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.
Analyzerwill not run
Official skill for upkuajing (跨境魔方). Find companies (找公司) and global buyers using customs trade data. Get trade order details, business contact info, and lead generation tools for
- References files that are not bundled: scripts/*.py
- 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 · ↓ 1 015 ★ 13
Generator
Manage Google Photos library. Upload photos, create albums, and list library content. Use when the user wants to backup, organize, or share images via Google Photos.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- Does not say what the process needs to start
clawhub · ↓ 2 948 ★ 3
Integration
Operate the OpenTask agent-to-agent marketplace through hosted MCP: publish services and capabilities, discover agents or work, bid or submit entries, evaluate and award work, mana
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- No condition that starts the skill
- Does not say what the process needs to start
clawhub · ↓ 3 175 ★ 3
ReferencePhotoshopBlender
Let agents control software, including Adobe Photoshop, Illustrator, After Effects, Premiere, Autodesk 3DS Max, Blender, Unity, Houdini, and Microsoft Office.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- Does not say what the process needs to start
clawhub · ↓ 5 645 ★ 1
Reference
Support legal understanding from everyday rights to professional practice and scholarship.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 993 ★ 3
Integration
Local-first budget and policy guardrails for agent actions, with optional remote sync to AgentSentinel.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 3 807 ★ 2
Procedure
Ye Wubin authorized AI coach for energy-based time management with calendar, context lists, and self-evolution.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 3 082 ★ 3
Analyzer
Support financial understanding from personal budgeting to professional analysis and research.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 3 004 ★ 3
Reference
Configure and troubleshoot VPN connections for privacy and remote access.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- Does not say what the process needs to start
clawhub · ↓ 2 445 ★ 4
Integration
Cloud-hosted markdown collaboration for agents and humans. One API call to create, one link to share. End-to-end encrypted, no account required.
- 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
- The response is described with custom markup (7 tags): a typed call is more reliable
clawhub · ↓ 3 304 ★ 3
Integration
When user asks for interview prep, mock interview, practice questions, behavioral questions, technical interview, HR round, salary negotiation, STAR method, common interview questi
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 31 top-level sections: this looks like several domains in one skill
- Does not say what the result is
clawhub · ↓ 2 398 ★ 4
Analyzer
Runs growth as a system: finds which funnel stage is the constraint, picks the loop that compounds, and sizes the channel and experiment program. Use when growth stalled or a numbe
- 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
- Does not say what the process needs to start
clawhub · ↓ 2 512 ★ 4
Procedurewill not run
Use this skill when the user asks for financial data ("price of BTC", "P/E ratio of NVDA"), market analysis, stock or crypto research, quant strategies, backtesting ("backtest a mo
- References files that are not bundled: user.md, market-views.md, references/api/*.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 · ↓ 1 215 ★ 10
GeneratorPowerPoint
Create stunning, animation-rich HTML presentations from scratch or convert PowerPoint files (.ppt/.pptx) to beautiful web slides. Use when the user wants to build a pitch deck, pre
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- The response is described with custom markup (3 tags): a typed call is more reliable
- Does not say what the result is
clawhub · ↓ 6 807 ★ 1
Generatorwill not run
Write or update a skill (SKILL.md and supporting files) to match host structure and best practices. Use when user says create skill, write skill, update SKILL.md, /document-skills.
- References files that are not bundled: /en/hooks, ../../agents/references/coordinator-flows.md, ../../agents/references/
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 7 referenced file(s) missing: /en/hooks, ../../agents/references/coordinator-flows.md, ../../agents/references/
clawhub · ↓ 5 795 ★ 1
Integration
Search the web using Perplexity's Search API for ranked, real-time web results with advanced filtering. Use when you need to search for current information, market research, trendi
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- No condition that starts the skill
- Does not say what the process needs to start
clawhub · ↓ 3 783 ★ 2
Analyzerwill not run
Use when auditing content quality, E-E-A-T, or publish readiness; runs a typed 80-item CORE-EEAT profile with evidence coverage, veto checks, and a fix plan. Not for structural tag
- References files that are not bundled: ../../../references/runtime-invocation.md, ../../../references/core-eeat-benchmark.md, ../../../references/auditor-runbook.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 15 top-level sections: this looks like several domains in one skill
clawhub · ↓ 6 248 ★ 1
Analyzer
Intelligent code security scanner with hybrid local-cloud detection. Fingerprints packages, runs static behavioral analysis, and consults cloud threat intelligence (enabled by defa
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- The response is described with custom markup (19 tags): a typed call is more reliable
- Does not say what the result is
clawhub · ↓ 1 406 ★ 8
Procedure
Universal multi-agent workflow orchestration using Claude Code Agent Teams. Use when user asks to run a team workflow, create an agent team, or coordinate parallel work across mult
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 6 mutating operations with no state check
clawhub · ↓ 2 053 ★ 5
AnalyzerKubernetes
Writes, debugs, and reviews Go: goroutine leaks, data races, nil interfaces, slices and maps, go.mod, and net/http. Use when Go panics or misbehaves — "all goroutines are asleep -
- 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
- Does not say what the process needs to start
clawhub · ↓ 3 106 ★ 3
Generator
Morfeo Academy's Remotion video style guide. Use when creating Remotion videos, stories, or animations for Paul/Morfeo Academy. Triggers on "estilo Morfeo", "mi estilo Remotion", "
- 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
- Does not say what the result is
clawhub · ↓ 2 326 ★ 4
Integration
Meta Business Suite automation via Graph API. Use this skill when:
(1) Publishing posts to Facebook Pages
(2) Scheduling Facebook posts
(3) Publishing to Instagram (photos, reels,
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 059 ★ 5
ProcedureGitHubwill not run
Git workflow, CI/GitHub Actions, and supply-chain pinning rules for Mistral Vibe. Use when changing CI pipelines, GitHub Actions, dependency pinning, container images, pre-commit h
- References files that are not bundled: scripts/ci/
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- The response is described with custom markup (10 tags): a typed call is more reliable
mistralai/mistral-vibe · ★ 4 958
Reference
Python coding conventions for Mistral Vibe. Use when writing, reviewing, or refactoring Python code in the Vibe codebase. Covers style, type hints, imports, Pydantic patterns, logg
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- Does not say what the process needs to start
mistralai/mistral-vibe · ★ 4 958
Integration
Blockchain security API for AI agents. Scan tokens, simulate transactions, check addresses for threats.
- 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
- Does not say what the result is
clawhub · ↓ 2 323 ★ 4