multi-ai-testing

Test-driven development with independent verification to prevent test gaming. TDD workflows, test generation, coverage validation (≥80% gate, ≥95% target), property-based testing, edge case discovery. Use when implementing TDD workflows, generating comprehensive test suites, validating test coverage, or preventing test gaming through independent multi-agent verification.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/multi-ai-testing/SKILL.md

Quality

Content

58%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 skill's workflows are clearly sequenced with strong validation loops, but the body is heavily padded with repetition and inlines material that should be split into reference files. Referenced bundle paths (examples/) are missing entirely.

Suggestions

Deduplicate the coverage-gate (≥80%/≥95%) and quality-score statements that recur across Overview, Workflows, Quality Standards, and Quick Reference; state them once in Quality Standards and reference that section.

Move Appendix A (Independence Protocol), Appendix B (Technical Foundation), and the CI/CD YAML into separate reference files under references/ and link to them, rather than inlining ~150 lines of supplementary material.

Create the referenced examples/ directory (or remove the 'see examples/' pointer) so progressive-disclosure references resolve to real files.

Dimension	Reasoning	Score
Conciseness	The ~790-line body is noticeably verbose: coverage gates (≥80%/≥95%) and quality-score tables are restated many times, Quick Reference repeats earlier sections, and code blocks embed full prompt strings with placeholders like "[paste from spec]".	2 / 5
Actionability	Provides concrete executable guidance — TypeScript task() calls, bash commands (npm test --coverage), and a CI yaml workflow — though several prompt blocks contain illustrative placeholders rather than fully copy-paste-ready code.	4 / 5
Workflow Clarity	All four workflows are explicitly sequenced with numbered steps and validation checkpoints (confirm tests fail, verify pass, independent score ≥90), plus per-workflow Validation checklists and a fail→implement→pass→verify feedback loop in the TDD workflow.	5 / 5
Progressive Disclosure	Content is a single monolithic SKILL.md with appendices, CI/CD config, and framework tables inlined that would belong in separate reference files, and it points to an examples/ directory that does not exist alongside absent references/scripts/assets bundles.	2 / 5
	Total	13 / 20 Passed

Description

88%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 specific, complete, and well-targeted, clearly stating both what the skill does and when to use it with concrete trigger phrases. Minor gaps in trigger term synonyms keep it just below a perfect score on two dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "test generation", "coverage validation (≥80% gate, ≥95% target)", "property-based testing", "edge case discovery" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ("Test-driven development with independent verification... TDD workflows, test generation, coverage validation...") and when ("Use when implementing TDD workflows, generating comprehensive test suites, validating test coverage, or preventing test gaming...").	5 / 5
Trigger Term Quality	Strong natural keywords ("TDD", "test generation", "comprehensive test suites", "test coverage", "test gaming", "property-based testing") but missing common variations like "unit tests" or "E2E".	4 / 5
Distinctiveness Conflict Risk	Clear niche around independent multi-agent verification and preventing test gaming is mostly distinct from generic testing skills, with only minor overlap risk against sibling multi-ai-implementation/verification skills.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (797 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/multi-ai-testing/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.