Jsrpc Skill — Development skill for Claude Code
Claude Code / Agent skill:通过 JsRpc 远程调用网站自己的 sign/encrypt 函数,免抠算法、免补环境.
How to install Jsrpc Skill
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open heart147/jsrpc-skill and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Jsrpc Skill does
Claude Code / Agent skill:通过 JsRpc 远程调用网站自己的 sign/encrypt 函数,免抠算法、免补环境。基于JsRpc。
Alternatives in Development
- Agentlas Login — Sign this machine into Agentlas (opens the browser sign-in window) 1.1k ★
- Claude For Commerce Examples — Shopify implementations of Anthropic's commerce-agents blueprint: a storefront shopping agent over UCP and Sig 111 ★
- Aod.Define — Create PRD with Triad governance (PM + Architect + Team-Lead sign-offs) - Streamlined v2 89 ★
README
jsrpc-skill — Claude Code / Agent Skill
**English** · [中文](README.zh.md)
*Fewest parameters registered. Most variables controlled.*
A [Claude Code](https://docs.claude.com/en/docs/claude-code) skill for the **JS 逆向远程调用 (RPC)** workflow: drive a real browser as a live JS execution engine over WebSocket, and call a site's own encryption / signing / token functions through simple HTTP endpoints — no algorithm extraction, no environment patching.
Built on top of [`jxhczhl/JsRpc`](https://github.com/jxhczhl/JsRpc) (Go WebSocket server + injectable browser JS client).
What it does
When a target's front-end crypto is too heavy to reverse (WASM, obfuscation, jsvmp, fingerprint/anti-bot), you inject a small client into the page, register the site's own `sign`/`encrypt` function as an action, and call it from Python/curl. The browser does the work; you get the result.
This skill gives Claude a verified, phase-gated workflow for that: **locate → serve+inject → call → re-verify → harden**, with anti-hallucination checkpoints (every claim of success must show a real HTTP response).
Install
git clone https://github.com/heart147/jsrpc-skill
cp -r jsrpc-skill/jsrpc-skill ~/.claude/skills/jsrpc-skill
Then in Claude Code, invoke with `/jsrpc-skill` or just describe a JS-reversing task.
Layout
jsrpc-skill/
├── SKILL.md # workflow, triggers, 5-phase checklist
└── references/
├── find-crypto-entry.md # playbook: find crypto entry, hang RPC, multi-site reuse
├── setup.md # run the server, config.yaml, https/wss
├── api.md # every HTTP endpoint + exact response shapes
├── examples.md # every call scenario (no-arg / args / POST / execjs / page info / crypto fn)
├── jsrpc_client.py # ready-to-use Python client (requests only) + offline self-check
├── clients.md # where to get the injectable browser / WeChat clients
├── w
Related Skills
Aod.Okrs
Scaffold an OKR document with standard template and PM sign-off
Aod.Project Plan
Create implementation plan with dual sign-off (PM + Architect) - Streamlined v2
Brow
Claude Code usage and rate limits in the MacBook notch. Track the 5-hour and weekly limits of multiple Claude
Logout
Sign out — remove the local stagent cloud token
Handler
You are Harvey, responding to replies from prospects. Every reply is an opportunity, but some replies are a st
Submit
Build, sign, and submit app to Mac App Store
Related Agents
Scope Guard (Shared Prompt Block For Tier 2 Agents)
This file is not a standalone agent. It contains the shared scope enforcement prompt text that Tier 2 (executi
Research Reba
Guardian/QA - Validates everything, guards safety rails, nothing merges without her. Use for code review, vali
AI Team Qa.Agent
AI QA engineer agent (Ivy). Use when: testing features, running E2E tests, playtesting, filing bug reports, wr