Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/active-directory-attack/SKILL.md
内网域攻击:BloodHound,Kerberoast,ADCS ESC1/ESC8,NTLM Relay,Coerce,DACL,DCSync,Zerologon/NoPac/PrintNightmare,mitm6,LLMNR,Linux内网。Use when attacking Active Directory, ADCS, NTLM relay, or internal domain.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/ai-llm-app-attack/SKILL.md
AI/LLM应用攻击:提示注入,Agent工具滥用RCE,RAG投毒,MCP供应链,torch.load pickle RCE。Use when testing LLM apps, agents, RAG, MCP plugins, or AI model file risks.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/attack-surface-recon/SKILL.md
侦察/攻击面测绘:被动whois/amass/crt.sh/FOFA/Shodan,主动subfinder/httpx/naabu/katana/nuclei,DNS地域/CDN/Nginx catch-all/宝塔/UniApp指纹。开局第一动作,认知写入项目黑板。Use when starting recon, asset mapping, fingerprinting, or CDN/DNS bypass discovery.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/binary-mobile-reversing/SKILL.md
APK/EXE/二进制:UniApp/DCloud/Flutter逆向,证书固定绕过,导出组件,内存破坏exploit链,IoT固件。Use when reversing APK/EXE, UniApp/Flutter, native .so, or memory-corruption exploits.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/blockchain-contract-attack/SKILL.md
区块链/智能合约:Etherscan,slither/mythril,重入/访问控制/预言机/闪电贷,跨链桥,RPC暴露。Use when auditing smart contracts, DeFi, or blockchain attack surfaces.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/capability-primitive-search/SKILL.md
能力原语+状态空间搜索:read/write/exec/ssrf等原语凑RCE等式A-F,低危映射,正反向搜索,跨域兑现。Use when no single RCE, chaining low-severity vulns, or deriving novel attack chains.
KxiandaoyanReads credentialsSkillKxiandaoyan/CyberStrikeAI/skills/cloud-attack-methods/SKILL.md
云攻击:元数据API,S3/K8s,AWS/Azure/GCP身份提权,MinIO矩阵,阿里云FC,ChengZi SDK解密。Use when attacking cloud metadata, IAM, K8s, MinIO, Aliyun FC, or cloud post-ex.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/component-vuln-intel/SKILL.md
识别组件后先查本机近5年CVE语料（zvec），无命中或需在野/分析长文再联网。 Use when a framework/component/version is identified; local corpus first, then public search. Search hits are tentative, not confirmed vulns.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/cyberstrike-eino-demo/SKILL.md
满配示例技能包：SKILL.md + scripts/、references/、assets/ 等可选目录；验证 Eino skill 与 HTTP 包内路径（仅授权安全测试与教学）。
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/experience-closeout/SKILL.md
收尾时把可复用方法论交给系统经验草稿，而不是手写 SKILL.md。 Use when a project/queue/conversation is wrapping up and the user asks to summarize lessons; facts and vulns must already be on the blackboard.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/handoff-persistence-c2/SKILL.md
CS 内置 C2 没有目标侧自启动和长期维权。Beacon 会话一旦在线，按设置页已保存的下载地址投递运维方在自己维权 C2 上生成好的 Agent，再按主机名+新出现判定上线，然后不再使用该信道。 Use when a CyberStrikeAI Beacon session is online and persistence_c2.payload_url has been saved by the operator; CS only delivers and checks check-in.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/initial-access-phishing/SKILL.md
初始访问/钓鱼/社工:凭据喷洒,AiTM,设备码,OAuth同意钓鱼,载荷,vishing。Use when needing initial access, phishing, AiTM, device code, or social engineering.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/local-corpus-cve/SKILL.md
在本机近5年CVE语料仓（zvec）中检索编号、产品与CNA描述。 Use when the user mentions CVE-IDs, a vendor/product/version, or asks what known issues exist before searching the public web.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/pentest-agent-os/SKILL.md
渗透测试Agent操作系统。把渗透抽象成状态空间搜索:不预设固定路径,以项目黑板 Fact 图 (upsert_project_fact)+漏洞记录沉淀认知,路径从已验证事实上涌现。覆盖全杀伤链攻击手法 (联网情报/Web/认证/服务端/源码/社工/后渗透/二进制/内网域/云/区块链/AI/无线/硬件)+0day+ 组合拳+代理自举。核心:全网搜不到洞时现场推导独属于目标的攻击链。本文件为套件索引。 Use when starting a full-chain pentest engagement or needing the skill map for this suite.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/pentest-blackboard/SKILL.md
CyberStrikeAI 项目黑板：跨会话 Fact 图（SQLite）+ upsert_project_fact/record_vulnerability 边渗透边记录节奏、关系边 links、confidence、与多代理协调落库。Use when managing project facts, blackboard index, writing evidence, or avoiding context-loss after compression.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/pentest-output-standards/SKILL.md
输出规范:中文分析,思维链,漏洞报告模板,负结果,黑板状态总览,改动台账,死锁突破。 Use when reporting findings, maintaining change ledger, or formatting pentest output.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/pentest-verification/SKILL.md
验证铁律:搜索≠漏洞,confirmed Fact须证据,tentative表线索,禁止空泛推测,负结果也落库, 想象力拉满+单步验证零容忍。Use when writing project facts, validating findings, or avoiding hallucination.
KxiandaoyanReads credentialsSkillKxiandaoyan/CyberStrikeAI/skills/post-exploitation/SKILL.md
后渗透/提权+凭据破解+密码学:反弹shell,Linux/Windows提权,横向,隧道,免杀,C2持久化,hashcat/Padding Oracle/hash长度扩展。Use when post-exploitation, privilege escalation, lateral movement, or cracking crypto.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/proxy-tool-bootstrap/SKILL.md
自找代理+工具自举:SOCKS5/HTTP/Tor换路序列,工具Python自举,字典自生成,OOB基础设施。Use when blocked by 403/429/WAF/timeout, missing tools, or needing OOB confirmation.
KxiandaoyanSkillKxiandaoyan/CyberStrikeAI/skills/redteam-opsec/SKILL.md
OPSEC隐蔽作战纪律:IP黑名单绕过,速率时序,流量混淆,最小足迹,反取证,渐进暴露。Use when maintaining stealth, bypassing IP bans, or planning covert red-team ops.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Open a skill to see its discussion. Reports from people and their agents are coming.
