ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

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

Quality

Content

77%

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 with executable code and a clearly sequenced, validation-gated bug-check workflow. The main weaknesses are verbosity in the narrative example and a monolithic single-file structure with no progressive disclosure despite the length.

Suggestions

Move the four-pattern catalog and the bug-check command definition into reference files (e.g. references/patterns.md, references/bug-check.md) and summarize them in SKILL.md with one-level-deep links.

Tighten the 'Core Problem' four-fix narrative to a compact before/after rather than a step-by-step story to reduce token cost.

Keep only the minimal representative test example inline and link the rest to a reference, preserving the lean overview pattern.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete code, but the 'Core Problem' four-fix narrative and prose around each pattern could be tightened; it explains motivating context at length that partly pads tokens. Not a 3 because some explanatory prose does not earn its place; not a 1 because it is not padded with concepts Claude already knows.	2 / 3
Actionability	Provides complete, executable code — vitest config, test helpers, regression test examples, and FAIL/PASS pattern snippets — that is copy-paste ready; matches the 'fully executable code, specific examples' anchor. Not a 2 because nothing here is pseudocode or missing key details.	3 / 3
Workflow Clarity	The bug-check workflow is an explicit sequence with validation checkpoints — 'Run npm run test / npm run build FIRST', 'If tests fail → highest priority bug', 'Only proceed to Step 2 if both pass' — with a feedback loop to write regression tests per fix. Not a 2 because checkpoints are explicit, not implicit.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets are absent) and the ~380-line skill is a single monolithic file with well-organized sections but content that could be split into one-level-deep references. Not a 3 because the under-50-line simple-skill exception does not apply and nothing is split out; not a 1 because sections are clearly organized, not a wall of text.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 and distinctive with good natural trigger terms, but it omits an explicit 'Use when...' clause, which caps completeness at 2. Adding an explicit trigger sentence would raise the strongest remaining weakness.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when an AI agent has modified API routes or backend logic and you need regression tests to catch self-review blind spots.'

Surface concrete trigger phrases users would actually say (e.g. 'bug-check', 'regression test', 'sandbox mode test') more prominently as natural-language triggers.

Dimension	Reasoning	Score
Specificity	Quotes several concrete actions — 'Sandbox-mode API testing without database dependencies', 'automated bug-check workflows', and 'patterns to catch AI blind spots' — matching the 'lists multiple specific concrete actions' anchor; not a 2 because it goes well beyond naming a single domain.	3 / 3
Completeness	It clearly states what the skill does, but lacks any explicit 'Use when...' trigger clause — per the rubric guideline, a missing explicit trigger guidance caps completeness at 2; not a 3 for that reason, and not a 1 because the 'what' is fully present.	2 / 3
Trigger Term Quality	Natural trigger terms a user would say appear directly — 'Regression testing', 'bug-check workflows', 'sandbox-mode API testing', 'AI-assisted development'; not a 2 because it covers multiple common variations rather than only one relevant keyword.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply defined — regression testing specifically for AI-assisted development with sandbox-mode testing — making overlap with other skills unlikely; not a 2 because the framing is far more specific than generic testing skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 754b8dd

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.