Agent skill

Re AI Model

by dslsdzc in dslsdzc/rev-skills

AI 模型文件逆向与静态分析:ONNX/PyTorch/Safetensors/TFLite 格式解析、 网络结构还原、权重提取、文件级水印分析(权重 pattern/metadata/tensor hash/embedding 异常)。

Apache-2.0Auto-check passedAI & LLM Engineering

Install Re AI Model

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

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

GitHub CLI
$ gh skill install dslsdzc/rev-skills re-ai-model --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-ai-model .claude/skills/re-ai-model && 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-ai-model
GitHub stars
130
Token cost
~2.4k tokens
SKILL.md length
536 words
Files
1
Skills in repo
40
Repo updated
First seen
Licence
Apache-2.0

At a glance

AI 模型文件逆向与静态分析:ONNX/PyTorch/Safetensors/TFLite 格式解析、 网络结构还原、权重提取、文件级水印分析(权重 pattern/metadata/tensor hash/embedding 异常)。

  • Works in 5 steps: 模型格式识别(onnx / safetensors / pytorch pkl… → 结构解析(图/层/算子) → 权重提取(张量 dump) → …
  • Tasks that involve Deep learning
  • 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 python3, pip and brew; reaches download.pytorch.org

What it does

Re AI Model is an agent skill from dslsdzc/rev-skills. AI 模型文件逆向与静态分析:ONNX/PyTorch/Safetensors/TFLite 格式解析、 网络结构还原、权重提取、文件级水印分析(权重 pattern/metadata/tensor hash/embedding 异常)。 触发词:模型文件、权重提取、ONNX解析、safetensors、pth分析、pt文件、模型结构还原、文件级水印

Its SKILL.md is about 2.4k 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 AI & LLM Engineering, covering Deep learning and Embeddings. It works with ONNX, Python, PyTorch and TensorFlow. 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

  • Tasks that involve Deep learning
  • Tasks that involve Embeddings

Example prompts

  • “/re-ai-model”

Requirements

  • Python 3

Workflow steps

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

  1. 模型格式识别(onnx / safetensors / pytorch pkl / tflite)
  2. 结构解析(图/层/算子)
  3. 权重提取(张量 dump)
  4. 模型水印/指纹检测(嵌入权重)
  5. 模型窃取判定(架构相似度)

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:

    • python3
    • pip
    • brew
    • apt
    • dnf
    • choco
    • winget

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • download.pytorch.org

    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 AI Model loads about 2.4k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 536 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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). 536 words, ~2,361 tokens.

Download SKILL.mdSave it as .claude/skills/re-ai-model/SKILL.md (or your agent's skills folder).
name
re-ai-model
description
AI 模型文件逆向与静态分析:ONNX/PyTorch/Safetensors/TFLite 格式解析、 网络结构还原、权重提取、文件级水印分析(权重 pattern/metadata/tensor hash/embedding 异常)。 触发词:模型文件、权重提取、ONNX解析、safetensors、pth分析、pt文件、模型结构还原、文件级水印
capabilities
ai-model-analysis

AI 模型逆向(ONNX / PyTorch / Safetensors)

何时使用 / 何时不用

  • 用:拿到 .onnx / .pt / .pth / .safetensors / .tflite 等模型文件,要还原网络结构、提取权重
  • 用:文件级水印检测(东西藏在哪里:权重 pattern / metadata / tensor hash / embedding 异常——怀疑模型是从原版复制/微调而来时先查文件侧)
  • 用:模型文件本身是载荷——权重里藏数据、torch.save 打包恶意 pickle、后门/投毒模型(下载执行类样本)
  • 不用:行为级水印(模型表现出来是什么:trigger 触发响应 / 查询响应 / 黑盒指纹)与 API 行为层攻击(走 [[re-ai-attack]])
  • 不用:纯推理脚本/训练代码(那是源码,走 [[re-script-deob]])
  • 不用:模型被打包进可执行文件(PyInstaller/pyarmor 等)——先 [[re-binary-core]] 拆包,拆出的模型文件再回本技能
  • 边界:本技能定位 = 模型文件解析 / 结构分析 / 权重分析 / 文件级水印——恶意模型判定、投毒/后门行为侧、归属取证属取证域(未来独立 re-ai-malware 技能承接;当前此类需求暂在本技能范围,以安全边界(坑 2 pickle 隔离)处理,行为侧转 [[re-ai-attack]])
  • 注意:安全提示——不要直接 torch.load 未知 pkl 文件(pickle 反序列化可执行任意代码,见坑 2);一切对未知 pkl 的加载默认隔离环境([[re-analyze/platform-tips]] 沙箱最高原则),先读后跑;模型解析/权重提取为静态步骤,可免沙箱

工具准备

参考 [[re-analyze/platform-tips]]——模型文件 GB 级常见,静态分析按「静态优先(大型样本)」思路:先格式识别与结构解析,按需提取权重,不整载内存(坑 1)。

python3 —— 所有解析脚本基础
  • Linux: apt install python3 / dnf install python3 / pacman -S python
  • macOS: brew install python3;Windows: choco install python
  • 验证: python3 --version(本技能脚本均为 Python 3)
onnx(pip,Python 3.10+)—— ONNX 解析主力
  • pip install onnx(官方 PyPI;当前 onnx 要求 Python 3.10+,具体版本以 PyPI Requires-Python 为准;自带 protobuf 依赖与 onnx.proto3 类型定义)
  • 验证: python3 -c "import onnx; print(onnx.__version__)"
netron(pip,Python 3)—— 模型可视化
  • pip install netron(官方 PyPI,无 Python 版本上界);桌面独立版可选: macOS brew install --cask netron、Windows winget install netron、Linux snap snap install netron
  • 验证: netron --help 有输出(pip show netron 查版本)
  • 用法: netron model.onnx(本地起 http 服务并开浏览器可视化;--no-browser 无头模式)
torch(pip,Python >=3.10)—— PyTorch 模型加载
  • Linux/Windows: pip install torch(默认 PyPI 轮子为带 CUDA 全量包,数 GB;仅 CPU 分析用 pip install torch --index-url https://download.pytorch.org/whl/cpu)
  • Python 版本下限:当前 torch 2.x 要求 Python >=3.10(PyPI requires-python;torchvision 同步为 >=3.10)——3.9 环境要装需 pin 到仍支持 3.9 的旧版(2.8.x 及更早)。torch / torchvision / Python 的具体组合以官方 compatibility matrix 为准,别按「3.9+」泛化
  • macOS: pip install torch(官方 wheel 为 CPU/arm64)
  • 验证: python3 -c "import torch; print(torch.__version__)"
  • 安全注:torch.load 底层是 pickle——不要直接 load 未知 pkl 文件;PyTorch 2.6+ 默认 weights_only=True,旧版本/显式 weights_only=False 仍有任意代码执行风险;未知模型先 unzip -l/xxd 粗查(坑 2),在隔离环境用 weights_only=True 加载,能转 safetensors 就转
safetensors(pip,Python 3)—— 安全格式读取
  • pip install safetensors;验证: python3 -c "import safetensors; print(safetensors.__version__)"
  • 设计目的即无代码执行(纯数据 + JSON 头),是未知 pkl 的替代分析入口(坑 2 对策之一)
protobuf / protoc(onnx 是 proto)—— 底层格式
  • Python 绑定: pip install protobuf(当前 7.x 要求 Python >=3.10,6.x 起下限已在抬升;3.8/3.9 需 pin 对应旧版本。onnx 已自带依赖、通常无需单独装)
  • protoc 编译工具: Debian/Ubuntu apt install protobuf-compiler、Fedora dnf install protobuf-compiler、Arch pacman -S protobuf、macOS brew install protobuf
  • 验证: protoc --version;python3 -c "import google.protobuf; print(google.protobuf.__version__)"

操作步骤

按顺序执行,每步产物(模型哈希/结构摘要/权重清单)存档 sha256 + 路径([[re-ioc]] 证据链)。

  1. 模型格式识别(onnx / safetensors / pytorch pkl / tflite):

    sh
    file model.bin && sha256sum model.bin > model.sha256 && xxd model.bin | head -2
    • ONNX:无固定魔数——protobuf 流,首字段为 ir_version(tag 0x08 + 变长值;值随 ONNX 版本递增:IR 8 对应 ONNX 1.10,当前发布已到 IR 13——所以第二个字节不是常量 08,不能拿 08 08 12 当识别特征);producer_name(tag 0x12,长度前缀)按规范只 SHOULD 出现,不保证紧跟其后;onnx.checker.check_model 可验证合法性
    • Safetensors:前 8 字节 = 小端 u64 头长度(struct.unpack("<Q", data[:8])),随后是 JSON 头(张量名/形状/dtype/偏移)
    • PyTorch:file 显示 Zip archive(PK\x03\x04 头)——unzip -l model.pt 看条目(state_dict 含 data.pkl;torch.jit.script 含 data.pkl/constants.pkl/bytecode.pkl);老式纯 pkl 是裸 pickle 流(无 PK 头)——不直接 load,先 xxd/strings 粗看(坑 2)
    • TFLite:flatbuffers 流——无固定魔数,但字节 4–7 为文件标识符 TFL3(对应 schema 的 __model_identifier 字段),xxd/strings 可见;结构解析可用 Netron(支持 .tflite 可视化),权重提取分支思路同 onnx(flatbuffers 解析,超出本技能深度时标注"结构化 dump 为准")
    • 判定后按格式走对应分支;拿不准先 [[re-triage]] 初勘(熵/strings 特征)
  2. 结构解析(图/层/算子):

    sh
    netron model.onnx --no-browser          # 可视化(有图形界面再开浏览器)
    python3 - <<'PY'
    import onnx
    m = onnx.load("model.onnx")
    print("producer:", m.producer_name, m.producer_version)   # 框架/优化器指纹(见坑 3)
    g = m.graph
    print("inputs:", [(i.name, [d.dim_value for d in i.type.tensor_type.shape.dim]) for i in g.input])
    print("nodes:", len(g.node), "initializers:", len(g.initializer), "outputs:", [o.name for o in g.output])
    for n in g.node[:20]:
        print(n.op_type, n.name, list(n.input), "->", list(n.output))
    PY
    • PyTorch 侧:torch.jit.load 得 ScriptModule 可打印 model.graph(TorchScript 结构);torch.load 的 state_dict 只有张量没有网络结构——结构在训练/推理脚本里,需配合源码还原(见跨域 [[re-script-deob]])
    • 关注点:算子序列(卷积/注意力等结构指纹)、输入输出张量形状、常量节点位置(权重藏在哪)
  3. 权重提取(张量 dump):

    sh
    mkdir -p weights
    # ONNX:逐 tensor 惰性落地(大模型见坑 1)
    # 注意:这不是"流式"——to_array() 对使用 external data 的 tensor 会先把该张量【完整】读进 ndarray,
    #       只是"一次一个张量"而不是"一次整个模型";显存/内存峰值取决于最大的那个张量
    python3 - <<'PY'
    import onnx, numpy as np
    m = onnx.load("model.onnx", load_external_data=False)     # 只载图结构,不载外部权重
    for init in m.graph.initializer:
        # base_dir 默认为空字符串——外部权重不在 CWD 时必须显式指定其所在目录
        arr = onnx.numpy_helper.to_array(init, base_dir=".")   # 该张量在此处被完整 materialize
        np.save(f"weights/{init.name.replace('/', '_')}.npy", arr)
        print(init.name, arr.shape, arr.dtype)
        del arr                                                # 及时释放,为下一张量让出内存
    PY
    # Safetensors:惰性按张量读取(不整载内存)
    python3 - <<'PY'
    from safetensors import safe_open
    with safe_open("model.safetensors", framework="numpy") as f:
        print(len(f.keys()), "tensors")
        for k in list(f.keys())[:10]:
            t = f.get_tensor(k); print(k, t.shape, t.dtype)
    PY
    # PyTorch state_dict(weights_only 安全加载,见坑 2)
    python3 - <<'PY'
    import torch
    sd = torch.load("model.pth", weights_only=True)
    for k, v in list(sd.items())[:10]:
        print(k, tuple(v.shape) if hasattr(v, "shape") else type(v))
    PY
    • 产出:权重清单(张量名/形状/dtype/数值摘要)+ npy 存档——这是水印检测与窃取判定的原料
  4. 模型水印/指纹检测(嵌入权重):

    • 权重级:逐张量统计(min/max/mean/std、直方图分桶)与疑似原版模型比对;水印常嵌在特定层(首层卷积 bias、归一化 scale、embedding 矩阵行),多为低比特位扰动——检查关键张量的低比特位模式与数值分布异常,而非精确相等(坑 4)
    • 指纹级:全权重 sha256 摘要、逐层张量 hash 序列;与候选原版逐层距离(L2/余弦)比对,输出"每层距离热点图"
    • 行为级:同一测试输入集跑两模型推理,比较 logits 与激活分布——重训练/蒸馏窃取者权重不同但行为接近
    • 产出:相似度矩阵 + 热点图,结论注明判定依据与阈值
  5. 模型窃取判定(架构相似度):

    sh
    python3 - <<'PY'
    import onnx
    from difflib import SequenceMatcher
    m1 = onnx.load("suspect.onnx"); m2 = onnx.load("original.onnx")
    s1 = [n.op_type for n in m1.graph.node]; s2 = [n.op_type for n in m2.graph.node]
    print("op-seq similarity:", SequenceMatcher(None, s1, s2).ratio())   # 算子序列相似度
    # 层对齐后逐层权重余弦/L2 距离:见步骤 4 的每层距离矩阵
    PY
    • 维度:算子序列(SequenceMatcher)、输入/输出形状、逐层权重余弦/L2、输出 logits 距离
    • 判定纪律:单一维度是弱证据(同架构不同训练=正常);多维度一致且权重分布高度接近(如逐层余弦 >0.99)才可主张窃取,结论标注各维度数值
    • 隐藏载荷检查:m.metadata_props(ONNX metadata 藏字符串/代码)、zip 条目中多余文件(坑 2 相关)、权重中形状/数值分布特异的异常张量
Show full SKILL.md (121 more words)Show less

跨域联合

  • [[re-managed]]:本网关「识别运行时」识别到 AI 模型文件后固定调用本技能(模型是"代码在数据里"的托管域分支)
  • [[re-binary-core]]:模型内嵌代码、模型被打包进可执行文件(PyInstaller/pyarmor 打包的推理程序)——先二进制域拆解(格式解析/反编译),拆出的模型文件回本技能
  • [[re-sandbox]]:一切未知 pkl 的 load 默认隔离环境([[re-analyze/platform-tips]] 最高原则)
  • [[re-malware]]:恶意模型载荷(pickle 恶意代码、后门权重、投毒模型分发)的行为与情报侧
  • [[re-ioc]]:模型指纹(sha256/张量 hash/水印模式)进 IOC;[[re-triage]]:模型文件初勘入口与哈希存档
  • [[re-script-deob]]:PyTorch 推理/训练脚本还原(state_dict 无结构时的补全路径)
  • 引用 [[re-analyze/platform-tips]] 静态优先(大型样本)与沙箱最高原则分支
  • [[re-ai-attack]]:文件级证据 → 行为级验证(单向数据流)——本技能产出的文件侧结论(结构 / 权重 / 文件级 fingerprint)作为 re-ai-attack 行为一致性验证的输入。示例:拿到 suspect.pt → 本技能提取结构+权重生成 fingerprint → 转 re-ai-attack 做行为一致性验证(API 侧比对)
  • 只有 API(无文件)的评估直接进 [[re-ai-attack]],不经本技能

常见坑与陷阱

  • 大模型文件巨大(GB 级):现象——onnx.load/torch.load 吃满内存卡死,netron 打开超时,np.save 批量写盘满;原因——权重数 GB,一次性整体加载到内存;对策——分析前先 du -sh/sha256sum 存档;ONNX 用 onnx.load(..., load_external_data=False) 只载图结构,再逐 tensor 取值——注意 numpy_helper.to_array() 对该 tensor 是完整读出(不是流式),所以峰值取决于最大的张量,且用 external data 时要显式给 base_dir(默认空字符串,权重不在 CWD 时直接失败);Safetensors 用 safe_open 惰性按张量读;PyTorch 大模型 torch.load(..., mmap=True);处理对象是"结构摘要 + 定向张量",不是整个文件
  • pkl 反序列化风险(不要直接 torch.load 未知 pkl):现象——load 后进程反弹 shell/文件被删,或报诡异 AttributeError/ModuleNotFoundError;原因——pickle 协议可注入任意代码(__reduce__/__setstate__),torch.load 底层就是 pickle,恶意模型是投毒载荷载体;对策——安全提示:未知模型绝不直接 torch.load;先 unzip -l/xxd/strings 粗查(zip 头 PK vs 裸 pickle、条目有无可疑模块名),用 weights_only=True(PyTorch 2.6+ 默认)加载,需要全功能加载时在隔离环境([[re-sandbox]])执行;可转 safetensors 的样本直接转(纯数据无代码执行)
  • 图优化混淆层结构:现象——onnx-simplifier/TensorRT/onnxruntime 优化后的模型算子序列与训练态对不上(Conv+BN 融合成一个 Conv、常量折叠、名字全改),结构相似度误判;原因——优化器做算子融合/常量折叠,图结构与训练态不同,producer 字段会变;对策——先读 m.producer_name/m.producer_version 识别优化器与版本(融合 ConvBN 的特征:BN 层消失且 scale 并入 conv 权重);架构比较前先规范化算子序列(按算子类别抽象,忽略名字与常量差异);可用 onnx-simplifier/onnxruntime graph_optimization_level 对比优化前后 diff 还原原始层
  • 水印鲁棒性(剪枝后仍存):现象——精确值比对未命中就下"无水印"结论,或两个无关模型在个别层数值巧合相似被误判"窃取";原因——鲁棒水印经剪枝/量化/重训练后仍存活(设计目标),精确匹配必漏;正常模型同架构同数据权重分布相似,单层巧合是假阳性;对策——水印检测用"统计异常"(低比特位扰动/数值分布特异层)而非"精确相等",窃取判定用多维度证据 + 阈值(步骤 5 纪律),结论标注置信度与证据强度

© 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-ai-model of dslsdzc/rev-skills.

Open the folder on GitHubat commit bd21db8

Compare with similar skills

Re AI Model 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 AI Model compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Re AI Model this skilldslsdzc/rev-skills130—~2.4kAutomated safety check: PassApache-2.0
Technology Selectiondotnet/skills5.6k1 repos~2.1kAutomated safety check: PassMIT
Local Asrysyecust/lecture-to-notes273—~1.6kAutomated safety check: PassCustom licence
Formattingbrendanhasz/probflow175—~381Automated safety check: PassMIT
Migrate Workflow Ec2 To Osdcpytorch/test-infra113—~2kAutomated safety check: PassCustom licence
Embedded AI Deploymentmatlab/agent-skills-playground183—~3.4kAutomated safety check: PassCustom licence

Similar skills

  • Official

    Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework (MAF), GitHub Copilot SDK, ONNX…

    5.6k GitHub starsUsed in 1 repo~2.1k tokens
    AI & LLM EngineeringAuto-check passed
  • Local Asr

    ysyecust/lecture-to-notes

    把本地长视频/音频转写成文字稿 + 可选字幕,纯本地(不上传云端),用 sherpa-onnx X-ASR Zipformer transducer 模型(int8 量化、中英双语、自动标点)。已在 macOS Apple Silicon(int8 + AMX,~100× 实时)、Linux ARM64(CPU,~32× 实时)与 Windows(PowerShell…

    273 GitHub stars~1.6k tokensUpdated 6 days ago
    AI & LLM EngineeringAuto-check passed
  • Formatting

    brendanhasz/probflow

    Ensure consistent code formatting using the uv package manager and pre-commit.

    175 GitHub stars~381 tokensUpdated 12 days ago
    AI & LLM EngineeringAuto-check passed
  • Step-by-step playbook for migrating a pytorch/pytorch .github/workflows/.yml from EC2 to OSDC (ARC) runners — covers both dial-up and 100% opt-in patterns, with the inputs that must be plumbed…

    113 GitHub stars~2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Embedded AI Deployment

    matlab/agent-skills-playground

    Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder).

    183 GitHub stars~3.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Ray Train Distributed Training

    Orchestra-Research/AI-Research-SKILLs

    Scales PyTorch, TensorFlow and Hugging Face training from a single GPU to multi-node clusters with Ray Train, including Ray Tune sweeps and checkpoint recovery.

    13k GitHub starsUsed in 2 repos~2.7k tokens
    AI & LLM EngineeringAuto-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.

    130 GitHub stars~2k tokensUpdated 4 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.

    130 GitHub stars~2k tokensUpdated 4 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.

    130 GitHub stars~1.1k tokensUpdated 4 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.

    130 GitHub stars~1.9k tokensUpdated 4 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.

    130 GitHub stars~1.4k tokensUpdated 4 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.

    130 GitHub stars~2.8k tokensUpdated 4 days ago
    Auto-check passed

Questions about Re AI Model

What does Re AI Model do?

AI 模型文件逆向与静态分析:ONNX/PyTorch/Safetensors/TFLite 格式解析、 网络结构还原、权重提取、文件级水印分析(权重 pattern/metadata/tensor hash/embedding 异常)。. Re AI Model is an agent skill from dslsdzc/rev-skills.

When should I use Re AI Model?

Re AI Model fits situations like: tasks that involve Deep learning; tasks that involve Embeddings.

How do I install Re AI Model in Claude Code?

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

How do I install Re AI Model in Codex?

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

Can I use Re AI Model 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-ai-model -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-ai-model, .gemini/skills/re-ai-model, .github/skills/re-ai-model and .opencode/skills/re-ai-model in your project.

What does Re AI Model need to run?

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

Does Re AI Model access the network?

SKILL.md names 1 domain. In commands or code: download.pytorch.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Re AI Model 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 AI Model use?

Re AI Model 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 AI Model use?

About 2.4k tokens (SKILL.md is roughly 9.4k 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 AI Model?

Skills that share tags, products or a category with Re AI Model: Technology Selection (dotnet/skills, 5.6k stars), Local Asr (ysyecust/lecture-to-notes, 273 stars), Formatting (brendanhasz/probflow, 175 stars) and Migrate Workflow Ec2 To Osdc (pytorch/test-infra, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Re AI Model?

dslsdzc (a GitHub user) maintains it in dslsdzc/rev-skills, which has 130 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.