> ## Documentation Index > Fetch the complete documentation index at: https://leetcode-py.wisl.dev/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > leetcode-py is a Python LeetCode practice environment generator with one CLI: lcpy. It is not a service or platform. > Each problem is a directory under leetcode/ with README.md, solution.py, test_solution.py, helpers.py, and playground.ipynb. lcpy gen creates them from JSON templates bundled with the package. > Examples are backed by tests; copy them verbatim. # Problem creation > Add problems end to end with an AI assistant, from a one-sentence prompt to generated, tested content. The repo ships skill specs that let an AI coding assistant (Claude Code, Cursor, GitHub Copilot Chat, Amazon Q, or any IDE assistant with repo context) add new LeetCode problems end to end. You describe the problem in one sentence; the assistant scrapes, templates, generates, implements the optimal solution, and verifies. Human intervention stays minimal: the prompt, and a review of the result. ## Set up the context For best results, have these files in the assistant's context: * [`.claude/skills/problem-creation/SKILL.md`](https://github.com/wislertt/leetcode-py/blob/main/.claude/skills/problem-creation/SKILL.md): the complete creation workflow * [`.claude/skills/test-quality-assurance/SKILL.md`](https://github.com/wislertt/leetcode-py/blob/main/.claude/skills/test-quality-assurance/SKILL.md): test enhancement and reproducibility checks * [`.claude/CLAUDE.md`](https://github.com/wislertt/leetcode-py/blob/main/.claude/CLAUDE.md): code standards and testing patterns ## Ask for a problem Example prompt requesting a new problem from the assistant Prompts that work: ```text theme={"theme":{"light":"github-light","dark":"github-dark"}} Add problem 198. House Robber Add problem 198. House Robber. tag: grind Create problem 70. Climbing Stairs with grind-75 tag ``` Include the problem number and title; adding a tag puts it in a collection. ## What the assistant does 1. Scrapes the problem data from LeetCode 2. Transforms it into the JSON template format, images included 3. Creates `json/problems/{problem_name}.json` 4. Updates `tags.json5` with the requested tags 5. Generates `leetcode/{problem_name}/` with the full problem structure 6. Runs the lint checks, iterating from step 3 until everything passes Source control view of files created during problem generation Step 5 produces real content under `leetcode/{problem_name}/`: the full [six-file layout](/practice/problem-anatomy) with the README description, helpers, playground, and tests, all from the JSON template. The generated `solution.py` arrives as a typed stub with a `TODO`, and `test_solution.py` ships parametrized cases: Generated solution.py with TODO placeholder and type hints Generated test_solution.py with parametrized test cases ## Implement and verify The assistant then implements the optimal solution in `solution.py` (one `Solution` class) and runs quality assurance per the test QA skill: tests pass, at least 12 cases, and the suite reproduces after a regenerate and restore cycle. ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}} bake p-test -p house_robber bake check-test-cases -t 12 ``` Generated test cases are a starting point, not gospel. The assistant verifies expected values, and so should you before trusting a suite. ## Batch creation `/batch-problem-creation [count]` (default 5) loops the whole workflow over the next problems in the roadmap lists: ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}} uv run python .claude/.dev/next_problem.py # picks the next problem ``` The picker skips known unscrapable problems (premium, API issues), which live in `.claude/.dev/problem_lists/unscrapable.py`. Failed problems are logged and the batch continues; you get a summary with success rate and retry candidates at the end. ## The pipeline, for reference Everything above drives this machinery: ```text theme={"theme":{"light":"github-light","dark":"github-dark"}} src/leetcode_py/cli/resources/leetcode/ ├── json/ │ ├── problems/*.json # one template per problem (source of truth) │ └── tags.json5 # collection membership └── {{cookiecutter.problem_name}}/ # cookiecutter scaffold | | lcpy gen v leetcode// # README, solution, tests, helpers, playground ``` A problem template JSON carries the metadata (`problem_name`, `problem_number`, `problem_title`, `difficulty`, topics, tags) plus the rendered content for each output file: the README description, examples and constraints, helper function sources, solution skeleton, test content, and playground cells. Bulk generation for practice is covered in [Collections](/cli/collections). ## Fix drift `leetcode/` is never edited by hand. When `bake check-consistency` (or CI) reports that `leetcode/` no longer matches the templates, edit the JSON template, then regenerate: ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}} bake p-gen -p two_sum --force ``` To rebuild everything from scratch, `bake gen-all-problems` deletes `leetcode/` and regenerates all problems (it asks first outside CI). Two more skills automate the common fixes: [`consistency-fix`](https://github.com/wislertt/leetcode-py/blob/main/.claude/skills/consistency-fix/SKILL.md) (drift repair) and [`update-tags`](https://github.com/wislertt/leetcode-py/blob/main/.claude/skills/update-tags/SKILL.md) (collection membership changes).