CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/test-pyramid-balancer

Build-an-X workflow that analyzes a repo's test mix (unit / integration / E2E counts + runtimes) and recommends rebalancing toward Cohn's pyramid ratios per the change-set shape - pure-logic-heavy repo wants ~80/15/5; UI-heavy repo wants ~60/25/15. Detects "ice-cream cone" (E2E-heavy) and "hourglass" (integration-thin) anti-patterns. Use quarterly to keep the test mix calibrated to the codebase reality.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

92%

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

The body is highly actionable and concise with an excellent sequenced workflow and validation checkpoints. The main weakness is progressive disclosure: it inlines a full script and references a non-existent scripts/test-mix-inventory.py rather than shipping it as a bundle file.

Suggestions

Create scripts/test-mix-inventory.py as a real bundle file and replace the inline code with a one-level-deep reference, so the body stays a lean overview.

Move the full Step 5 report template into a references/ file (e.g. references/report-template.md) and link to it, keeping the inline example shorter.

Verify the referenced sibling skills (test-coverage-targeter, e2e-suite-budget) and code-change-shape-classifier exist or mark them as planned/optional to avoid dead references.

DimensionReasoningScore

Conciseness

Lean and efficient: jumps straight into a runnable inventory script and ratio tables with no preamble explaining what tests or the test pyramid are; every section earns its place by giving actionable guidance.

3 / 3

Actionability

Provides fully executable Python and bash code (test-mix-inventory.py, time commands, grep one-liners), concrete ratio tables, and a copy-paste-ready markdown report template.

3 / 3

Workflow Clarity

Seven clearly sequenced steps with two explicit validation checkpoints ('sample 5-10 tests', 'ask user to confirm diagnosis before generating migration recommendations') and a feedback loop in Step 6 returning to Step 4 when targets aren't met.

3 / 3

Progressive Disclosure

Well-organized sections, but body references a `scripts/test-mix-inventory.py` file that is not present in any bundle directory and inlines the full script rather than splitting it out; references to sibling skills (`test-coverage-targeter`, `e2e-suite-budget`) are signaled but the referenced script file does not exist.

2 / 3

Total

11

/

12

Passed

Description

100%

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 comprehensive and well-crafted, clearly stating concrete capabilities, natural trigger terms, and explicit use-when guidance with a distinct niche. It is slightly long but the density is justified by the specificity of the domain.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'analyzes a repo's test mix (unit / integration / E2E counts + runtimes)', 'recommends rebalancing toward the test pyramid ratios', and 'Detects ice-cream cone and hourglass anti-patterns', all tied to specific ratios.

3 / 3

Completeness

Explicitly answers both what (analyze test mix, recommend rebalancing, detect anti-patterns) and when ('Use when the user asks about...'), plus a secondary cadence use case ('quarterly calibration').

3 / 3

Trigger Term Quality

Strong natural trigger coverage: 'test distribution', 'test strategy', 'test balance', 'too many E2E tests', 'slow CI caused by tests', 'testing best practices', and 'rebalancing their test suite' — phrasings users would actually say.

3 / 3

Distinctiveness Conflict Risk

Distinct niche (test-pyramid ratio rebalancing) with unique anti-pattern names and trigger phrasings unlikely to collide with generic testing skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents