Chess Engine Perft Buddy

Finds an incorrect or missing move of user's chess engine by comparing perft results with Stockfish. Use when user reports getting wrong perft results.

Security Scan

The skill's requirements and runtime instructions are consistent with its stated purpose (comparing perft output with Stockfish) and do not request unrelated credentials or surprising installs.

Purpose & Capability

Name/description ask to compare perft results with Stockfish; the only required binary is 'stockfish', which is exactly what's needed to compute reference perft counts. The skill expects the user's engine/test-case to provide perft results or a perft utility (described in SKILL.md) — that explains why no extra engine binary is declared. No unrelated environment variables or config paths are requested.

Instruction Scope

SKILL.md instructs the agent to extract a test file/test case from the user's commands, run perft in the user's engine (or a supplied tool) and run Stockfish locally to compare results. These actions are within scope (they necessarily require reading user-provided test files and invoking local binaries). This grants the agent discretion to read/execute user-specified files and binaries — expected for this task but worth noting: the agent will operate on whatever test files or engine binaries the user points it at.

Install Mechanism

The registry metadata lists no install spec, but SKILL.md contains a metadata.install block suggesting 'apt install stockfish'. Installing stockfish via apt is a low-risk, expected install for this skill. The minor inconsistency between the registry install spec and the SKILL.md metadata is likely harmless but should be noted.

Credentials

No environment variables, credentials, or config paths are requested. The skill does not ask for secrets or unrelated tokens — proportional to its functionality.

Persistence & Privilege

The skill is not forced-always, does not request elevated persistent privileges, and does not modify other skills or system-wide settings. Normal autonomous invocation is allowed (platform default).

Assessment

This skill appears coherent for diagnosing perft mismatches: it will read the user-supplied test file and invoke local perft utilities (the user's engine or a provided tool) and the local 'stockfish' binary. Before running: 1) ensure 'stockfish' is installed from a trusted source (apt is suggested); 2) inspect the test case and any helper scripts the user provides — the agent will read and may execute them, so do not point it at untrusted binaries; 3) be aware the agent will run local commands but does not request network access or secrets; and 4) note the small metadata inconsistency (SKILL.md suggests an apt install while the registry listing shows no install spec) — that's likely benign but worth checking.

Perft diff skill

The user's chess engine is generating illegal moves or not generating all legal moves in some position. This is demonstrated by incorrect perft results.

By systematically following the following workflow steps you will end up with a sequence of moves leading to an illegal or a missed move (an anomaly move). The sequence to the anomaly move is your final result you must log to the user.

Workflow

From the user's commands you must extract the specific test file and test case which demonstrates the perft result mismatch.

From the test case you must extract:

• x = the position's FEN notation

• d = the desired perft depth.

Now you must simply follow this stepwise algorithm:

Let search position be x.

Let remaining depth be d.

1. Log perft from the search position in the user's engine. The test file may include a tool to perform perft logging. You are free to use that or implement your own.

2. Log perft from search position in Stockfish.

3. There is at least one mismatch. Choose any move that has a mismatched result. The search position becomes the search position with your chosen move played. Remaining depth decrements by one.

4. If the remaining depth is 0, stop. Else go to step 1.

5. You now have the move sequence to an anomaly move. Report it to the user and you are done.

There is an example of applying this workflow in practice in {basedir}/example.txt . Inspect it for reference.

Notes

Important:

• Don't modify the code base apart from the specified test case and possibly creating your own logging tool.

• By systematically following the workflow steps you will end up with a sequence of moves leading to an illegal or a missed move. That is your final result.

• DON'T try to find out why the engine is not working. Just demonstrate that it doesn't work by finding the move sequence leading to a missed or an illegal move.