找可复用的 Agent 能力,而不只是提示词
LooksLikeCode 索引精选 ClawHub 技能,保留核心 SKILL.md 数据,并补充中文摘要、场景标签和风险提示,方便发现和复用。
描述任务,让 AI 帮你找技能
不知道该搜什么时,直接写目标。AI 会从已索引的 ClawHub 技能里筛选匹配项,并说明适用场景、风险和下一步。
Phy Dockerfile Audit
一个面向 Security 场景的 Agent 技能。原始说明:Dockerfile static security auditor. Scans any Dockerfile for 10 security issues — running as root, unpinned base images, secrets in ENV/ARG, remote ADD fetch...
Phy Otel Audit
一个面向 Security 场景的 Agent 技能。原始说明:OpenTelemetry instrumentation coverage auditor. Scans Node.js/Python/Go/Java source code to detect missing or misconfigured OTel instrumentation — HTTP handl...
Phy Social Suite
一个面向 Security 场景的 Agent 技能。原始说明:Unified social media content pipeline. One command runs the full flywheel — pulls relevant content atoms from your library, audits AI signature (LinkedIn 360...
OpenClaw Governance
一个面向 Security 场景的 Agent 技能。原始说明:Operate OpenClaw multi-agent governance with openclaw-gov — read-only audit, material change documentation, staged discovery, validate registry/runbooks, and...
Phy Crypto Audit
一个面向 Security 场景的 Agent 技能。原始说明:Weak cryptography detector (OWASP A02:2021 — Cryptographic Failures). Scans Python, JavaScript/TypeScript, Go, Java, and PHP source code for 10 classes of in...
Phy Rate Limit Audit
一个面向 Security 场景的 Agent 技能。原始说明:Missing rate limit detector for API codebases. Scans Express/Koa/Fastify/NestJS, FastAPI/Flask/Django, Go (gin/chi/echo), Spring Boot, and Ruby (Rack) for 10...
Phy Lock File Auditor
一个面向 Security 场景的 Agent 技能。原始说明:Lockfile security and integrity auditor for JavaScript, Python, Go, and Rust projects. Detects phantom dependencies (packages in lockfile but not in manifest...
audit-exec
一个面向 Security 场景的 Agent 技能。原始说明:审计多平台 exec 命令,识别高风险操作并根据白名单过滤,生成包含风险等级和说明的执行报告。
Migrate Model Defaults
一个面向 Security 场景的 Agent 技能。原始说明:Find, classify, and update hardcoded default-like model references in a repo. Use when the user wants to replace model strings, audit model defaults, central...
Claude Memory Graph Audit
一个面向 Security 场景的 Agent 技能。原始说明:审计并修复 Claude Code 的 session memory 目录(如 ~/.claude/projects//memory/)作为知识图谱的健康度。 触发场景: - 用户说"体检/审计/检查我的 memory"、"memory 库健康度"、"哪些 memory 是孤立的" - 用户说"...
AU Construction SWMS Generator
一个面向 Security 场景的 Agent 技能。原始说明:Generate compliant Australian construction Safe Work Method Statements (SWMS) for all 19 high-risk construction work categories, applying the WHS Act 2011 hi...
NDIS Progress Note Claiming
一个面向 Security 场景的 Agent 技能。原始说明:Write audit-safe NDIS progress notes with goal referencing, generate compliant shift note templates, identify correct support catalogue line item codes, and...
AU Modern Award Payroll Auditor
一个面向 Security 场景的 Agent 技能。原始说明:Audit Australian payroll for Modern Award compliance — identify the correct award and classification, verify base rates, penalty rates, overtime, allowances,...
Threat Modeling
一个面向 Security 场景的 Agent 技能。原始说明:Threat model, security audit, find vulnerabilities, check security of my app, risk assessment, penetration test prep, analyze attack surface, what could an a...
Clawdbot Security Check
一个面向 Security 场景的 Agent 技能。原始说明:Perform a comprehensive read-only security audit of Clawdbot's own configuration. This is a knowledge-based skill that teaches Clawdbot to identify hardening opportunities across the system. Use when user asks to "run security check", "audi...
ClawDefender - OpenClaw Security - Prompt injection, rogue skills etc
一个面向 Security 场景的 Agent 技能。原始说明:Security scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal attacks. Use when (1) installing new skills from ClawHub, (2) processing external input like...
Dont Hack Me
一个面向 Security 场景的 Agent 技能。原始说明:別駭我!基本安全檢測 — Security self-check for Clawdbot/Moltbot. Run a quick audit of your clawdbot.json to catch dangerous misconfigurations — exposed gateway, missing auth, open DM policy, weak tokens, loose file permissions. Auto-fix inc...
Google Calendar (via gcalcli)
一个面向 Security 场景的 Agent 技能。原始说明:Google Calendar via gcalcli: today-only agenda by default, bounded meaning-first lookup via agenda scans, and fast create/delete with verification--optimized for low tool calls and minimal output.
Security Monitor
一个面向 Security 场景的 Agent 技能。原始说明:Real-time security monitoring for Clawdbot. Detects intrusions, unusual API calls, credential usage patterns, and alerts on breaches.
security-reviewer
一个面向 Security 场景的 Agent 技能。原始说明:Use when conducting security audits, reviewing code for vulnerabilities, or analyzing infrastructure security. Invoke for SAST scans, penetration testing, DevSecOps practices, cloud security reviews.
News Aggregator Skill
一个面向 Security 场景的 Agent 技能。原始说明:Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and Weibo. Best for 'daily scans', 'tech ne...
AgentLedger
一个面向 Security 场景的 Agent 技能。原始说明:Expense tracking and accounting for AI agents. Log purchases, set budgets, generate spending reports, and manage multi-currency finances — all stored locally. Privacy.com card import, natural language queries, CSV/JSON export. Use when agen...
Security Skill Scanner
一个面向 Security 场景的 Agent 技能。原始说明:Security scanner for ClawdHub skills - detects suspicious patterns, manages whitelists, and monitors Moltbook for security threats.
Moltbot Security
一个面向 Security 场景的 Agent 技能。原始说明:Security hardening for AI agents - Moltbot, OpenClaw, Cursor, Claude. Lock down gateway, fix permissions, auth, firewalls. Essential for vibe-coding setups.