cerebro-regression-tests

Add focused regression coverage for Cerebro review findings, bugs, and security edge cases.

1.11x

Quality

52%

Does it follow best practices?

Impact

94%

1.11x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.factory/skills/cerebro-regression-tests/SKILL.md

Quality

Discovery

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description provides a rough sense of purpose—adding regression test coverage related to Cerebro reviews—but lacks concrete actions, explicit trigger guidance, and natural user-facing keywords. It would be difficult for Claude to reliably distinguish this skill from other testing or security-related skills in a large skill library.

Suggestions

Add an explicit 'Use when...' clause specifying triggers, e.g., 'Use when the user asks to write regression tests for Cerebro review findings, fix-verification tests, or security edge-case coverage.'

List specific concrete actions such as 'write unit tests for reported bugs, create security boundary test cases, generate regression test suites from review comments.'

Include natural trigger terms users might say, such as 'regression test', 'test coverage', 'bug verification', 'security test', 'Cerebro findings'.

Dimension	Reasoning	Score
Specificity	It names a domain (regression testing for Cerebro review findings) and some actions (add coverage for bugs, security edge cases), but doesn't list concrete specific actions like 'write test cases', 'generate test fixtures', or 'validate patches'.	2 / 3
Completeness	It describes what (add regression coverage for findings, bugs, security edge cases) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' should cap completeness at 2, and the 'what' is also only partially clear, warranting a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'regression', 'bugs', 'security edge cases', and 'Cerebro review', but 'Cerebro' is a proprietary/internal term that may not be naturally used by all users. Missing common variations like 'test', 'testing', 'test coverage', 'bug fix verification'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Cerebro review findings' provides some distinctiveness as it references a specific tool/process, but 'regression coverage', 'bugs', and 'security edge cases' are broad enough to overlap with general testing or security-related skills.	2 / 3
	Total	7 / 12 Passed

Implementation

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a concise, well-scoped skill that efficiently communicates regression testing guidelines for a specific project. Its main weakness is the lack of concrete executable examples (e.g., a sample table-driven test structure) and the absence of explicit validation/feedback loops in the workflow. The content would benefit from a small code example and clearer error-recovery steps.

Suggestions

Add a concrete example of a table-driven Go regression test skeleton showing the expected structure (test name, input, expected error/output fields).

Add an explicit feedback loop: e.g., 'If the new test passes against unfixed code, the test is not correctly capturing the regression — tighten assertions and re-run.'

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. It assumes Claude knows Go testing conventions, what table-driven tests are, and how regression testing works. Every line adds specific, non-obvious guidance.	3 / 3
Actionability	The instructions are specific about what to do (table-driven tests, `-count=1 -v`, `make verify`) but lack concrete code examples. A sample table-driven test skeleton or example test case would make this fully actionable and copy-paste ready.	2 / 3
Workflow Clarity	There is a reasonable sequence (reproduce bug → write test → run focused test → run make verify), but validation checkpoints are implicit. There's no explicit feedback loop for when the test doesn't fail against unfixed behavior or when `make verify` fails.	2 / 3
Progressive Disclosure	This is a simple, short skill under 50 lines with no need for external references. The content is well-organized into Instructions and Success Criteria sections, which is appropriate for its scope.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: writer/cerebro
Commit: 3aeaf20

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.