Entdecke geprüfte X-Beiträge über Skills, die Menschen dahinter und die erwähnten Projekte.
Gezählt werden nur erfasste und geprüfte Beiträge über Skills. Ein leerer Tag bedeutet, dass hier nichts erfasst wurde. Datumsangaben in UTC.
8 erfasste Beiträge
Adds tester-army/e2e to selected projects, assigning one coding subagent per project and a verifier for each loop to cover flows, run tests, and report failures.
Loris Comba explains blueline, a collection of six marketing-site review Skills. Its checks connect findings to evidence, severity, proposed fixes and verification steps; the Article demonstrates noindex and price-mismatch findings on a deliberately faulty local test site.
Onlyoneuche introduces an early Skill for reviewing code changes against OWASP ASVS controls, tracing affected security paths, and reporting evidence, gaps and runtime checks.
GStack adds test-audit to review duplicate or low-value tests. It produces evidence cards before any approved changes.
Fred quotes an earlier post and shares an APK analysis experience with reverse-skill, describing guidance through static scanning, unpacking and decompilation. He says algorithm and protocol analysis still require human work. The link covers the repository.
agent-security checks incoming content before coding agents act on it and scans repository changes before they are pushed. Its author describes treating web pages, emails, tool output, and Skill files as data rather than instructions.
Ilia introduced ia-test-audit in whetstone 5.0. Adapted from OpenClaw's test-audit Skill, it checks whether tests would catch plausible incorrect implementations.
The test-audit Skill reviews tests for low-value or implementation-coupled coverage. Peter Steinberger linked it while saying OpenClaw removed about 400,000 lines of tests with little change in code coverage.