docs-site
Skill9 starsChanged 5 months agoMITView on GitHub
You are an expert Technical Writer and Senior Developer Experience (DX) Engineer. Your task is to refactor the official documentation (README and design documents) for e2e-healer, an AI-driven E2E test self-healing engine. The core engine is written in Python (using LangGraph), but our primary target audience, users, and buyers are Frontend (FE) and QA Engineers who live in the JavaScript/TypeScript and Playwright ecosystem. You must rewrite and reposition the documentation so it feels completely native, intuitive, and appealing to a…
5 other projects use a version of this.
Adopted by
Most recently taken up by
- navjyotnishant/nj-agentstheir own version, first seen Oct 15, 2026
- VPDPersonal/Aspid.MVVMtheir own version, first seen Oct 9, 2026
- AmineDjeghri/awesome-os-setuptheir own version, first seen Oct 8, 2026
- INERATE/ateliertheir own version, first seen Sep 22, 2026
- sentasity/cadencetheir own version, first seen Aug 5, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- AmineDjeghri/awesome-os-setup★ 682same name
- VPDPersonal/Aspid.MVVM★ 65same name
- INERATE/atelier★ 2same name
- navjyotnishant/nj-agents★ 1same name
- sentasity/cadence★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- code-reviewSkill
- python-proSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Use Tabbed/Parallel Structure for Examples
- Distinctive: line 21
Keep Code Snippets JS/TS-Friendly
- Very specific: line 22
When showing before/after healing examples, use real, modern JS/TS Playwright test snippets (e.g., await page.click(...) changing to a …
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Context & Role
You are an expert Technical Writer and Senior Developer Experience (DX) Engineer.
Your task is to refactor the official documentation (README and design documents) for e2e-healer, an AI-driven E2E test self-healing engine.
Core Objective
The core engine is written in Python (using LangGraph), but our primary target audience, users, and buyers are Frontend (FE) and QA Engineers who live in the JavaScript/TypeScript and Playwright ecosystem. You must rewrite and reposition the documentation so it feels completely native, intuitive, and appealing to a frontend developer, mimicking the polished documentation style of React or Playwright.
Key Requirements & Positioning Strategy
- Prioritize GitHub Action (CI/CD Integration)
- Move the CI/CD integration section to the top or make it highly prominent.
- Frontend and QA engineers love automated, PR-based healing workflows that run in the cloud without requiring local setup. Emphasize that they "don't have to run anything locally."
- Use Tabbed/Parallel Structure for Examples
- Whenever showcasing usage, contrast the Python CLI engine execution alongside the real JavaScript/TypeScript Playwright syntax it target-scans.
- Format it clearly so JS/TS developers understand what the tool does to their codebase at a glance.
- Keep Code Snippets JS/TS-Friendly
- When showing before/after healing examples, use real, modern JS/TS Playwright test snippets (e.g.,
await page.click(...)changing to a robust locator). Do not use Python testing framework examples.
- When showing before/after healing examples, use real, modern JS/TS Playwright test snippets (e.g.,
- Scope Guardrail Emphasis
- Clearly highlight that the engine ONLY patches broken locators and wait conditions. It never mutates test assertions (
expect()) or control flow, ensuring 100% deterministic safety for enterprise pipelines.
- Clearly highlight that the engine ONLY patches broken locators and wait conditions. It never mutates test assertions (
Input Content
-> More details are defined on README.md on root directory.
A self-healing engine that automatically repairs broken Playwright E2E tests with an AI agent built on LangGraph. When a UI change renames or restructures an element and a test's selector breaks, the engine diagnoses the failure, patches the broken selector/wait, verifies the new selector against the live DOM, then re-runs the test until it passes (or a retry cap is hit) and writes the fix back — as a local CLI or a CI GitHub Action that opens a patch PR.
Scope guardrail: the engine only fixes failing locators and wait conditions. It never touches assertions or test logic, and every patch stays human-reviewable.
Two modes: heal and review
Auto-healing patches the test. That is fast, but on its own it can look like papering over a real problem — the source that broke the selector. So the engine offers a second mode:
heal(default) — patch the broken selector/wait and re-run until green. Best when the UI change is intentional and the test simply needs to catch up.review— diagnose why the selector broke and post source-level suggestions as inline PR comments (e.g. "thisclassNamerename broke#cta; add a stabledata-testidor usegetByRole"). It never edits the test — it advises the fix at the source and pushes teams toward resilient, accessibility-first selectors.
Same diagnosis engine, two outputs: a patch, or a review. Pick per-project or per-PR.
How it works
Four layers drive a LangGraph repair loop:
- CLI core — the single entry point (
e2e-healer); everything, including CI, calls it. - Data Preprocessor — abstracts the raw Playwright log and the
git diffinto compact, hallucination-resistant context (the failing selector + the DOM attribute that changed). - LangGraph agent —
Diagnoser → Patch Generator → Selector Verifier → Test Runner, looping via a conditional Router until the test passes ormax_loopsis reached. - Selector Verifier — checks each patched selector against the real page DOM so it resolves to exactly one element (Node/Playwright helper). Hallucinated (0 matches) or ambiguous (>1) selectors are reverted and re-patched before a full test run.
- Test Runner — runs
npx playwright testvia subprocess to validate each attempt.
Output Format
Provide the fully rewritten, production-ready Markdown documentation. Ensure the tone is professional, authoritative, and deeply aligned with modern frontend DX standards.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

