Agent skill

Re Sdr

by dslsdzc in 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.

Apache-2.0Auto-check passedSecurity

Install Re Sdr

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

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

GitHub CLI
$ gh skill install dslsdzc/rev-skills re-sdr --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-sdr .claude/skills/re-sdr && 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-sdr
GitHub stars
135
Token cost
~1.1k tokens
SKILL.md length
353 words
Files
3 (incl. references)
Skills in repo
40
Repo updated
First seen
Licence
Apache-2.0

At a glance

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.

  • Works in 5 steps: 信号采集与频谱分析 → 解调 → 帧同步与协议恢复 → …
  • 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 apt, brew and dnf

What it does

Re Sdr is an agent skill from 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。 触发词:SDR、射频、信号分析、解调、RTL-SDR、HackRF、无线协议、遥测。

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/commands.md` and `references/gotchas.md`).

It sits in Security. It works with Homebrew and macOS. 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-sdr”

Requirements

  • Python 3

Workflow steps

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

  1. 信号采集与频谱分析
  2. 解调
  3. 帧同步与协议恢复
  4. 重放与交互(授权场景)
  5. 证据整理(收尾):IQ 文件、解调位流、帧结构表(字段偏移/长度/语义)、重放记录(时间/参数/结果)对照入档;结论写 [[re-analyze/analysis-contract]]——信号级证据(截图/波形)与协议级结论(帧结构)分开归档

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:

    • apt
    • brew
    • dnf
    • pip

    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 Sdr loads about 1.1k tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 20 tokens; SKILL.md has 353 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.3k

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). 353 words, ~1,076 tokens.

Download SKILL.mdSave it as .claude/skills/re-sdr/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
re-sdr
description
射频逆向:信号采集、频谱分析、解调、帧同步与协议恢复、重放。 触发词:SDR、射频、信号分析、解调、RTL-SDR、HackRF、无线协议、遥测。
type
atomic
capabilities
rf-analysis, sdr-analysis

射频信号逆向(SDR)

何时使用 / 何时不用

  • 用:无线协议/遥控/遥测信号(IoT 无线、遥控器、遥测链路)、信号级协议恢复
  • 用:433/868/915MHz ISM 频段传感器/遥控设备快速识别(rtl_433 自带解码器,见 [[commands]])
  • 用:重放攻击验证(仅授权目标——先把帧解出来再重放,别盲放)
  • 不用:有线协议(转 [[re-protocol]]);无线 IoT 协议已封装分析(转 [[re-iot-proto]])
  • 不用:只分析已解调的数据流/应用层(直接 [[re-proto-rev]] / [[re-crypto-decrypt]])
  • 不用:多通道同时监测(单 RTL-SDR 单通道;多通道需多设备或相位一致的采集方案)

工具准备

RTL-SDR / HackRF(接收硬件)
  • 选购指引:RTL-SDR(接收,低成本入门)/ HackRF(收发,重放需要)
  • 驱动: apt install rtl-sdr / brew install rtl-sdr;HackRF: apt install hackrf / brew install hackrf
  • 验证: 硬件插入后 rtl_test 或 hackrf_info 有输出
  • 频率校准: rtl_test -p 挂几分钟读稳定 ppm 误差值,采集时 rtl_sdr ... -e <ppm> 补偿——频率偏移是解调乱码的首要原因
  • 带宽差异: RTL-SDR 稳定带宽约 2.4MHz(理论 3.2MHz 不稳);HackRF 最高 20MHz、半双工——宽带采集/主动发射选 HackRF(见 [[gotchas]])
GNU Radio(信号处理)
  • Linux: apt install gnuradio / pacman -S gnuradio;macOS: brew install gnuradio
  • Windows: 官方安装包
  • 验证: gnuradio-companion --version 或 grcc --version
  • 无头编译: grcc flow.grc 把流程图编译成可执行 Python 脚本——批量/重复解调链用文件管理比每次 GUI 拖线快
Gqrx(频谱/接收 GUI)
  • Debian/Ubuntu: apt install gqrx-sdr(注意包名带 -sdr 后缀);Arch: pacman -S gqrx;Fedora: dnf install gqrx;macOS: brew install --cask gqrx
  • 验证: gqrx --version(或 GUI 能打开并看到频谱瀑布)
  • 用途: 实时频谱/瀑布图快速定位活跃信号与中心频率,比命令行扫频直观
inspectrum(频谱/时序可视化)
  • Linux: apt install inspectrum 或源码编译;macOS: brew install inspectrum
  • 验证: inspectrum --version
  • 用途: 对录好的 IQ 文件做离线时域/频谱分析(找帧结构、符号宽度)
Universal Radio Hacker (URH)(解调与帧恢复)
  • 多平台: pip install urh
  • 验证: urh --version
  • 用途: 解调(调制识别)、位流分析(同步字/编码反转)、字段划分一体
rtl_433(ISM 频段传感器解码)
  • Debian/Ubuntu: apt install rtl-433;Fedora: dnf install rtl-433;macOS: brew install rtl_433(下划线);Arch: pacman -S rtl_433
  • 验证: rtl_433 -h 列出支持设备列表(如 0: 通用协议族、1: 温湿度计……)
  • 用途: 433/868MHz 气象站/温湿度/车库门等常见遥控协议一键解码
  • 持续输出: rtl_433 -F json -f 433.9M 按 JSON 持续打印解码结果——长时间监测/采集多个设备信号时配合日志重定向
Show full SKILL.md (181 more words)Show less

操作步骤

按顺序执行;仅限授权测试(红线:重放/交互需授权)。

  1. 信号采集与频谱分析:

    sh
    # 示例(工具可替换):GNU Radio 或命令行采集
    rtl_sdr -f 433.9M -s 1M capture.iq
    • 先全频段扫(找活跃信号)→ 定中心频率与带宽 → 采集 IQ
    • 扫描: rtl_power -f 400M:470M:250k -g 40 -i 10 scan.csv(输出 CSV,可用 gnuplot 画图)或用 Gqrx 瀑布图
    • 调制识别:频谱形状(FSK 双峰/PSK 平坦/AM 载波);Gqrx 实时看,inspectrum 离线细看
    • 采集参数: rtl_sdr -f <频率> -s <采样率> -g <增益> -n <采样数> out.iq;-g 0 自动增益
    • 采样率原则: 采样率 ≥ 2×信号带宽——窄带遥控(几十 kHz)用 250k–1M 足够,别为省事开满 2.4M 徒增文件体积
  2. 解调:

    • URH:加载 IQ → 自动/手动调制识别 → 解调出位流
    • GNU Radio:按识别结果搭解调链(AM/FM/PSK/QAM/FSK)
    • 快速监听: rtl_fm -f 433.9M -M fm -s 22050(FM 语音/FSK 音频监听,听/录音频辅助识别)
    • 产出:解调位流(0/1 序列)
  3. 帧同步与协议恢复:

    • URH 打开捕获文件 → 位流分析视图找同步字、试编码反转(NRZ/Manchester)
    • 找同步字(重复模式/固定前缀)→ 定帧边界 → 字段划分(地址/长度/载荷/CRC)
    • 多帧对照(重复发射)→ 不变字段=固定头、变化字段=数据/序号
    • 位流转字节: 先确认位序(MSB/LSB first)与长度对齐(8 的倍数)——URH 默认按位显示,转字节前核对,否则字段划分全错
    • 产出:帧结构表(字段偏移/长度/语义)
    • 已知 ISM 设备: 先跑 rtl_433 -f 433.9M -A(-A 分析模式打印解出的脉冲序列与协议猜测)——常见协议(气象站/车库门/胎压)直接命中,省去人工恢复
  4. 重放与交互(授权场景):

    • HackRF 回放捕获帧(重放攻击验证——仅授权目标):
      sh
      hackrf_transfer -r capture.iq          # 先采集(HackRF 口)
      hackrf_transfer -t capture.iq -f 433.9M -a 1 -s 2M   # 回放(-a 1 开放大器)
    • 交互式:改字段重发(滚动码/加密需先分析算法——转 [[re-crypto-id]] / [[re-crypto-decrypt]])
    • 重放前先验证采样率/增益与采集时一致——参数不匹配重放出去目标收不到(见 [[gotchas]])
  5. 证据整理(收尾):IQ 文件、解调位流、帧结构表(字段偏移/长度/语义)、重放记录(时间/参数/结果)对照入档;结论写 [[re-analyze/analysis-contract]]——信号级证据(截图/波形)与协议级结论(帧结构)分开归档

跨域联合

  • [[re-iot-proto]]:无线 IoT 协议衔接(MQTT/CoAP 等封装层)
  • [[re-protocol]]:帧结构状态机重建衔接
  • [[re-crypto-id]] / [[re-crypto-decrypt]]:载荷加密分析
  • [[re-feedback]]:信号案例经验沉淀(脱敏后)

常见坑与陷阱

  • 频率偏移/采样率错误:现象——解调全乱码;原因——中心频率偏、采样率不匹配;对策——先用已知信号(FM 广播)校准
  • 调制误判:现象——FSK 当 PSK 解;原因——频谱特征相似;对策——对照时域波形(inspectrum)再定
  • 重放需授权:现象——未授权重放触发设备动作;原因——越界操作;对策——红线:仅授权目标
  • 编码反转漏看:现象——位流全反;原因——NRZ/Manchester 未识别;对策——试反相与编码模式组合
  • 捕获不完整:现象——帧被截断;原因——带宽不够/触发时机;对策——加宽带宽、延长采集、按同步字触发
  • RTL-SDR 镜像频率/带宽限制:现象——采到的信号在错误频率出现、带宽超 2.4MHz 后解调全乱;原因——直接采样混叠、USB 传输不稳;对策——带宽 ≤2.4M、先 rtl_test -p 校准 ppm 后用 -e 补偿(详见 [[gotchas]])
  • URH 对复杂调制支持弱:现象——DSSS/OFDM/跳频信号 URH 解不出稳定位流;原因——URH 面向简单调制(ASK/FSK/PSK)设计;对策——频谱扩展类信号改用 GNU Radio 搭完整解调链(解扩/均衡),URH 只做后续位流分析
  • 硬件差异、工具特有坑见 [[gotchas]];命令速查见 [[commands]]

© 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

SKILL.md and 2 other files (references) in .claude/skills/re-sdr of dslsdzc/rev-skills.

  • SKILL.md
  • references/commands.md
  • references/gotchas.md

Open the folder on GitHubat commit bd21db8

Compare with similar skills

Re Sdr 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 Sdr compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Re Sdr this skilldslsdzc/rev-skills135—~1.1kAutomated safety check: PassApache-2.0
Ctf Cryptoljagiello/ctf-skills3.4k—~11kAutomated safety check: NotesMIT
Mole CLI Release Flowtw93/Mole70k—~2.6kAutomated safety check: PassGPL-3.0
Reproduce macOS Python FlavorsNuitka/Nuitka15k—~1.7kAutomated safety check: PassAGPL-3.0
CodexBar macOS Releasesteipete/CodexBar22k—~1.5kAutomated safety check: PassMIT
Releaseeugene1g/agent-safehouse2.1k—~3.5kAutomated safety check: PassApache-2.0

Similar skills

  • Ctf Crypto

    ljagiello/ctf-skills

    Provides cryptography attack techniques for CTF challenges. An agent skill from ljagiello/ctf-skills.

    3.4k GitHub stars~11k tokensUpdated 26 days ago
    SecurityAuto-check: notes
  • Runbook for assessing and executing a Mole CLI release: distribution channels, pre-flight checks, capital-V tags, build artifacts and the handoff to curated release notes.

    70k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Reproduce macOS Nuitka issues across Python distributions and GitHub Actions Python packaging.

    15k GitHub stars~1.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • CodexBar macOS Release

    steipete/CodexBar

    Releases a signed, notarized CodexBar build: confirms the changelog, resolves signing credentials from 1Password, runs the release script in tmux, and updates the Sparkle appcast and Homebrew tap.

    22k GitHub stars~1.5k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Release

    eugene1g/agent-safehouse

    Run the local Agent Safehouse release flow: inspect commits since the last published release, propose the next SemVer version and changelog, present a dry-run for confirmation, then update…

    2.1k GitHub stars~3.5k tokensUpdated 10 days ago
    DevelopmentAuto-check passed
  • Gearcoleco Debugging

    drhelius/Gearcoleco

    Debug and trace ColecoVision and Super Game Module games using the Gearcoleco emulator MCP server.

    142 GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check passed

More from dslsdzc/rev-skills

All 40 skills in this repo
  • 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.

    135 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed
  • APK Static Analysis

    dslsdzc/rev-skills

    Guides static analysis of an Android APK with jadx and apktool: reading the manifest, Java code, resources and permissions, and recognizing hardening or obfuscation.

    135 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed
  • 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.

    135 GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check passed
  • Re Format Elf

    dslsdzc/rev-skills

    ELF 格式解析:ehdr/phdr/shdr、GOT/PLT、initarray、符号恢复. An agent skill from dslsdzc/rev-skills.

    135 GitHub stars~1.9k tokensUpdated 5 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.

    135 GitHub stars~1.4k tokensUpdated 5 days ago
    Auto-check passed
  • Re Frida

    dslsdzc/rev-skills

    Frida 动态插桩(桌面+移动统一). An agent skill from dslsdzc/rev-skills.

    135 GitHub stars~2.8k tokensUpdated 5 days ago
    Auto-check passed

Works with

Categories

Questions about Re Sdr

What does Re Sdr do?

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. Re Sdr is an agent skill from dslsdzc/rev-skills.

When should I use Re Sdr?

Re Sdr fits situations like: security work in your project.

How do I install Re Sdr in Claude Code?

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

How do I install Re Sdr in Codex?

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

Can I use Re Sdr 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-sdr -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-sdr, .gemini/skills/re-sdr, .github/skills/re-sdr and .opencode/skills/re-sdr in your project.

What does Re Sdr need to run?

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

Does Re Sdr 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 Sdr 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 Sdr use?

Re Sdr 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 Sdr use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.

What are the alternatives to Re Sdr?

Skills that share tags, products or a category with Re Sdr: Ctf Crypto (ljagiello/ctf-skills, 3.4k stars), Mole CLI Release Flow (tw93/Mole, 70k stars), Reproduce macOS Python Flavors (Nuitka/Nuitka, 15k stars) and CodexBar macOS Release (steipete/CodexBar, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Re Sdr?

dslsdzc (a GitHub user) maintains it in dslsdzc/rev-skills, which has 135 GitHub stars. The repository holds 40 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.