Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

leetcode-problem-fetcher · a5c-ai | DecimalAI

a5c-ai/leetcode-problem-fetcher

SkillScore55Maintained

Fetch and parse LeetCode problems with metadata, constraints, examples, hints, difficulty ratings, and related problems. Integrates with LeetCode API for comprehensive problem data retrieval.

researchby a5c-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/a5c-ai-leetcode-problem-fetcher/SKILL.md

decimalai skills pull a5c-ai-leetcode-problem-fetcher --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/a5c-ai-leetcode-problem-fetcher/SKILL.md https://app.decimal.ai/s/a5c-ai-leetcode-problem-fetcher/SKILL.md

Raw file: /s/a5c-ai-leetcode-problem-fetcher/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-leetcode-problem-fetcher.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 54d ago

Yes — +50% lift · at higher cost+56% tokens0% turns55% of whole cases pass with skill (12/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	92%	0%
case-02	✗→✓	▲ Improved	125%	0%
case-09	✗→✓	▲ Improved	-15%	0%
case-10	✗→✓	▲ Improved	21%	0%
case-11	✗→✓	▲ Improved	-17%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/31/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

a5c-ai / babysitter

library/specializations/algorithms-optimization/skills/leetcode-problem-fetcher/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

leetcode-problem-fetcher

A specialized skill for fetching and parsing LeetCode problems with complete metadata, suitable for competitive programming practice, interview preparation, and algorithm learning workflows.

Purpose

Extract comprehensive problem data from LeetCode including:

Problem statements and descriptions
Input/output constraints and formats
Test cases and hidden constraints
Problem difficulty, tags, and acceptance rate
Related problems and pattern tags
Hints and solution approaches

Capabilities

Core Features

Problem Retrieval

Fetch problems by title slug (URL-friendly name)
Retrieve daily challenge problems
Search problems by category, tags, difficulty, or keywords
Access premium problem alternatives when available

Metadata Extraction

Difficulty level (Easy, Medium, Hard)
Acceptance rate and submission statistics
Problem tags and categories
Related problems and similar questions
Company tags (when available)

Content Parsing

Problem description in markdown format
Input/output examples with explanations
Constraints and edge cases
Follow-up questions and optimizations
Code templates for multiple languages

User Data Access

User profile and statistics
Contest ranking and history
Submission history and solutions
Progress tracking across problem sets

Integration Options

MCP Server (Recommended)

bash
# Install LeetCode MCP Server by jinzcdev
claude mcp add-json "leetcode" '{"type":"stdio","command":"npx","args":["-y","@jinzcdev/leetcode-mcp-server","--site","global"]}'

Available MCP Tools:

get_daily_challenge - Fetch daily LeetCode challenge
get_problem - Retrieve problem by titleSlug
search_problems - Filter by category, tags, difficulty, keywords
get_user_profile - Access user data
get_user_contest_ranking - Track contest performance

Direct API Integration

javascript
// GraphQL endpoint for LeetCode
const LEETCODE_GRAPHQL = 'https://leetcode.com/graphql';

// Query for problem details
const problemQuery = `
  query getProblem($titleSlug: String!) {
    question(titleSlug: $titleSlug) {
      questionId
      title
      titleSlug
      content
      difficulty
      topicTags { name slug }
      hints
      sampleTestCase
      codeSnippets { lang code }
      stats
    }
  }
`;

Browser Extension

Competitive Companion - Parses problems from LeetCode and 115+ other online judges:

Chrome: competitive-companion
Firefox: competitive-companion

Usage

Fetch a Problem

bash
# Using MCP Server
leetcode get_problem --titleSlug "two-sum"

# Output includes:
# - Problem title and description
# - Difficulty and acceptance rate
# - Topic tags
# - Examples and constraints
# - Code templates

Search Problems

bash
# Search by difficulty and tags
leetcode search_problems --difficulty MEDIUM --tags "dynamic-programming,array"

# Search by keyword
leetcode search_problems --keyword "substring"

Get Daily Challenge

bash
# Fetch today's daily challenge
leetcode get_daily_challenge

Output Schema

json
{
  "problem": {
    "id": "string",
    "title": "string",
    "titleSlug": "string",
    "difficulty": "Easy|Medium|Hard",
    "acceptanceRate": "number",
    "description": "string (markdown)",
    "constraints": ["string"],
    "examples": [
      {
        "input": "string",
        "output": "string",
        "explanation": "string"
      }
    ],
    "hints": ["string"],
    "topicTags": ["string"],
    "similarQuestions": ["string"],
    "codeTemplates": {
      "python3": "string",
      "cpp": "string",
      "java": "string"
    }
  },
  "metadata": {
    "fetchedAt": "ISO8601 timestamp",
    "source": "leetcode.com|leetcode.cn"
  }
}

Integration with Processes

This skill enhances the following processes:

leetcode-problem-solving - Core problem-solving workflow
pattern-recognition - Identifying algorithmic patterns
faang-interview-prep - FAANG interview preparation

References

Error Handling

| Error | Cause | Resolution | |-------|-------|------------| | PROBLEM_NOT_FOUND | Invalid titleSlug | Verify problem URL or slug | | RATE_LIMITED | Too many requests | Implement exponential backoff | | AUTH_REQUIRED | Premium problem | Use alternative or authenticate | | NETWORK_ERROR | Connection failed | Check network, retry with backoff |

Best Practices

Caching: Cache problem data to reduce API calls
Rate Limiting: Respect LeetCode's rate limits (use delays between requests)
Error Handling: Gracefully handle premium/locked problems
Offline Mode: Store fetched problems for offline practice
Data Freshness: Re-fetch periodically for updated statistics

Illustrative Want to see what a5c-ai/leetcode-problem-fetcher would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/1/2026, 00:31 UTC · 22 cases

Lift

+50%

55% vs 5%

Agent turns

1.0 vs 1.0

Tokens

+56%

2,022.64 vs 1,300.73

fail → pass · 11pass → pass · 1fail → fail · 10

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 I want to review the LeetCode problem '3sum'. Please retrieve its problem statement formatted in markdown, difficulty level, acceptance stats, input/output example cases with explanations, constraints, hints, and initial code templates for Python3 and C++ formatted in JSON.	fail→pass	8,515	9,522	+12%	1	1	0%	1,912	3,679	+92%	0	0	—
case-02 I want to configure Claude Desktop to connect to an MCP server for fetching LeetCode problem data. Write the JSON CLI command to add this stdio server using npx.	fail→pass	4,422	3,219	-27%	1	1	0%	909	2,042	+125%	0	0	—
case-03 What specific tool name provided by the LeetCode MCP server should be called to fetch today's featured problem?	pass→pass	5,159	1,504	-71%	1	1	0%	885	1,575	+78%	0	0	—
case-04 We want to query the LeetCode MCP server for medium-difficulty dynamic programming problems matching a keyword. What is the standard tool name to run this search?	fail→fail	4,386	1,915	-56%	1	1	0%	779	1,652	+112%	0	0	—
case-05 Which tool in the LeetCode MCP server retrieves a user's contest history and ranking?	fail→fail	5,915	2,761	-53%	1	1	0%	992	1,736	+75%	0	0	—
case-06 What is the exact endpoint URL used for sending Direct API GraphQL queries to LeetCode global?	fail→fail	5,192	1,543	-70%	1	1	0%	817	1,591	+95%	0	0	—
case-07 Write a GraphQL query to fetch problem details from LeetCode. What root query field and argument variable name should be passed to request a problem by its URL slug?	fail→fail	5,392	3,619	-33%	1	1	0%	1,092	1,919	+76%	0	0	—
case-08 What popular browser extension parses problem data across LeetCode and over 115 other competitive programming online judges into standard JSON format?	fail→fail	4,188	2,715	-35%	1	1	0%	676	1,727	+155%	0	0	—
case-09 When requesting a paid subscriber problem without valid authentication, what standardized error code string is returned, and what is the prescribed resolution?	fail→pass	10,993	1,837	-83%	1	1	0%	1,937	1,645	-15%	0	0	—
case-10 When too many automated problem requests are sent in a short period, what error code is returned, and what strategy should be implemented?	fail→pass	7,011	1,724	-75%	1	1	0%	1,342	1,629	+21%	0	0	—
case-11 If a non-existent titleSlug like 'two-sum-nonexistent' is passed to the fetcher, what error code string is returned?	fail→pass	10,342	1,554	-85%	1	1	0%	1,949	1,618	-17%	0	0	—
case-12 In the standard fetcher output JSON schema, what are the two allowed exact string values for the metadata source field?	fail→pass	12,287	1,705	-86%	1	1	0%	2,122	1,609	-24%	0	0	—
case-13 What format standard is required for the fetchedAt field under the metadata object in the problem schema?	fail→fail	8,080	1,927	-76%	1	1	0%	1,238	1,636	+32%	0	0	—
case-14 Inside the output JSON schema, the problem object contains an array of examples. What are the three required keys in each example item?	fail→fail	3,632	1,803	-50%	1	1	0%	631	1,600	+154%	0	0	—
case-15 Construct the leetcode CLI command to search for medium difficulty problems tagged with dynamic programming and array.	fail→pass	5,554	1,995	-64%	1	1	0%	991	1,653	+67%	0	0	—
case-16 Construct the leetcode CLI command to search for problems matching the keyword 'substring'.	fail→pass	3,194	1,787	-44%	1	1	0%	558	1,609	+188%	0	0	—
case-17 What command should be run via the CLI tool to fetch today's daily problem challenge?	fail→pass	6,576	1,277	-81%	1	1	0%	1,157	1,475	+27%	0	0	—
case-18 When writing a script that fetches multiple problem descriptions in batch, what practice is advised to stay within LeetCode request limits?	fail→fail	11,280	10,022	-11%	1	1	0%	2,036	3,339	+64%	0	0	—
case-19 To reduce API request volume and allow practice without an active internet connection, what two strategies should be implemented?	fail→fail	6,614	3,012	-54%	1	1	0%	1,165	1,837	+58%	0	0	—
case-20 I have written a Python solution for two-sum. How do I submit this solution to LeetCode's online judge and check runtime/memory results using this problem fetcher tool?	fail→pass	11,823	7,575	-36%	1	1	0%	2,376	2,711	+14%	0	0	—
case-21 How do I execute sample test cases against my C++ solution binary locally using this problem fetcher command-line interface?	fail→pass	9,762	8,535	-13%	1	1	0%	1,866	2,988	+60%	0	0	—
case-22 Please use the fetcher tool to download Codeforces problem 158A (Next Round) with its sample test cases.	fail→fail	5,478	11,092	+102%	1	1	0%	1,186	3,228	+172%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +50 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 4.6%
Pass rate with the skill: 54.6%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 1
Skill version measured: v1
Run completed: 8/1/2026, 00:31 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

I want to review the LeetCode problem '3sum'. Please retrieve its problem statement formatted in markdown, difficulty level, acceptance stats, input/output example cases with explanations, constraints, hints, and initial code templates for Python3 and C++ formatted in JSON.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run55

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+78% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 54 days ago

Other measured skills in the registry, with their headline benchmark lift.