← 返回 Skills 市场

12 Cool Skills for OpenClaw Agent

Name: 12 Cool Skills for OpenClaw Agent
Author: rioo-maker

作者 rioo-maker · GitHub ↗ · v1.0.1 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install 12-cool-skills-openclaw-agent

功能描述

Assistant de trading automatisé pour l'analyse de marché, la détection de signaux et l'exécution de stratégies techniques (RSI, MA, Support/Résistance). À ut...

使用说明 (SKILL.md)

AI Trading

Cette compétence transforme Manus en un assistant de trading discipliné, capable de suivre des stratégies techniques strictes tout en priorisant la gestion des risques.

Fonctionnalités Principales

Analyse Technique Multi-Indicateurs : Utilisation du RSI (période 14), des Moyennes Mobiles (MA20, MA50) et détection dynamique des supports et résistances.
Gestion des Risques Intégrée : Calcul automatique de la taille de position pour limiter le risque par trade à 1-2% du capital total.
Filtrage des Signaux : Validation des entrées par le volume et la tendance globale pour éviter les faux signaux.
Suivi de Performance : Génération de rapports détaillés incluant le taux de victoire, le profit moyen et le maximum drawdown.

Ressources de la Compétence

Scripts

scripts/position_sizing.py : Calcule la taille optimale de la position en fonction du capital, du risque souhaité et de la distance du Stop Loss.
- Usage : python3 scripts/position_sizing.py \x3Cbalance> \x3Crisk_percent> \x3Cstop_loss_dist>

Références

references/trading_strategies.md : Contient les règles détaillées pour les entrées ACHAT/VENTE, les paramètres des indicateurs et les contraintes de sécurité (max 3 trades simultanés).

Templates

templates/performance_report.md : Modèle pour la création de rapports de trading professionnels.

Flux de Travail Recommandé

Analyse de Marché : Récupérer les données de prix (1m, 5m, 15m, 1h) et calculer les indicateurs techniques (RSI, MA).
Détection de Tendance : Vérifier la tendance avec les MA20/MA50. Ne trader que dans le sens de la tendance.
Validation du Signal : Attendre que le RSI, le volume et les niveaux de support/résistance confirment l'entrée.
Calcul du Risque : Utiliser position_sizing.py pour déterminer la taille de la position avant toute exécution.
Exécution et Suivi : Définir obligatoirement un Stop Loss et un Take Profit (Ratio R/R 1:2 minimum).
Reporting : Utiliser le template de rapport pour documenter chaque trade et analyser la performance globale.

Contraintes de Sécurité

Stop Loss Obligatoire : Aucun trade ne doit être ouvert sans un Stop Loss défini.
Limite de Risque : Ne jamais dépasser 2% de risque par trade.
Mode Test : Privilégier le "Paper Trading" pour valider de nouvelles stratégies sans risque financier réel.
Fail-Safe : En cas de perte de connexion ou d'erreur API, fermer les positions ouvertes ou arrêter les nouveaux trades.

安全使用建议

This package is mixed: the visible ai-trading instructions and position_sizing.py look legitimate, but the archive contains many unrelated and potentially dangerous tools (port scanner, SQL injection tester, sandbox executor, etc.). Before installing or running anything: 1) Do not run any scripts you don't understand or that contact external hosts. 2) Ask the publisher for a trimmed package that only contains the trading files you need (SKILL.md, position_sizing.py, templates, references). 3) If you must test, run in an isolated sandbox or VM with no network access and inspect dependencies (Playwright requires browser binaries). 4) Be aware of legal/ethical rules—port scanning and automated injection tests can be illegal or abusive against third-party systems. 5) Prefer official/verified trading skills from known authors, and if you proceed, scan the files for unexpected network calls or credential access and remove offensive tools. If you want, I can list all filenames flagged as unrelated or produce a cleaned manifest containing only the trading-related files.

功能分析

Type: OpenClaw Skill Name: 12-cool-skills-openclaw-agent Version: 1.0.1 This skill bundle provides high-risk capabilities including automated vulnerability scanning (SQL injection and port scanning via sql_injector.py and port_scanner.py) and arbitrary code execution with dependency management (sandbox-script-executor). While these features are consistent with the stated purpose of a security and utility toolkit, they grant the agent broad network and shell access. No evidence of intentional malice or exfiltration was detected, but the inclusion of offensive security tools and execution environments meets the threshold for a suspicious classification.

能力评估

⚠ Purpose & Capability

The skill's declared purpose (AI trading assistant) and the runtime SKILL.md focus only on market analysis and a position sizing script. However the package contains many unrelated components (port_scanner.py, sql_injector.py, vulnerability-scanner, sandbox-script-executor, Playwright-based analyzer, etc.). Those capabilities (network scanning, SQL injection testing, sandbox execution) are not required for a trading assistant and are disproportionate to the stated purpose.

⚠ Instruction Scope

The provided ai-trading SKILL.md keeps scope to market analysis and risk management and references only position_sizing.py and templates. But many extra files and nested SKILL.md exist that instruct or enable: long-running monitoring loops (monitor.py), browser automation via Playwright (analyze_token.py), port scanning and basic SQL injection testing. Even if not referenced in the top SKILL.md, those scripts are present and could be executed by the agent if given leeway—this is scope creep and a security concern.

ℹ Install Mechanism

There is no install spec (instruction-only), which limits automatic installation risk. However the bundle includes scripts that require additional dependencies (Playwright browser, requests, network access). If the agent or a user installs dependencies or runs these scripts, the environment may be extended to run browser automation and network probing. The lack of declared required binaries/envs is inconsistent with included Playwright-based code.

⚠ Credentials

The skill declares no environment variables or credentials (appropriate for trading helper), but contains scripts that contact arbitrary hosts and perform potentially intrusive actions (port scanning, SQL injection tests, external site scraping). While no secrets are requested, the presence of offensive testing tools is disproportionate and raises abuse/legal risk if executed against third-party targets.

✓ Persistence & Privilege

Flags show always:false and normal agent invocation settings. The skill does not request persistent system-level privileges in metadata. That said, some included scripts could run indefinitely (monitor.py with 'forever') if executed—so runtime behavior could be persistent if invoked.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install 12-cool-skills-openclaw-agent
安装完成后，直接呼叫该 Skill 的名称或使用 /12-cool-skills-openclaw-agent 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.1

Initial release of the OpenClaw Multi-Skill Pack. - Added a complete AI Trading toolkit with: - RSI, Moving Average, and Support/Resistance analysis - Risk-based position sizing script - Multi-indicator validation logic - Performance tracking templates - Included security and automation tools: - Vulnerability scanner (port scanner, SQL injection tester) - Security alert detection system - Auto-watchdog monitoring scripts - Added productivity and development utilities: - API test generator - Code conversion assistant - Auto summarization templates - Sandbox script execution module - Integrated blockchain-related tools: - NFT scouting automation - Rug pull detection assistant - Added UX design reference tools and templates. This release provides a modular foundation for building powerful OpenClaw agents.

元数据

Slug 12-cool-skills-openclaw-agent

版本 1.0.1

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题