Reverse Engineer Js

Reverse-engineer minified or obfuscated JavaScript bundles. Primary tool: humanify (humanifyjs) — uses an LLM to rename mangled identifiers back to meaningful names. Default model: gemini-3.8-flash. Use when the user says 'deobfuscate this bundle', 'humanify this', 'rename minified vars', 'reverse engineer this JS', 'what does bundle.js do', or is working in a project with a deobfuscated `og/` or `modules/` folder fed by humanify. Covers humanify CLI invocation, the pseudo-TTY workaround for cursorTo crashes, single-module extraction from a bundle, and chaining with beautifiers.

9 stars 1 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add vladmdgolam/agent-skills --skill reverse-engineer-js
Manual install
git clone --depth 1 https://github.com/vladmdgolam/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/reverse-engineer-js ~/.claude/skills/reverse-engineer-js

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Reverse Engineer JS

LLM-assisted deobfuscation of minified / mangled JavaScript using [humanifyjs](https://github.com/jehna/humanify) plus surrounding tooling for extracting and reintegrating modules.

# Tools at a glance

| Tool | Purpose | When |
|------|---------|------|
| `humanifyjs` (npx) | Rename mangled vars/functions via LLM | Mangled but already valid JS |
| `prettier` / `js-beautify` | Reformat single-line minified code | Before humanify, if needed |
| `webcrack` | Unpack webpack / browserify bundles into per-module files | When bundle is one big file |
| Source-map sleuthing | `// # sourceMappingURL=...` may exist next to the bundle | Always check first — beats LLM rename |

Always check for a sourcemap (`bundle.js.map` or `sourceMappingURL` comment in the file) **before** spending tokens on humanify. If found, original sources are recoverable for free.

# Default humanify invocation

Use Gemini unless the user says otherwise:

```bash
npx humanifyjs gemini -m "gemini-3.8-flash" -o <outputDir> <inputFile>
```

Requires `GEMINI_API_KEY` in env (the project's root `.env` is the usual place).

Other backends:

```bash
# OpenAI
npx humanifyjs openai --apiKey="$OPENAI_API_KEY" --model gpt-4.1-mini bundle.js

# Local (slower, free)
npx humanifyjs local bundle.js
```

# Critical gotchas

## 1. Pseudo-TTY required in non-interactive shells
Read the full skill on GitHub

Details

Skill name
reverse-engineer-js
Path
skills/reverse-engineer-js/SKILL.md
License
MIT
Repo updated
14 October 2026

FAQ

What does the Reverse Engineer Js skill do?

Reverse-engineer minified or obfuscated JavaScript bundles. Primary tool: humanify (humanifyjs) — uses an LLM to rename mangled identifiers back to meaningful names. Default model: gemini-3.8-flash. Use when the user says 'deobfuscate this bundle', 'humanify this', 'rename minified vars', 'reverse engineer this JS', 'what does bundle.js do', or is working in a project with a deobfuscated `og/` or `modules/` folder fed by humanify. Covers humanify CLI invocation, the pseudo-TTY workaround for cursorTo crashes, single-module extraction from a bundle, and chaining with beautifiers.

How do I install the Reverse Engineer Js skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add vladmdgolam/agent-skills --skill reverse-engineer-js. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Reverse Engineer Js popular?

It lives in vladmdgolam/agent-skills, which has 9 GitHub stars and 1 forks.

Related skills

Agent Sessions

9

vladmdgolam/agent-skills

Search, list, and resume AI agent sessions across Claude Code, Codex CLI, Gemini CLI, opencode, Hermes Agent, and Cline CLI. Use when the user asks to find a past conversation, search session history, resume a previous session, list recent agent activity, or check what was discussed in a prior session. Also use when asked to "find that conversation where I...", "resume my last codex session", "read latest convo", "read last messages", "what did I work on yesterday", "search my claude history for X", or gives an agent session id such as `ses_...`, a UUID, or a Cline id like `1782988565588_qqrxi

AI, LLMs & Agents

Apple Books MCP

9

vladmdgolam/agent-skills

Extracts highlights, annotations, and book data from Apple Books via MCP. Use when: user asks to export book highlights, extract annotations with colors, search highlights across books, create highlight summaries, or match books from a reading list against their Apple Books library. Covers efficient batch color extraction (5 calls instead of 150+), annotation-to-book matching, and markdown export patterns.

AI, LLMs & Agents

Blender MCP

9

vladmdgolam/agent-skills

Blender MCP expert for scene inspection, Python scripting, GLTF export, and material/animation extraction. Activate when: (1) using Blender MCP tools (get_scene_info, execute_python, screenshot, etc.), (2) writing Blender Python scripts for extraction or manipulation, (3) exporting scenes to GLTF/GLB for web (Three.js, R3F), (4) debugging material or texture export losses, (5) optimizing GLB files with gltf-transform, (6) using asset integrations (PolyHaven, Sketchfab, Hyper3D Rodin, Hunyuan3D). Covers critical export gotchas, material mapping survival, texture optimization pipeline, headless

Images, Video & Audio

Semantic Compression

5

therealmoronto/claude-semantic-compression

Apply semantic logic compression (Ovchinnikov method) when crafting prompts for LLMs or describing complex conditional logic. Use this skill whenever the user asks to: write or optimise a prompt for an LLM, compress or rewrite a task description, describe multi-condition business logic (if/and/or/not chains), or asks why an LLM misunderstood their instructions. Also trigger when the user says ‘compress the logic’, ‘write a prompt for’, ‘the LLM doesn't understand’, ‘simplify the conditions’, or similar intents. Also trigger when the user wants to use output modifiers such as →code or →no-meta,

AI, LLMs & Agents

Prompt Engineering Canon

10

Archive228/lab-skills

Canonical prompt-engineering operating procedure distilled from Google's 68-page Prompt Engineering whitepaper (Lee Boonstra, Feb 2025): when to use zero/few-shot, system/contextual/role prompting, chain-of-thought, step-back, self-consistency, ToT, ReAct, output-format control, and exact temperature/top-K/top-P starting values. Trigger whenever writing, reviewing, or debugging a prompt for an LLM, choosing sampling configuration, or deciding which prompting technique fits a task.

AI, LLMs & Agents

Skill Manager

9

kargnas/skills

Creates, restructures, merges, and splits agent skills: directory layout, bundled guides/scripts/assets, cross-agent placement under .agents/skills, importing community skills, merging several skills into one so fewer descriptions load into every session, and a sanitization pass that checks model IDs against models.dev. Triggers on 스킬 생성, 스킬 병합, 스킬 분리, 스킬 구조 정리, 외부 스킬 가져오기, 스킬 검증, 모델 업그레이드. Step wording and name/description wording go to skill-prompter; finding published skill packages goes to skill-finder. Confirm with the user before running, with a brief explanation of what this skill will

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.