🛠️
AI EngineeringPython

Skill Creator

by idavidov13

Skill Creator is an AI Engineering skill for Claude Code, published by idavidov13 in agentic-playwright.

162 stars46 forkson idavidov13/agentic-playwrightAdded 2026/09/08Repository updated 2026/09/03
View source on GitHubDownload repo ZIP
agenticaiapi-testingclaude-codecursore2egithub-copilotplaywrighttest-automationtestingtypescript
Install in seconds
Install Skill Creator
Copy Skill Creator into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/idavidov13/agentic-playwright/tree/main/.github/skills/skill-creator ~/.claude/skills/skill-creator

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/idavidov13/agentic-playwright.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
.github/skills/skill-creator/SKILL.md in idavidov13/agentic-playwright
Installs to
~/.claude/skills/skill-creator
Collection
One of 18 skills cataloged from this repository
Category
AI Engineering — 3670 skills

What Skill Creator does

Skill Creator helps create new skills, edit existing ones, and measure how well they work. Use it when you want to draft a skill, refine its trigger or behavior, run evals, or benchmark performance.

Skill Creator is cataloged under AI Engineering on DirSkills. Skill Creator comes from a repository tagged agentic, ai, api-testing, claude-code and cursor.

Documentation

README

Skill Creator

This repository (GitHub / Copilot): This copy lives at .github/skills/skill-creator/. In command examples, set <skill-creator-path> to that folder. Run Python modules from that directory, e.g. cd .github/skills/skill-creator && python -m scripts.aggregate_benchmark …. A parallel copy for Cursor is at .cursor/skills/skill-creator/.

GitHub Copilot: Parallel “subagent” runs may not be available—run with-skill vs baseline evals sequentially if needed. Description optimization (run_loop.py / claude -p) requires the Claude Code CLI where installed; skip those steps in pure Copilot-only environments without claude on PATH.

A skill for creating new skills and iteratively improving them.

This is the opening of the README. Read the full README on GitHub.

Commands Skill Creator provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /skill-test

Frequently asked about Skill Creator

  • What else does idavidov13 publish alongside Skill Creator?

    Skill Creator is one of 18 skills that DirSkills catalogs from idavidov13/agentic-playwright, the repository it ships in. Its siblings there include AI-Native Workflow, API Testing and Common Tasks. Each one is a separate skill with its own page in this directory, installs the same way Skill Creator does, and is maintained by idavidov13 in that same repository. The rest of the collection is listed on the idavidov13/agentic-playwright page.

  • How does Skill Creator compare to other AI Engineering skills?

    Skill Creator ranks #3400 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Skill Creator against them. Open each page to compare what they document and how they install.

More from idavidov13/agentic-playwright

Skill Creator is one of 18 skills cataloged on DirSkills from idavidov13/agentic-playwright.

See all 18 skills →
🧭
1h ago

AI-Native Workflow

AI-Native Workflow routes non-trivial Playwright tasks to the right specialized skill and defines the 8-phase process for exploring, planning, gating, applying, and verifying changes. Use it when starting an AI-assisted task, choosing a skill, or coordinating a multi-step change.
AI Engineering
16246
🧪
1h ago

API Testing

API Testing covers Playwright patterns for API specs, including apiRequest usage, Zod response validation, multi-call test.step wrapping, and negative testing for request bodies and path parameters. Use it when adding or updating endpoint tests or comparing documented contracts with API behavior.
Quality
16246
🧩
1h ago

Common Tasks

Common Tasks provides copy-paste prompt templates for common Playwright scaffold work like page objects, tests, schemas, factories, fixtures, and components. Use it when bootstrapping a new artifact or asking for a standardized starting prompt.
Automation
16246
⚙️
1h ago

Config

Config defines the environment variable conventions for the Playwright scaffold, including env file layout, dotenv loading, and where app and utility URLs belong. Use it when adding env-driven settings, credentials, or config properties consumed by tests and fixtures.
DevOps
16246
🗂️
1h ago

Data Strategy

Data Strategy defines how to choose between Faker factories, static TypeScript datasets, and inline values for Playwright tests. Use it when creating test data, adding invalid-value sets, or deciding where a value should live.
Quality
16246
🐞
1h ago

Debugging

Debugging helps you investigate Playwright test failures by reading error messages, classifying timeout and locator issues, and choosing the right tool to replay the problem. Use it when a test flakes, fails in CI, or needs local reproduction from traces and reports.
Quality
16246

More AI Engineering skills

Skill Creator is one of 3670 AI Engineering skills cataloged on DirSkills, ranked #3400 by stars among them.

Browse all AI Engineering skills →
📐
4w ago

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.
AI Engineering
239.8K36.4K
🤖
4w ago

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.
AI Engineering
239.8K36.4K
🤖
4w ago

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.
AI Engineering
239.8K36.4K