Spec Compliance Judge — Testing & QA agent for Claude Code
Use this agent when you need to determine whether a solution correctly implements a specific part of a specification.
How to install Spec Compliance Judge
Installs to ~/.claude/agents/sprocketlab-slop-code-bench-spec-compliance-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/SprocketLab/slop-code-bench/HEAD/.claude/agents/spec-compliance-judge.md -o ~/.claude/agents/sprocketlab-slop-code-bench-spec-compliance-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Spec Compliance Judge does
name: spec-compliance-judge description: Use this agent when you need to determine whether a solution correctly implements a specific part of a specification. This is particularly useful during code review, test failure analysis, or when validating that implementation matches requirements. Examples of when to use this agent:\n\n\nContext: A test case is failing and you need to understand if the code is wrong or the test expectation is incorrect.\nuser: "Test case 'validate_email_for
Alternatives in Testing & QA
- Arbiter — You are a specialized validation agent 3.6k ★
- Distill — Extract an Allium specification from an existing codebase 474 ★
- Review Test Concurrency — Reviews test code for concurrency testing quality: whether multi-threaded behavior is properly verified, race 432 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Engine QA Review Usability
After a change you've asked for is built, checks whether it actually works well for the people who use it — is
Testing Reviewer
Reviews test coverage for PR changes, analyzing whether changes are adequately tested at appropriate levels (u
Mutant Triager
Runs Stryker on specific files of a Node/TypeScript service and returns only the real test gaps, with discarde
Spec Compliance
Reviews whether code matches docs/specs — every rule has a test, monetary precision holds, feature interaction
Eval Improver
Improver role of the D365FO agent eval loop. Reads the corpus of run records, ranks failure clusters, reproduc
Sms Assistant Test Writer
Use this agent when the user needs to write or improve unit tests for the SMS assistant functionality, particu
Related Skills
Intent Based Prompt Calibration
A system for automatic prompt optimization using Claude 3.5 models. IPC enables dynamic prompt refinement thro
Spec Validate
Analyze a specification document to determine if it has enough detail for autonomous implementation. Use to va
Validate Replica
Validate a ReplicaClient implementation in Litestream. This command helps ensure a replica client correctly im