14 skills · sorted by relevance
Guides experiments that inspect and change internal model values using nnsight. Covers local PyTorch models and remote experiments through NDIF, including replacing intermediate values to test how particular layers affect a model’s predictions.
Guides experiments that inspect and modify internal values in PyTorch models to study their effects on predictions. Covers local analysis and remote experiments through NDIF for models too large for local GPUs.
Compare software binaries before and after a security patch to identify the underlying flaw. Guide creation of a proof of concept, a small vulnerability demonstration, and compare its behavior across patched and unpatched versions.
Generate and interpret security-research diffs between Windows versions or patch levels using this repo's WinDiff CLI and databases. Use when comparing Windows builds or binaries such as ntoskrnl.exe, ntdll.dll, win32k*.sys, ci.dll, or cng.sys to find changed syscalls, symbols, types, mitigation flags, callbacks, ETW/EtwTi telemetry, code-integrity behavior, drivers, or attack surface. Explain likely intent and security relevance with Windows-internals knowledge, and frame findings for anti-malware/EDR, anti-cheat, and vulnerability-research audiences rather than returning an uninterpreted symbol list.
The English summary is being prepared. Showing the original description.
Fornece orientação para interpretar e manipular internals de redes neurais usando nnsight com execução remota NDIF opcional. Use quando precisar executar experimentos de interpretabilidade em modelos massivos (70B+) sem recursos locais de GPU, ou ao trabalhar com qualquer arquitetura PyTorch.
The English summary is being prepared. Showing the original description.
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
The English summary is being prepared. Showing the original description.
Transfer known function and variable names from an older binary to a newer version. Compare disassembly and pseudocode with an LLM, produce structured mappings, and apply names and comments in IDA.
Investigate malicious software delivered through trusted updates or dependencies. Compare suspect files with legitimate versions, examine signing anomalies and injected code, and organize evidence to assess the infection path and downstream impact.
跨版本符号迁移与二进制差分。当你有旧版本的符号/逆向结果，需要快速迁移到新版本时使用。 适用场景：内核缺 PDB 用旧版符号推导、程序更新后批量迁移函数名、应用更新后快速定位新偏移。 核心方法：用 LLM 做结构化差异比对，程序化输入输出，成本极低（200 函数 ~1 元）。 触发关键词：符号迁移、bindiff、跨版本、PDB 缺失、函数偏移迁移、symbol migration、binary diff、版本对比。
The English summary is being prepared. Showing the original description.
N-day / patch-diff workflow - given a CVE/advisory or a suspicious patch, diff pre- vs post-patch to locate the fixed bug, build a PoC for the unpatched version, and run variant analysis for a fresh bug. Triggers - "n-day", "patch diff", "diff the patch", "bindiff".
The English summary is being prepared. Showing the original description.
跨版本符号迁移与二进制差分。当你有旧版本的符号/逆向结果，需要快速迁移到新版本时使用。 适用场景：内核缺 PDB 用旧版符号推导、程序更新后批量迁移函数名、游戏反作弊更新后快速定位新偏移。 核心方法：用 LLM 做结构化差异比对，程序化输入输出，成本极低（200 函数 ~1 元）。 触发关键词：符号迁移、bindiff、跨版本、PDB 缺失、函数偏移迁移、symbol migration、binary diff、版本对比。
The English summary is being prepared. Showing the original description.
"Conduct Van Westendorp Price Sensitivity Meter analysis to identify acceptable price ranges. Use this skill when the user needs to determine price boundaries for a new product, find the optimal and indifference price points, or survey-based pricing research — even if they say 'what should we charge', 'price sensitivity survey', or 'acceptable price range'.".
The English summary is being prepared. Showing the original description.
Compares two related malware samples to surface what changed between variants using section-level hashing, import-set differences, and fuzzy similarity scoring. Activates for requests to diff two samples, compare malware variants, or measure similarity between two binaries for variant tracking.
The English summary is being prepared. Showing the original description.
Use when a task needs the judgment of an emergency medicine physician — risk-stratifying an undifferentiated chief complaint against a can't-miss diagnosis, deciding an ED disposition (discharge/observation/admit/transfer) under time and bed pressure, reasoning through EMTALA screening-and-stabilization obligations, or triaging a department under crowding/boarding load.
The English summary is being prepared. Showing the original description.