CtrlK
BlogDocsLog inGet started
Tessl Logo

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. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

68

Quality

82%

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

The canonical home for this skill is tdg-personal/ai-regression-testing

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 highly actionable with executable code and a clearly sequenced, validation-gated workflow. Its main weaknesses are verbosity (a long production anecdote and repeated FAIL/PASS blocks) and the absence of progressive disclosure — inlining config/helpers/patterns rather than splitting them into reference files.

Suggestions

Move the full vitest.config.ts, setup.ts, and helpers.ts into a references/ file and keep only a minimal inline snippet, to tighten conciseness and add progressive disclosure.

Condense the four pattern blocks into a compact FAIL/PASS table or split them into a references/patterns.md, linking from a short inline summary.

Trim the multi-fix production anecdote in "The Core Problem" to one or two lines; the example code already illustrates the blind-spot pattern.

DimensionReasoningScore

Conciseness

Most content is concrete and non-obvious rather than concepts Claude already knows, but the multi-fix production anecdote and the four full FAIL/PASS pattern blocks run long; the body could be tightened without losing value, so it sits at the mostly-efficient 3 anchor rather than the lean 5.

3 / 5

Actionability

Provides fully executable, copy-paste-ready artifacts (vitest.config.ts, setup.ts, helpers.ts, real test files with assertions, a bug-check command definition, and concrete FAIL/PASS code per pattern) covering the common cases, matching the 5 anchor.

5 / 5

Workflow Clarity

The bug-check workflow is explicitly sequenced with validation checkpoints (mandatory tests first, branching PASS/FAIL, build check, then AI review, then per-fix regression tests) and feedback loops shown in the diagram, including the gate "Only proceed to Step 2 if both pass".

5 / 5

Progressive Disclosure

No bundle files exist and all content is inlined in a ~380-line SKILL.md; sections are well-organized, but the full vitest config, test helpers, and the four-pattern catalog arguably belong in separate reference files, so structure is present but content that should be split is inline.

3 / 5

Total

16

/

20

Passed

Description

87%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 strong: it states concrete capabilities in third person, gives an explicit "Use when" trigger with two specific conditions, and carves out a distinctive niche. Minor gains are possible by tightening "patterns" into more concrete verbs and adding a synonym or two.

DimensionReasoningScore

Specificity

Names multiple concrete actions ("Sandbox-mode API testing without database dependencies", "automated bug-check workflows", "patterns to catch AI blind spots where the same model writes and reviews code") in third person, though "patterns" is slightly abstract, leaving minor coverage gaps below the comprehensive 5 anchor.

4 / 5

Completeness

Clearly answers "what" (regression testing strategies, sandbox-mode API testing, bug-check workflows, blind-spot patterns) and explicitly provides a "Use when" clause with two concrete trigger conditions, matching the 5 anchor.

5 / 5

Trigger Term Quality

Includes natural user-facing terms ("regression testing", "AI-assisted development", "adding regression coverage", "bug-check") plus the vivid trigger "when the same model both wrote and reviewed a change", but misses a few common synonyms, so it is not quite the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (regression testing for AI-assisted development, anchored on the model-writes-and-reviews-code blind spot) with distinct triggers and minimal overlap with other skills.

5 / 5

Total

18

/

20

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
Reviewed

Table of Contents

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.