cerebro-regression-tests

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

1.11x

Quality

73%

Does it follow best practices?

Impact

94%

1.11x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.factory/skills/cerebro-regression-tests/SKILL.md

Quality

Content

92%Weight 40%Scale 1-5

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

The body is an exemplary lean, instruction-only skill: concrete guidance, a clearly sequenced workflow with an explicit verification step, and a success checklist, with zero padding. The only minor gap is the absence of a copy-paste-ready command line or table-driven test example.

Dimension	Reasoning	Score
Conciseness	The ~20-line body is lean and every line earns its place: "Reproduce the reported bug class with the smallest package-level test" and "Run the focused package test with `-count=1 -v`" instruct without explaining Go, table-driven tests, or make, which Claude already knows. Not a 4 because there is no over-explanation anywhere to trim.	5 / 5
Actionability	Guidance is concrete and executable for an instruction-only skill: specific test style ("table-driven Go tests"), exact flags ("`-count=1 -v`"), a real command ("`make verify`"), and enumerated edge-case categories ("URL, host, tenant, auth, pagination, size-limit, and error-mapping fixes"). It is not a 5 because no copy-paste-ready full command line (e.g. `go test ./... -count=1 -v`) or example table-driven test skeleton is provided.	4 / 5
Workflow Clarity	The five-step sequence is clearly ordered from reproduce → write → include security cases → place fixtures → run and verify, with an explicit validation step ("Run the focused package test with `-count=1 -v`, then run `make verify`") and a "Success Criteria" checklist including that the test "fails against the unfixed behavior". Not destructive or batch, so the validation cap does not apply, and the simple-skill exception for a clear single-purpose flow holds.	5 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references (none exist in the bundle), and is organized into well-signaled "Instructions" and "Success Criteria" sections, satisfying the simple-skill exception for a top progressive-disclosure score.	5 / 5
	Total	19 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 is concise, specific, and clearly scoped to the Cerebro project, with a concrete single capability statement. Its main weakness is the complete absence of any 'when to use' trigger clause, which both caps completeness and limits trigger-term coverage.

Suggestions

Append an explicit trigger clause, e.g. "Use when a Cerebro review, bug fix, or security finding needs a regression test" — this would raise completeness from 3 to 4-5.

Add natural trigger phrases users would actually say, such as "regression test", "write a test for this bug", or "add coverage for this fix", to improve trigger-term quality.

Optionally enumerate a couple of concrete actions (e.g. "reproduce the bug class, write table-driven Go tests, run package tests") to move specificity from one action toward several.

Dimension	Reasoning	Score
Specificity	"Add focused regression coverage" names the domain and one concrete action, applied to specific target classes ("Cerebro review findings, bugs, and security edge cases"), but it lists only a single action verb rather than several distinct actions, so it matches the 3 anchor and falls short of 4's "lists several specific actions".	3 / 5
Completeness	The "what" is clear and concrete, but there is no "Use when..." clause or equivalent trigger guidance; the judging guideline explicitly caps completeness at 3 for a missing 'when'. It is not a 2 because the 'what' is specific and multi-faceted, not vague.	3 / 5
Trigger Term Quality	Relevant keywords are present ("regression coverage", "bugs", "security edge cases"), but common natural variations users would say — "regression test(s)", "write tests", "add a test for this bug" — are missing, matching the 3 anchor (some relevant keywords, missing variations) rather than 4's fuller coverage.	3 / 5
Distinctiveness Conflict Risk	The project-scoped "Cerebro" naming plus the regression-coverage niche make it mostly distinct with minor overlap risk against a generic test-writing skill. It is not a 5 because a user asking to "add tests for a bug" without mentioning Cerebro could plausibly trigger a general testing skill instead.	4 / 5
	Total	13 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: writer/cerebro
Path: .factory/skills/cerebro-regression-tests/SKILL.md
Commit: 20bd7fe

Reviewed: 6 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.