Agent skill

Re Crypto Decrypt

by dslsdzc in dslsdzc/rev-skills

加密数据还原:定位解密函数、写解密脚本. An agent skill from dslsdzc/rev-skills.

Apache-2.0Auto-check passedSecurity

Install Re Crypto Decrypt

skills CLI
$ npx skills add dslsdzc/rev-skills --skill re-crypto-decrypt -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dslsdzc/rev-skills re-crypto-decrypt --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/dslsdzc/rev-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/re-crypto-decrypt .claude/skills/re-crypto-decrypt && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
re-crypto-decrypt
GitHub stars
125
Token cost
~1.8k tokens
SKILL.md length
518 words
Files
1
Skills in repo
41
Repo updated
First seen
Licence
Apache-2.0

At a glance

加密数据还原:定位解密函数、写解密脚本. An agent skill from dslsdzc/rev-skills.

  • Works in 6 steps: 证伪"密文":先定位真实密文边界(跳过此步是加密分析最常见的失败方式) → 定位解密函数(交叉引用密文输入点) → 反编译还原算法 → …
  • Security work in your project
  • SKILL.md covers 何时使用 / 何时不用, 工具准备, 操作步骤 and 跨域联合, plus 1 more section
  • Calls pip, python3 and apt

What it does

Re Crypto Decrypt is an agent skill from dslsdzc/rev-skills. 加密数据还原:定位解密函数、写解密脚本。 触发词:解密、decrypt、还原数据、解密流量

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Security. It works with Python. The repository describes itself as: 122 个逆向工程 AI 技能(可发布、跨平台):恶意软件分析 / 软件逆向 / 固件嵌入式 / 协议逆向 / 移动应用 / 脱壳反混淆 / 软件破解 / 漏洞挖掘 / 托管代码 / 取证情报 / CTF。 The licence is Apache-2.0.

When your agent uses it

  • Security work in your project

Example prompts

  • “/re-crypto-decrypt”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 证伪"密文":先定位真实密文边界(跳过此步是加密分析最常见的失败方式)
  2. 定位解密函数(交叉引用密文输入点)
  3. 反编译还原算法
  4. 重写为独立脚本(python)
  5. 用已知明文验证
  6. 流量场景:解出明文流量流

What it can do on your machine

Read from SKILL.md and the folder at commit bd21db8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip
    • python3
    • apt
    • dnf
    • brew
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Re Crypto Decrypt loads about 1.8k tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 518 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~16
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from dslsdzc/rev-skills at commit bd21db8, republished under its Apache-2.0 licence (© dslsdzc). 518 words, ~1,837 tokens.

Download SKILL.mdSave it as .claude/skills/re-crypto-decrypt/SKILL.md (or your agent's skills folder).
name
re-crypto-decrypt
description
加密数据还原:定位解密函数、写解密脚本。 触发词:解密、decrypt、还原数据、解密流量
capabilities
crypto-decryption

加密数据还原

何时使用 / 何时不用

  • 用:需要把密文(数据 blob / 流量 / 配置段)还原成明文
  • 用:算法与密钥已知(或已由 [[re-crypto-id]] / [[re-crypto-keys]] 得出),需要批量解密
  • 用:从样本里还原解密逻辑并重写为独立可复用的脚本
  • 不用:算法/密钥都未知(先 [[re-crypto-id]] → [[re-crypto-keys]])
  • 不用:静态可读的明文([[re-triage]] 熵低直接读)
  • 不用:想跑原样本看输出(那是 [[re-behavior]] / [[re-sandbox]] 的活——解密脚本是为了脱离样本复现)

工具准备

所有工具先验证再使用。本技能处理的是转储/反编译产物与密文数据,运行样本环节在 [[re-sandbox]] 内([[re-analyze/platform-tips]] 最高原则)。

python3 + pycryptodome —— 解密脚本主力
  • Linux: apt install python3 python3-pip / dnf install python3 python3-pip / pacman -S python python-pip
  • macOS: brew install python
  • Windows: python.org 安装包(勾选 Add to PATH);WSL 内 Linux 版
  • 加密库: pip install pycryptodome(AES/DES/RSA/ChaCha 等标准算法)
  • 验证: python3 -c "from Crypto.Cipher import AES; print('ok')";python3 --version
目标程序转储/反编译产物 —— 还原算法的依据
  • 转储: [[re-memdump]] 默认转储(gcore)——定位密文输入点与解密调用现场
  • 反编译: [[re-ghidra]] / [[re-ida]] / [[re-radare2]] 的产物(函数反编译视图)
  • 验证: file out 是 ELF core;反编译器里能找到目标函数(ghidra / rizin 可启动)
angr(可选)—— 符号执行补足难还原的逻辑
  • 全平台: pip install angr——Python 版本兼容性以 [[re-angr]] 的「工具准备」为准(版本矩阵只在该处维护一份,避免多处漂移);依赖多,建议 venv: python3 -m venv venv && venv/bin/pip install angr
  • 验证: venv/bin/python -c "import angr; print(angr.__version__)"
  • 用途: 反编译分支爆炸/混淆严重时,用符号执行求解密函数输出(加载目标二进制 → 设密文输入为符号 → 约束求解)

操作步骤

按顺序执行,每步记下结果。前提:算法([[re-crypto-id]])与密钥([[re-crypto-keys]])已确认或至少有一方候选;脚本与验证结果(明文样本 + sha256)存档供报告引用。

  1. 证伪"密文":先定位真实密文边界(跳过此步是加密分析最常见的失败方式):

    • 高熵段可能是"伪密文"——容器/压缩数据流被误当加密层(如 zip 数据本体、附加在图片后的压缩流)。压缩数据熵同样是 8.0,与加密不可区分
    • 先做整体结构观察:文件头/尾魔数、格式 marker 分布(JPEG 逐段统计大小)、尾部已知结构当锚点(zip EOCD 的 cd_offset/cd_size 反推数据起点,EOCD 签名是已知明文)
    • 定格式边界不要用 first/last 裸 marker 搜索:标记字节对可以合法出现在载荷里——PNG 的 IEND 字样可落在 tEXt chunk 数据内、JPEG 的 FF D9 可落在 APP1 等 length-delimited 段内(拿首个命中当结尾会截掉合法数据)。正确做法是按格式规范解析:PNG 从 8 字节签名起按 Length/Type/Data/CRC 逐 chunk 遍历,直到结构合法且长度为 0 的 IEND(必要时逐块验 CRC);JPEG 从 SOI 起按 marker/segment 解析,进入 SOS 后按 FF00 stuffing 与 RSTn 规则处理,语法位置成立的 EOI 才是结尾。裸字节搜索只能用来产生候选位置,候选要经结构校验后才能定边界
    • 同尺寸文件先比尾部 16 字节/整体哈希——"换头副本"(同一 payload 的第二种封装,仅头部不同)直接省掉一整条支线
    • 压缩率是信号:解压后明显变大的层说明内容有结构(可压=编码/明文),接近 1:1 说明内层已压缩或加密
    • 确认是孤立高熵 blob 后再进入步骤 1 的密文定位
  2. 定位解密函数(交叉引用密文输入点):

    • 从密文偏移出发:[[re-crypto-id]] 步骤 2 的高熵区偏移 → 反编译器里找读取该偏移/该全局变量的函数 → 沿调用链看谁写入了它(写入方常是解密函数)
    • 从 API 出发:[[re-crypto-keys]] 步骤 4 找到的 Crypt*/EVP_* 调用点就是候选;观察入参的密文指针是否指向步骤 2 的偏移
    • 动态辅助: [[re-gdb]] / [[re-x64dbg]] 在候选函数下断点(沙箱内),打印入参/返回值,确认它输出可读明文
    • 找不到明确函数 → 密文可能由内联展开的算法处理(无调用边界),回 [[re-crypto-id]] 用数据特征定位(常量表引用处)
  3. 反编译还原算法:

    • 把反编译视图逐段抄译成伪代码,明确:算法(AES-CBC/自定义 XOR…)、密钥与 IV 来源(固定值/派生/上下文)、模式与填充(CBC 的 IV 在哪、PKCS7 还是零填充)
    • 自定义算法: 逐条翻译位运算(XOR/移位/查表),注意字节序([[re-proto-rev]] 坑 1 同理——长度/密钥字段先试大小端)
    • 还原标准算法时留意细节:AES 用 CBC 还是 ECB、key 长度 16/24/32、IV 是否复用密钥(常见错误实现,见坑 1)
    • 反编译看不清的循环/查表逻辑 → angr 符号执行兜底(构造求解脚本,把函数当黑盒求输出)
  4. 重写为独立脚本(python):

    python
    # decrypt.py —— 按反编译还原的算法重写
    from Crypto.Cipher import AES
    import sys
    key = bytes.fromhex("...")          # 来自 [[re-crypto-keys]] 步骤 1/2/5
    iv  = key[:16]                       # 样本实现: IV = key 前 16 字节
    data = open(sys.argv[1], 'rb').read()
    pt = AES.new(key, AES.MODE_CBC, iv).decrypt(data)
    print(pt)                            # 或写文件 + 后续校验
    • 脚本参数化(密钥/IV/输入文件走参数或配置),一次写对、反复复用——批量解流量用
    • 关键:脚本逻辑必须与样本一致(填充处理、尾部截断),不一致时回查边界条件(见坑 1)
  5. 用已知明文验证:

    • 已知明文来源:协议头 magic(如 \xAA\x55)、文件头(PK zip / \x89PNG)、报文字段([[re-proto-rev]] 步骤 2 的固定头)、或 [[re-behavior]] 行为里观察到的明文串
    • 验证方式:解密输出里能找到已知明文片段 → 成功;找不到 → 依次检查:密钥/IV 是否对([[re-crypto-keys]] 候选逐个试)、字节序、填充处理、是否还有外层加密(见坑 3)
    • 无已知明文时用"可读性"验证:输出可打印率 >70% 或通过 file - 识别出格式(PDF/zip/文本)→ 视为成功候选
  6. 流量场景:解出明文流量流:

    • 已按 [[re-crypto-id]] / [[re-crypto-keys]] 确认流量加密算法与密钥后,从 pcap 提取密文载荷([[re-netcap]] 步骤 3 tshark 导出):
      sh
      tshark -r c2.pcap -Y 'tcp.payload' -T fields -e data.data | sed 's/://g' | xxd -r -p > payloads.bin
    • 写批量脚本:按流切分(每 TCP 流一段)、逐段调用解密逻辑(同步骤 3 的脚本),输出明文流文件
    • 验证: 明文流里能看到协议结构(会话序号/命令字),再转 [[re-proto-rev]] 做状态机重建
    • 注意会话密钥变化(每次握手重新派生)→ 脚本里为每个会话取对应密钥([[re-crypto-keys]] 步骤 5 的派生还原)
Show full SKILL.md (205 more words)Show less

跨域联合

  • [[re-protocol]]:本网关工作流第 4 步(解密)——加密通信链路的落地点(crypto-id → crypto-keys → crypto-decrypt → proto-rev)
  • [[re-malware]]:C2 流量解密——re-malware 第 4 步;解出的明文(指令/配置)进行为判断与 IOC([[re-ioc]])
  • [[re-firmware]]:固件加密层/加密通信解密——配合 [[re-fw-extract]] 解包失败时的加密层处理
  • [[re-crypto-id]] / [[re-crypto-keys]]:上游——算法与密钥的输入来源
  • [[re-memdump]]:密文输入点定位与解密调用现场(转储产物)
  • [[re-anti-analysis]]:解密在壳内时先脱壳(见坑 2);[[re-gdb]] / [[re-x64dbg]] 动态辅助确认函数行为
  • 解出的明文转 [[re-proto-rev]] 重建状态机,或按 [[re-firmware]] / [[re-malware]] 流程继续

常见坑与陷阱

  • 还原脚本与样本行为不一致 → 回查边界条件(长度/填充):现象——脚本解出的明文与样本自身输出不一样(多/少字节、尾部乱码);原因——边界条件没对齐:填充方式(PKCS7/zero)、长度字段是否含填充、IV 是否每包变、密文尾部是否截断;对策——反编译里逐条核对填充与长度处理代码,脚本里显式实现,再回步骤 4 用已知明文验证
  • 解密在壳内 → 先脱壳:现象——在加壳样本里找不到解密函数,或找到的函数只是壳的解压;原因——密文数据/解密逻辑被壳包着,静态看是壳的初始状态([[re-memdump]] 坑 2 同理);对策——先 [[re-anti-analysis]] 脱壳(按明文/代码 materialization 定转储时机,不把 OEP 当通用判据),脱壳产物重新做定位
  • 多轮解密链:现象——解出第一层后仍是乱码/高熵(熵 7.0+);原因——多层加密(先 XOR 再 AES,或嵌套压缩+加密,见 [[re-crypto-id]] 坑 3);对策——每层单独验证(解一层测一次熵与可读性),分层还原;可用"熵下降即前进一层"作为停止条件
  • 密钥/IV 顺序用错解出乱码:现象——已知明文验证失败,但算法确定是 AES;原因——key/iv 参数顺序(样本是 key||iv 拼接还是分开传)、密钥字节序、或 IV 复用/固定 IV;对策——把 [[re-crypto-keys]] 的候选(含大小端变体、IV=key 前缀等常见错误实现变体)做成参数组合循环试解,命中即可读性/已知明文判定
  • 受限符号集 = 编码不是加密(伪加密):现象——熵 7.9+ 但字节值域明显受限(如只有 66 个符号、分布均匀、无周期),xortool/IC 对所有密钥长度全平;原因——这是"编码 + 单字节 XOR":单字节 XOR 不改变频率分布与符号集(只平移值),多字节 XOR 才会把符号打散成 256 值;对策——收集全部符号值集合,与已知字符集做 XOR 匹配(对 256 个 key 做集合比较,毫秒级,别用穷举):Base64 64 字符 + \n + = = 66 符号、Ascii85 85、hex 16 等;命中后 XOR 还原 → 解码;交叉验证:填充符(如 = 加密后仅出现 1 次在文件尾)、换行符频率、解码后魔数
  • xortool/IC 结果全平 = 换思路的信号:现象——密钥长度候选全部 ~10-20% 且无突出峰值;结论——统计上不存在周期结构,多字节重复密钥 XOR 基本排除,别换参数继续跑;对策——退回观察数据本身(值域/符号集/熵),通常是编码层或一次性密钥流(流密码)
  • 伪密文已确认但层数不止一层 → 分层剥离纪律:每层剥完用魔数/可读性验证产物完整性再进下一层;中间产物全部保留命名(可回滚);熵不降 / 解出仍高熵 = 还有外层(如 XOR 外再 Base64、再压缩)
  • 像素级 XOR(视觉密码学/图像隐写):现象——两张"随机噪点"图,题目提示叠加;原因——视觉密码学把信息分成两张 share,XOR(或 ADD)像素后可见;对策——ImageChops.logical_xor 或 numpy a^b 逐像素 XOR 两图(RGB 三通道);结果常是"99.5% 纯白背景 + 极浅灰文字"(文字 254 vs 背景 255)——直接看/反色都不可见,用阈值增强:==255 → 黑、其余 → 白,文字立现;位图小字再按字符网格(5x7)切分逐字读,重复字符用两两位图相似度矩阵验证(如 d562333d 的重复模式)
  • ADD 饱和加法是 XOR 的近亲:现象——XOR 结果无内容时;原因——share 可能由加法式秘密共享生成(XOR 得到噪声,ADD/SUB 才出图);对策——同样试 clip(a+b) 饱和加法与 a-b 减法,多运算组合对比
  • 新版混淆重 → 老版本回溯定位:现象——最新版核心函数混淆后体积异常庞大,IDA 分析卡顿,硬啃不现实;原因——同一 SDK 早期版本未上重混淆,核心逻辑更清晰;对策——按行为特征(如"同意隐私协议即触发采集")装历史版本包(豌豆荚等渠道)→ 点同意 → 抓包确认最早出现该参数的版本;选行为规范的版本做分析起点(调试方便:spawn/attach 都能复现);老版本还原出的逻辑反过来指导确认新版采集了哪些参数
  • 分段/分层加密上报(每段算法不同):现象——抓到的上报请求字段单看都像密文,但统一按一种算法解全是乱码;原因——客户端加密流程分多段:单字段加密 → 分段加密 → 整体加密,每段的算法/密钥不同(如第一层随机数做 key 逐字节加密、第二层固定 key、第三层拼接组合字段后再加密);且字段本身可能是设备采集的风险特征(svc 指令采集、r_1_0 类字段);对策——按"每层单独验证"纪律分层剥(熵降/可读即前进一层,见多轮解密链坑);注意同源 SDK 的"整体加密"可能再套 VM 化算法(约 70 个 handle 模拟基本指令、handle 未混淆时可逐个识别指令语义);key 来源分随机(抓包不可复现)与固定(可静态找)两类,先固定后随机
  • 双重 AES + 加密字符串(key/iv 也加密存):现象——确认 AES 后直接解仍失败,或 key/iv 每次会话都变;原因——实现常见套路:第一层 key/iv 固定(以加密字符串形式硬编码在 so,运行时经解密函数解出),第二层 key/iv 每次变化;两次加密间拼接固定前缀(如 03000001)再进同一函数;且加解密可能是同一函数(标志位控制方向);对策——hook 解密函数返回点批量导出全部解密字符串(JNI_OnLoad 前 memcpy 的加密串 → 全局变量 → 解密函数),key/iv 直接在其中搜索;找加密点用 findcrypt 扫特征常量(AES S-box 等)→ xref 定位校验 key/iv 长度(16)的函数;动态 hook 打印两次调用前后数据对照验证

© dslsdzc, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/re-crypto-decrypt of dslsdzc/rev-skills.

Open the folder on GitHubat commit bd21db8

Compare with similar skills

Re Crypto Decrypt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Re Crypto Decrypt compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Re Crypto Decrypt this skilldslsdzc/rev-skills125—~1.8kAutomated safety check: PassApache-2.0
C To AstNarwhal-Lab/MagicSkills316—~1.1kAutomated safety check: PassMIT
Security AuditTheDecipherist/claude-code-mastery550—~1.3kAutomated safety check: NotesMIT
Vpn Security CheckSergei-thinker/vpn-setup189—~1.5kAutomated safety check: NotesMIT
Banditalpha-omega-security/scrutineer231—~615Automated safety check: NotesMIT
Python Reviewliuyanghejerry/Clausura204—~164Automated safety check: PassMIT

Similar skills

  • C To Ast

    Narwhal-Lab/MagicSkills

    Parse C source code into an Abstract Syntax Tree (AST). An agent skill from Narwhal-Lab/MagicSkills.

    316 GitHub stars~1.1k tokensUpdated 6 mo ago
    SecurityAuto-check passed
  • Security Audit

    TheDecipherist/claude-code-mastery

    Checks a codebase for hardcoded secrets, vulnerable dependencies, weak input handling, weak authentication and unsafe transport settings before deployment or merge.

    550 GitHub stars~1.3k tokensUpdated 5 mo ago
    SecurityAuto-check: notes
  • Vpn Security Check

    Sergei-thinker/vpn-setup

    Infrastructure security audit for VPN server. An agent skill from Sergei-thinker/vpn-setup.

    189 GitHub stars~1.5k tokensUpdated 5 mo ago
    SecurityAuto-check: notes
  • Bandit

    alpha-omega-security/scrutineer

    Run bandit against the Python source in the repository and map its hits into the findings shape.

    231 GitHub stars~615 tokensUpdated today
    SecurityAuto-check: notes
  • Python Review

    liuyanghejerry/Clausura

    Python 遗留代码审查:bare except、SQL 注入、反序列化、密钥、调试输出. An agent skill from liuyanghejerry/Clausura.

    204 GitHub stars~164 tokensUpdated 9 days ago
    SecurityAuto-check passed
  • Security Setup

    luongnv89/skills

    Install local-first security hardening: pre-commit secret detection, offline dependency scans, static analysis, reports, and gated free CI.

    131 GitHub stars~4.5k tokensUpdated yesterday
    SecurityAuto-check passed

More from dslsdzc/rev-skills

All 41 skills in this repo
  • Re Attribution

    dslsdzc/rev-skills

    威胁归因方法论:钻石模型、基础设施图谱、置信度分级与归因报告. An agent skill from dslsdzc/rev-skills.

    125 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Captures an analyzable sample from a live system when the target leaves no file on disk, by finding abnormal executable memory and the execution context that reached it.

    125 GitHub stars~2k tokensUpdated 3 days ago
    Auto-check passed
  • Re Fp Runtime

    dslsdzc/rev-skills

    函数式语言运行时逆向(Haskell/OCaml):闭包/堆对象模型、调用约定、数据流优先策略. An agent skill from dslsdzc/rev-skills.

    125 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Re Hypervisor

    dslsdzc/rev-skills

    虚拟化逆向:VT-x/SVM、hypervisor 检测、VMCS/EPT 分析, 以及 Xen / QNX Hypervisor / Jailhouse / ACRN / Bao / Hyper-V·VMBus / XtratuM / LynxSecure / Quest-V 的分区与 vdev 语义。

    125 GitHub starsUsed in 1 repo~3.4k tokens
    Auto-check: notes
  • Re Sdr

    dslsdzc/rev-skills

    射频逆向:信号采集、频谱分析、解调、帧同步与协议恢复、重放. An agent skill from dslsdzc/rev-skills.

    125 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Re Uefi

    dslsdzc/rev-skills

    UEFI/BIOS 固件:SEC/PEI/DXE/BDS 阶段判定、DXE 驱动、UEFI 模块、bootkit. An agent skill from dslsdzc/rev-skills.

    125 GitHub starsUsed in 1 repo~2.3k tokens
    Auto-check passed

Works with

Categories

Questions about Re Crypto Decrypt

What does Re Crypto Decrypt do?

加密数据还原:定位解密函数、写解密脚本. An agent skill from dslsdzc/rev-skills. Re Crypto Decrypt is an agent skill from dslsdzc/rev-skills.

When should I use Re Crypto Decrypt?

Re Crypto Decrypt fits situations like: security work in your project.

How do I install Re Crypto Decrypt in Claude Code?

Run `npx skills add dslsdzc/rev-skills --skill re-crypto-decrypt -a claude-code`. Or copy the skill folder (.claude/skills/re-crypto-decrypt in dslsdzc/rev-skills) into .claude/skills/re-crypto-decrypt in your project. Claude Code loads it when a task matches its description.

How do I install Re Crypto Decrypt in Codex?

Run `npx skills add dslsdzc/rev-skills --skill re-crypto-decrypt -a codex`. Or copy the skill folder (.claude/skills/re-crypto-decrypt in dslsdzc/rev-skills) into .agents/skills/re-crypto-decrypt in your project. Codex loads it when a task matches its description.

Can I use Re Crypto Decrypt in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dslsdzc/rev-skills --skill re-crypto-decrypt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/re-crypto-decrypt, .gemini/skills/re-crypto-decrypt, .github/skills/re-crypto-decrypt and .opencode/skills/re-crypto-decrypt in your project.

What does Re Crypto Decrypt need to run?

Going by SKILL.md and its folder, Re Crypto Decrypt needs the command-line tools its instructions call (pip, python3, apt, dnf, brew and python). Our summary lists: Python 3.

Does Re Crypto Decrypt access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Re Crypto Decrypt safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Re Crypto Decrypt use?

Re Crypto Decrypt is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Re Crypto Decrypt use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Re Crypto Decrypt?

Skills that share tags, products or a category with Re Crypto Decrypt: C To Ast (Narwhal-Lab/MagicSkills, 316 stars), Security Audit (TheDecipherist/claude-code-mastery, 550 stars), Vpn Security Check (Sergei-thinker/vpn-setup, 189 stars) and Bandit (alpha-omega-security/scrutineer, 231 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Re Crypto Decrypt?

dslsdzc (a GitHub user) maintains it in dslsdzc/rev-skills, which has 125 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 5, 2026.

Source: dslsdzc/rev-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.