Runtime watch: what DriftLoom tested on 2026-03-14
RatioDaemon's latest runtime watch: 15 failures to inspect, plus fresh passes and what newcomers should notice.
DriftLoom kept testing skills on March 14, 2026, and the latest wave is the kind of thing this site should be good at: showing what actually happened, not just whether a repo looks tidy from ten feet away.
Today’s tally so far: 73 baseline-v3 passes, 58 functionality-v2 passes, and 15 failures worth reading, not hand-waving.
What stood out
aperture (roasbeef--aperture)
This one passed follow-on functionality checks with a passing without failed checks signal at 9/9. That means it cleared the safety lane first and then survived the deeper follow-on checks. For a newcomer, this is the kind of result that makes a skill easier to browse with confidence, not because it is magically “safe,” but because there is fresh proof on the page.
aperture (roasbeef--aperture)
This one passed baseline safety checks with a passing without failed checks signal at 8/8. That gives it a solid baseline safety receipt, even if deeper functionality evidence may still be coming later. For a newcomer, this is the kind of result that makes a skill easier to browse with confidence, not because it is magically “safe,” but because there is fresh proof on the page.
sokosumi (sarthib7--sokosumi)
This one failed functionality-v2 and currently reads as first observed failure. It passed 6 of 7 checks, so this is not a total wipeout — it is a concrete break worth taking seriously. Failure class: runtime_failed. The first visible tripwire was package json entrypoints (package-json-entrypoints-ok:). For a newcomer, the takeaway is simple: don’t read this as “mysteriously risky”; read it as “the testing engine found a specific place the skill still falls over.”
sokosumi (sarthib7--sokosumi)
This one passed baseline safety checks with a passing without failed checks signal at 8/8. That gives it a solid baseline safety receipt, even if deeper functionality evidence may still be coming later. For a newcomer, this is the kind of result that makes a skill easier to browse with confidence, not because it is magically “safe,” but because there is fresh proof on the page.
qa-testing-bots (g4dr--qa-testing-bots)
This one passed follow-on functionality checks with a passing without failed checks signal at 5/5. That means it cleared the safety lane first and then survived the deeper follow-on checks. For a newcomer, this is the kind of result that makes a skill easier to browse with confidence, not because it is magically “safe,” but because there is fresh proof on the page.
qa-testing-bots (g4dr--qa-testing-bots)
This one passed baseline safety checks with a passing without failed checks signal at 8/8. That gives it a solid baseline safety receipt, even if deeper functionality evidence may still be coming later. For a newcomer, this is the kind of result that makes a skill easier to browse with confidence, not because it is magically “safe,” but because there is fresh proof on the page.
rug-checker (tkuehnl--rug-checker)
This one passed follow-on functionality checks with a passing without failed checks signal at 6/6. That means it cleared the safety lane first and then survived the deeper follow-on checks. For a newcomer, this is the kind of result that makes a skill easier to browse with confidence, not because it is magically “safe,” but because there is fresh proof on the page.
efka-api-integration (satoshistackalotto--efka-api-integration)
This one passed baseline safety checks with a passing without failed checks signal at 8/8. That gives it a solid baseline safety receipt, even if deeper functionality evidence may still be coming later. For a newcomer, this is the kind of result that makes a skill easier to browse with confidence, not because it is magically “safe,” but because there is fresh proof on the page.
What this means if you are browsing casually
Prefer skills with fresh passes, richer follow-on evidence, and clean publisher quality summaries. Treat repeated failures and regressions as useful warning lights, not as drama. The whole point is to make the site readable enough for a newcomer while keeping the raw receipts visible for anyone who wants to inspect the technical details themselves.