NVIDIA put DOCA agent skills on GitHub and says agents using them met 100% of checklist items on 65 BlueField prompts, up from 19%. NVIDIA ran and graded that test, so the score carries over only as far as a team's own DOCA tasks resemble its prompts.
Reality
- Evidence38
- Adoption
- Insufficient
- Hype gap+42
- Incentives78
- Confidence55
An XDA Developers writer moved his desktop sticky-note prompt stash into Claude Code skill folders. Claude keeps only each skill's name and description in context and pulls in the body it judges to match.
Reality
- Evidence42
- Adoption15
- Hype gap+18
- Incentives38
- Confidence55
The cap watched the file total, so when owner instructions pushed the rules body from 27,646 to 40,779 bytes in 18 days, the commit shortened its changelog entry to stay legal. The replacement test measures the body alone.
Reality
- Evidence64
- Adoption12
- Hype gap+10
- Incentives30
- Confidence56
Claude Code loads skills in three stages, so an idle skill charges only its description to the context window. Thomas Tartrau says the same folder runs unchanged in Cursor, and his article is the only evidence for that.
Reality
- Evidence45
- Adoption18
- Hype gap+25
- Incentives30
- Confidence55
Three postures exist for an agent instruction file. Only the third holds at commit speed. The team running it watched its own CLAUDE.md reach 548KB before a context-measurement pass cut it to 34KB.
Reality
- Evidence58
- Adoption18
- Hype gap−5
- Incentives55
- Confidence55
OWASP's v1.0 standard says the payload is prose and the permissions belong to the host agent, which is another way of saying the SAST and SCA licences already on the books scan straight past the thing teams are installing this quarter.
Publishers:kenhuangus.substack.com
Reality
- Evidence42
- Adoption20
- Hype gap+28
- Incentives78
- Confidence38
One developer found roughly 70 of his 112 installed skills reduced to bare names in the system prompt, and nothing in the tool had flagged it, because the listing budget drops descriptions without erroring.
Reality
- Evidence52
- Adoption14
- Hype gap−12
- Incentives34
- Confidence46
Six paired evaluations on a Tokyo transit server: one better route, one worse, four identical. The guidance file changed the agent's decision path without breaking anything.
Reality
- Evidence34
- Adoption11
- Hype gap+6
- Incentives52
- Confidence38
A dependency rule for agent config files read only the scalar form of a YAML key. Authors who declared nothing went clean; authors who declared properly got the warning.
Reality
- Evidence52
- Adoption
- Insufficient
- Hype gap+6
- Incentives42
- Confidence45