← Back to Skills Marketplace
Chess Engine Perft Buddy
by
ottofreund
· GitHub ↗
· v1.0.2
· MIT-0
92
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install perft-diff
Description
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.
Usage Guidance
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.
Capability Analysis
Type: OpenClaw Skill
Name: perft-diff
Version: 1.0.2
The skill is designed to debug chess engines by comparing 'perft' (performance test) results against Stockfish to identify move generation errors. The workflow described in SKILL.md and example.txt is logically sound for its stated purpose and does not involve any high-risk behaviors, data exfiltration, or malicious execution.
Capability Assessment
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).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install perft-diff - After installation, invoke the skill by name or use
/perft-diff - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Cleaned up messy characters in YAML
v1.0.1
No functional changes; updated formatting in SKILL.md for consistency.
- Reformatted SKILL.md to use standard YAML syntax.
- WIndows CRLF -> Unix LF
- No changes to functionality or workflow.
v1.0.0
Initial release of perft-diff.
- Finds incorrect or missing moves in a user's chess engine by comparing perft results with Stockfish.
- Guides users to extract the position (FEN) and depth from their test case and systematically compare move counts.
- Provides a workflow to identify and log a sequence of moves leading to the anomaly.
- Includes clear instructions and an example for reference.
- Emphasizes reporting the anomalous move sequence, without diagnosing or fixing the underlying bug.
Metadata
Frequently Asked Questions
What is 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. It is an AI Agent Skill for Claude Code / OpenClaw, with 92 downloads so far.
How do I install Chess Engine Perft Buddy?
Run "/install perft-diff" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Chess Engine Perft Buddy free?
Yes, Chess Engine Perft Buddy is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Chess Engine Perft Buddy support?
Chess Engine Perft Buddy is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Chess Engine Perft Buddy?
It is built and maintained by ottofreund (@ottofreund); the current version is v1.0.2.
More Skills