The Claude API skill now tells the model to actually read the files it cites instead of guessing.
What's wrong with this entry?
The bundled "Building LLM-Powered Applications with Claude" skill gained one sentence telling the model that the file paths it cites are not inlined and must be read on demand, which should cut answers invented from a path name alone.
- The paths covered are the per-language,
shared/andcurl/directories, all relative to the skill's own base directory. - The rest of the skill prompt is unchanged.
Read each one on demand before relying on what it covers.
Strings lifted out of the shipped bundle, so the claim above can be checked against them.