Self Learn Reverse Engineer — Productivity skill for Claude Code
Claude Code skill bundle: capture a browser workflow once into a durable playbook, self-heal it when sites change, then codify it into HTTP-mimic production adapters.
How to install Self Learn Reverse Engineer
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Antheurus/self-learn-reverse-engineer and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Self Learn Reverse Engineer does
Claude Code skill bundle: capture a browser workflow once into a durable playbook, self-heal it when sites change, then codify it into HTTP-mimic production adapters.
Alternatives in Productivity
- Cs2 Technical Analysis — You are an Expert 3D Technical Director specialized in CS2 (Counter-Strike 2) weapon and item pipelines 14.1k ★
- Ccplugins — Claude Code Plugins that actually save time 2.7k ★
- Browser Harness JS — Self-healing browser harness that enables LLMs to complete any task 480 ★
README
self-learn-reverse-engineer
A [Claude Code](https://claude.com/claude-code) skill bundle for reverse-engineering a website **once** — its UI steps and the HTTP API underneath them — then running what was learned reliably forever, and turning it into production code that calls the site's own APIs instead of driving a browser on every cron tick.
Formerly `self-learn-automation`. The sub-skills keep their `sla-` prefix.
The core idea: **a playbook is durable knowledge.** Each session either confirms the playbook still works or repairs the part that broke. Discovery happens once; production replays captured requests with harvested auth context.
This is the opposite of "rediscover the DOM every run".
The lifecycle
┌─────────────┐
│ sla-capture │ ← playwright-cli: UI steps + network/API contracts
└──────┬──────┘
│ playbook + network calls + auth harvest
▼
┌─────────────┐ ┌──────────────┐
│ sla-run │ ──────▶ │ sla-correct │
└──────┬──────┘ └──────────────┘
│ verified
┌───────────┴───────────┐
▼ ▼
┌─────────────┐ ┌─────────────────────────────┐
│sla-extensify│ │ sla-codify │
│ MV3 ext │ │ 1) API mimic (default) │
└─────────────┘ │ 2) Patchright UI fallback │
└─────────────────────────────┘
The six sub-skills
| Sub-skill | Does | Triggered by |
|---|---|---|
sla-capture |
First-run discovery, writes the playbook | A brand-new workflow |
sla-run |
Executes a playbook, updates its run log | "run " / a known playbook |
sla-correct |
Self-heals broken selectors and steps | A failed run, "automation broken" |
sla-extensify |
Builds an MV3 Chrome extension from the playbook | "extensify" |
sla-codify |
Related Skills
Kata
Record a task once, get a skill every coding agent can run. Plus ambient history: capture your workflow all da
Heal Issues
Read and execute the workflow defined in .agent/workflows/heal-issues.md.
Claude Code Working
Working reverse-engineered Claude Code CLI rebuilt from source analysis to reproduce the original terminal wor
Quick Start — Building From Source
TL;DR: A full rebuild requires Bun (not Node.js) for its compile-time intrinsics (feature(), MACRO, bun:bundle
Workflow Blueprint
Shape a user-facing workflow bundle across commands, skills, agents, plugins, and MCP
Research Assistant Suite ChatGPT
Self-contained ChatGPT/Codex research workflow bundle for methodology, literature search, and evidence-aware n
Related Agents
Code Audit GitHub Workflows
Audits GitHub Actions workflow YAML and composite-action YAML for supply-chain, injection, permission, and sec
Exec Subtle
FRONTIER-DO tier at max effort. ULTRATHINK execution agent for the single subtlest workstream in a plan - deri
Collector
Spawned by /playbook:learn-project Phase 1 to gather raw material for one collector role: git-history, code-st