CtrlK
BlogDocsLog inGet started
Tessl Logo

sharaf/codebase-test-suite-audit

Use when the user wants a test suite audit, test quality or reliability review, regression-protection review, unit/integration/e2e test review, coverage or CI signal assessment, flaky CI investigation, fixture-realism review, spec-drift review, or generated-test validation for AI/LLM/agent-written code. Produces severity-ranked findings for weak assertions, oracle gaps, brittle fixtures, over-mocking, CI trust, and generated-code test risks.

100

1.31x
Quality

100%

Does it follow best practices?

Impact

100%

1.31x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Codebase Test Suite Audit

Use this skill to audit automated tests for relevance, validity, assertion and oracle strength, risk coverage, maintainability, CI signal quality, flakiness, fixture realism, and LLM-generated or agent-built codebase risks.

The skill is audit-first. It helps an agent inspect repo evidence, build a test system map, classify findings by severity, and produce a concrete remediation plan without rewriting tests unless the user explicitly asks for implementation.

When to Use

  • Test suite audits, test reviews, QA reviews, and test relevance reviews
  • Questions about whether tests are meaningful, brittle, flaky, shallow, or over-mocked
  • Reviews of generated tests, LLM-written tests, or agent-built codebases
  • Release, migration, refactor, or generated-code trust decisions

Install

tessl install sharaf/codebase-test-suite-audit

Organization

PathPurpose
skills/codebase-test-suite-audit/SKILL.mdMain workflow, evidence rules, and finding contract
skills/codebase-test-suite-audit/references/report-template.mdRequired report headings
skills/codebase-test-suite-audit/references/evidence-inventory.mdEvidence statuses and sampling prompts
skills/codebase-test-suite-audit/references/audit-domains.mdDomain-specific audit checks
skills/codebase-test-suite-audit/references/guardrails-and-success.mdSeverity guardrails and completion checks
tile.jsonTessl tile manifest and registry summary
README.mdRegistry-facing overview

Output Shape

The default deliverable is a test suite audit report with:

  • Executive summary
  • Evidence reviewed and open evidence gaps
  • Test system map
  • Findings ordered by severity
  • Domain-by-domain assessment
  • LLM and generated-test notes
  • CI signal, flakiness, coverage, mutation, and oracle notes
  • Prioritized remediation plan with verification steps

Eval Results

Tested on May 22, 2026 across three scenarios:

ScenarioBaselineWith skill
Weak oracle and assertionless test detection53%100%
LLM-generated test validity and spec drift audit94%100%
Flaky CI signal and fixture realism audit82%100%
Average76%100%

Activation: 3/3 scenarios naturally fired tessl__codebase-test-suite-audit.

Single-scenario multi-model spot check:

ModelBaselineWith skill
claude-haiku-4-562%99%
claude-sonnet-4-658%100%
claude-opus-4-661%100%
Workspace
sharaf
Visibility
Public
Created
Last updated
Publish Source
CLI
Badge
sharaf/codebase-test-suite-audit badge