manual-testing

manual-testing is an Agent behaviour & coding discipline skill for AI agents, published by relaticle in the relaticle repository on GitHub. Skillspace rates manual-testing B (84/100) and it passed the safety scan; the rating is based on static analysis only.

Use immediately after finishing any code change in Relaticle — implementation, fix, refactor, migration — before reporting work as complete. The skill itself decides whether to run; do not skip on 'small' changes. Triggers an adversarial post-task QA pass: reads the diff, scores risk, generates an SBTM charter, drives a real browser through a pairwise-reduced test matrix across Filament/Livewire/REST/MCP surfaces, classifies findings by severity, auto-fixes High findings within strict guardrails, and promotes High+ findings to permanent Pest browser regression tests. Reports land in .context/testing/reports/. Skip with [skip-qa] in the user message or MANUAL_TESTING_SKIP=1.

Grade

B

Quality

84 / 100

Safety

Passed

GitHub stars

1,451

Unproven: rated by static analysis only, not yet compared head-to-head.

Not launch-quality. It is graded B with a clean safety verdict, but our quality filters exclude it: a model that read it found it written only for the repository it lives in. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.