Logs coding solutions to a DSA vault with pattern analysis and technical review.

Install

mkdir -p .claude/skills/leetcode && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18781" && unzip -o skill.zip -d .claude/skills/leetcode && rm skill.zip

Installs to .claude/skills/leetcode

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Log a solved (or attempted) coding problem into the DSA area with pattern analysis and honest review. Use whenever the user runs /leetcode, pastes a solution, shares a LeetCode/HackerRank/Codeforces problem they worked on, says "I just solved...", "review my solution", or "log this problem" — even if they only paste code with no explanation.
343 charsno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Identify coding problem patterns
  • Review solution correctness and complexity
  • Write problem entries to the DSA area
  • Link similar problems within the vault
  • Update the DSA index with problem status and tallies

How it works

The skill identifies patterns in a coding problem solution, reviews its quality, writes a detailed entry to the DSA area, links similar problems, and updates a pattern-based index.

Inputs & outputs

You give it
Coding problem details, solution code, and user's experience
You get back
Pattern-tagged entry in `areas/dsa/` and updated `indexes/dsa.md`

When to use leetcode

  • Log solved coding problem
  • Analyze code patterns
  • Link related problems
  • Review algorithm performance

About this skill

Log a coding problem

Capture each practice problem as a pattern-tagged entry so the vault reveals, over time, which patterns the user has mastered and which keep costing them.

Inputs to gather

From the user's message (ask only for what's missing, in one question):

  • Problem name/link, their solution (pasted or a file path)
  • Whether they solved it unaided, and roughly how long it took
  • Where they got stuck, if anywhere

Procedure

  1. Identify the pattern(s) — the reusable technique, not the topic. "Two pointers on sorted array", not "arrays".
  2. Review the solution honestly. Correctness, complexity, idiomatic quality, edge cases missed. If their approach is suboptimal, explain the optimal one and, more importantly, the insight that leads to it. Do this review conversationally in chat — this is the interactive, valuable part.
  3. Write the entry to areas/dsa/lc-{number}-{kebab-name}.md using templates/leetcode-entry.md. Fill "The mistake to remember" with the single costliest error, phrased as a forward-looking rule ("When the array is sorted and you reach for a hashmap, check two pointers first").
  4. Link similar problems. Grep areas/dsa/ for entries sharing the pattern tag; add 2-3 to "Similar problems in vault" bidirectionally.
  5. Update indexes/dsa.md, which is organized by pattern, each pattern section listing its problems with a ✅ (clean solve) / ⚠️ (struggled) marker and a running tally. This index is the "which patterns do I fumble" dashboard — keep the tallies accurate.
  6. Commit: leetcode: LC 239 sliding-window-maximum (monotonic deque).

Rules

  • Be honest in the review; a flattering log is a useless log. But review the code, not the person — concrete and constructive.
  • If the user only pastes code, infer the problem from it, confirm your guess, then proceed.
  • Repeat attempts at a previously logged problem update the existing entry (append an "Attempt 2" section with date) — this repetition history is exactly what /quiz-me feeds on.

When not to use it

  • To provide a flattering log
  • To review the person instead of the code
  • When the user only pastes code without inferring the problem

Limitations

  • Requires honest review of the solution
  • Requires inferring the problem if only code is pasted
  • Repeat attempts update the existing entry rather than creating new ones

How it compares

This skill systematically logs and analyzes coding problems by pattern, providing a structured review and an index to track mastery, unlike simply storing solutions.

Compared to similar skills

leetcode side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
leetcode (this skill)017dNo flagsIntermediate
react-expert85moReviewAdvanced
rust-learner85moReviewBeginner
cartographer35moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

react-expert

reactjs

Use when researching React APIs or concepts for documentation. Use when you need authoritative usage examples, caveats, warnings, or errors for a React feature.

823

rust-learner

actionbook

Use when asking about Rust versions or crate info. Keywords: latest version, what's new, changelog, Rust 1.x, Rust release, stable, nightly, crate info, crates.io, lib.rs, docs.rs, API documentation, crate features, dependencies, which crate, what version, Rust edition, edition 2021, edition 2024, cargo add, cargo update, 最新版本, 版本号, 稳定版, 最新, 哪个版本, crate 信息, 文档, 依赖, Rust 版本, 新特性, 有什么特性

83

cartographer

kingbootoshi

Maps and documents codebases of any size by orchestrating parallel subagents. Creates docs/CODEBASE_MAP.md with architecture, file purposes, dependencies, and navigation guides. Updates CLAUDE.md with a summary. Use when user says "map this codebase", "cartographer", "/cartographer", "create codebase map", "document the architecture", "understand this codebase", or when onboarding to a new project. Automatically detects if map exists and updates only changed sections.

37

repo-research-analyst

parcadei

Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase

16

exploring-rust-crates

hashintel

Generate Rust documentation to understand crate APIs, structure, and usage. Use when exploring Rust code, understanding crate organization, finding functions/types/traits, or needing context about a Rust package in the HASH workspace.

33

investigation

talmolab

Scaffolds a structured investigation in scratch/ for empirical research and documentation. Use when the user says "start an investigation" or wants to: trace code paths or data flow ("trace from X to Y", "what touches X", "follow the wiring"), document system architecture comprehensively ("document how the system works", "archeology"), investigate bugs ("figure out why X happens"), explore technical feasibility ("can we do X?"), or explore design options ("explore the API", "gather context", "design alternatives"). Creates dated folder with README. NOT for simple code questions or single-file searches.

30

Search skills

Search the agent skills registry