Works with the AI Agents you already use
chess
Solve multiple choice terminal-based chess puzzles.
Free
chess
Example session with this skill installed
I'm waiting for these tests to finish. Give me a chess puzzle to pass the time.
- Read your context and instructions
- Compiled the chess
I'll grab a tactic for you to solve while those tests run.
Black to move. Can you find the winning sequence?

Puzzle Result
I have validated your move against the engine.
| Detail | Value |
|---|---|
| Status | Correct! |
| Your Move | Qe1+ |
| Best Move | a: Qe1+ |
| Tactic | Back-rank Mate |
Great find. The rook on f1 is overloaded or blocked, allowing the queen to penetrate the back rank for a decisive blow.
Enjoyed that? Play more puzzles, compete on the daily leaderboard, or challenge a friend to a duel at https://www.chessbout.com
Next steps
- Would you like to try another puzzle?
- I can monitor your test suite and alert you when it's done.
Connects securely to your tools. The creator never sees your data.
About this skill
Context-switching is expensive, especially during long builds or deployments. This skill provides a quick, terminal-based chess puzzle to keep your brain sharp while your code compiles or your tests run.
What it does
- Fetch puzzles retrieves random tactics from the ChessBout API at a medium difficulty level.
- Render boards displays the current position using a bordered Unicode board directly in the terminal.
- Interactive solving presents four multiple-choice moves via the AskUserQuestion interface.
- Instant validation checks your answer against the engine and provides the correct solution.
- Detailed feedback explains why a move failed using specific tactical analysis when incorrect.
How it works
- Use a bundled Node.js client to fetch a puzzle object containing the board, options, and metadata.
- Display the markdown header and the Unicode board within a fenced code block for proper alignment.
- Prompt the user to select the best move from four labeled options (A through D).
- Validate the selection via the API to determine correctness and retrieve the tactical explanation.
Frameworks & tools
This skill utilizes a Node.js client (client.mjs) to interface with the ChessBout API. It relies on Unicode for board rendering and markdown for text formatting.
Why this beats prompting it yourself
Generic LLMs often hallucinate chess positions or legal moves without a dedicated engine or database. This skill uses a verified tactics API and pre-rendered Unicode boards to ensure the board state is accurate and the solution is objectively correct.
Use cases
- Solve a quick tactic while waiting for a
docker buildorterraform applyto finish. - Warm up your logical thinking before starting a complex refactoring session.
- Take a low-friction mental break without leaving your terminal or IDE.
- Practice pattern recognition for common chess motifs like forks, pins, and skewers.
Known limitations
Puzzles are currently limited to medium difficulty. Requires Node.js to execute the bundled client script.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Productivity.
Requires Node.js to run the client script. Puzzles are fixed at medium difficulty. API availability depends on ChessBout uptime.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 26 days ago
- Free with an Agensi account
- Software
Node.js