains in one skill
  • The skill tells the model to perform an irreversible action with no human approval
sickn33/agentic-awesome-skills · ★ 46 412
Procedure

当用户需要使用小浣熊(Raccoon)进行数据分析会话管理、文件上传下载、数据可视化、数据分析交互时使用此技能。触发词包括"小浣熊数据分析"、"Raccoon数据分析"、"数据分析会话"。

  • 12 top-level sections: this looks like several domains in one skill
  • Does not say what the result is
  • No condition that starts the skill
clawhub · ↓ 1 607 ★ 72

Image Editing

D process
Generator

Edit images with AI inpainting, outpainting, background removal, upscaling, and restoration tools.

  • Does not say what the result is
  • No condition that starts the skill
clawhub · ↓ 10 844 ★ 8

elicitation

F process
Analyzerwill not run

Psychological profiling through natural conversation using narrative identity research (McAdams), self-defining memory elicitation (Singer), and Motivational Interviewing (OARS fra

  • References files that are not bundled: elicitation/self-defining-memories.md, elicitation/narrative-identity.md, elicitation/motivational-interviewing.md
  • 15 top-level sections: this looks like several domains in one skill
  • 7 referenced file(s) missing: elicitation/self-defining-memories.md, elicitation/narrative-identity.md, elicitation/motivational-interviewing.md
clawhub · ↓ 4 606 ★ 20

data-analyst

D process
Analyzer

Complete the data analysis tasks delegated by the user.If the code needs to operate on files, please ensure that the file is listed in the `upload_files` parameter, and **pay speci

  • Does not say what the result is
  • No condition that starts the skill
clawhub · ↓ 10 953 ★ 7

ppt-master

F process
GeneratorPowerPointwill not run

AI-driven multi-format SVG content generation system for presentations, social media graphics, and marketing materials. Use when creating PPTs, posters, or visual content from docu

  • References files that are not bundled: docs/design_guidelines.md, docs/canvas_formats.md, examples/ppt169_demo/
  • 10 top-level sections: this looks like several domains in one skill
  • The response is described with custom markup (5 tags): a typed call is more reliable
clawhub · ↓ 12 463 ★ 8

one-drive

F process
IntegrationStripeNotionwill not run

OneDrive API integration with managed OAuth via Microsoft Graph. Manage files, folders, and sharing. Use this skill when users want to upload, download, organize, or share files in

  • 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 · ↓ 8 161 ★ 10

alexa-cli

D process
IntegrationGitHub

Control Amazon Alexa devices and smart home via the `alexacli` CLI. Use when a user asks to speak/announce on Echo devices, control lights/thermostats/locks, send voice commands, o

  • 10 top-level sections: this looks like several domains in one skill
  • The response is described with custom markup (11 tags): a typed call is more reliable
  • Does not say what the result is
clawhub · ↓ 6 374 ★ 14

web-deploy-github

F process
GeneratorGitHubwill not run

Create and deploy single-page static websites to GitHub Pages with autonomous workflow. Use when building portfolio sites, CV pages, landing pages, or any static web project that n

  • References files that are not bundled: templates/base-html/, templates/portfolio/, templates/landing/
  • 3 referenced file(s) missing: templates/base-html/, templates/portfolio/, templates/landing/
  • Does not say what the result is
clawhub · ↓ 8 426 ★ 9
IntegrationStripeNotionwill not run

Google Search Console API integration with managed OAuth. Query search analytics, manage sitemaps, and monitor site performance. Use this skill when users want to access Search Con

  • 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 · ↓ 7 725 ★ 10

github-cli

D process
IntegrationGitHub

Comprehensive GitHub CLI (gh) reference. Covers repos, issues, PRs, Actions, releases, gists, search, projects v2, API, secrets/variables, labels, codespaces, extensions, auth, and

  • 22 top-level sections: this looks like several domains in one skill
  • The response is described with custom markup (12 tags): a typed call is more reliable
  • Does not say what the result is
clawhub · ↓ 11 679 ★ 6

qwen-image

F process
Integrationwill not run

Generate images using Qwen Image API (Alibaba Cloud DashScope). Use when users request image generation with Chinese prompts or need high-quality AI-generated images from text desc

  • References files that are not bundled: URL
  • 1 referenced file(s) missing: URL
  • Does not say what the result is
clawhub · ↓ 10 238 ★ 7

yahoo-finance

B process
Reference

This skill should be used when the user asks to "get stock prices", "check stock quotes", "look up earnings", "get financial data", "find trending stocks", or needs stock market da

  • The skill tells the model to perform an irreversible action with no human approval
  • Does not say what the result is
  • 1 mutating operations with no state check
clawhub · ↓ 8 304 ★ 9

telegram

F process
IntegrationTelegramStripewill not run

Telegram Bot API integration with managed authentication. Send messages, manage chats, handle updates, and interact with users through your Telegram bot. Use this skill when users

  • 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 · ↓ 8 822 ★ 9

telegram-bot

D process
IntegrationTelegram

Build and manage Telegram bots via the Telegram Bot API. Create bots, send messages, handle webhooks, manage groups and channels.

  • Does not say what the result is
  • No condition that starts the skill
clawhub · ↓ 8 508 ★ 9
AnalyzerYouTubewill not run

Use when the user asks to "analyze competitors" or "竞品分析"; benchmarks competitor keywords, content, backlinks, AI citations, and traffic share into strengths, weaknesses, and an ac

  • References files that are not bundled: ../content-gap-analysis/SKILL.md, ../../../references/skill-contract.md, ../../../CONNECTORS.md
  • 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 · ↓ 11 209 ★ 7
Analyzer

Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long'

  • Does not say what the result is
  • Does not say what the process needs to start
github/awesome-copilot · ★ 39 003
Procedure

Guides sliding time window scaling in Qdrant. Use when someone asks 'only recent data matters', 'how to expire old vectors', 'time-based data rotation', 'delete old data efficientl

  • The skill tells the model to perform an irreversible action with no human approval
  • Does not say what the result is
  • Does not say what the process needs to start
github/awesome-copilot · ★ 39 003
Analyzer

Diagnoses and guides Qdrant horizontal scaling decisions. Use when someone asks 'vertical or horizontal?', 'how many nodes?', 'how many shards?', 'how to add nodes', 'resharding',

  • Does not say what the result is
  • Does not say what the process needs to start
github/awesome-copilot · ★ 39 003
Procedurewill not run

Guides Qdrant vertical scaling decisions. Use when someone asks 'how to scale up a node', 'need more RAM', 'upgrade node size', 'vertical scaling', 'resize cluster', 'scale up vs s

  • References files that are not bundled: ../../../qdrant-monitoring/SKILL.md, ../horizontal-scaling/SKILL.md
  • 2 referenced file(s) missing: ../../../qdrant-monitoring/SKILL.md, ../horizontal-scaling/SKILL.md
  • Does not say what the result is
github/awesome-copilot · ★ 39 003