{"version":"2.1.309","anchor":"skill-description-truncation-now-emits-telemetry","canonical_anchor":"skill-description-truncation-now-emits-telemetry","heading":"Claude Code reports when skill descriptions are shortened","tier":"internal","area":"Skills","scope":"org","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.309\/e\/skill-description-truncation-now-emits-telemetry","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.309","markdown":"### Claude Code reports when skill descriptions are shortened\n\nWhen the list of skills is trimmed to fit a size limit, Claude Code now sends Anthropic a usage report about the trimming\n\n**What**\n\nSkills are reusable instructions Claude Code can draw on, and it gives the model a list of them with their descriptions. When that list has to be trimmed to fit a size limit, Claude Code now sends a usage report recording:\n\n- how many skills there are\n\n- the size limit and the full size before trimming\n\n- how the trimming was done\n\n- how many skills kept their full description, and how many were cut down\n\nThe list itself is the same as before.\n\n**Why**\n\nAnthropic is measuring how often skill descriptions get cut down to just a name, and nothing about what the model sees changes.\n\n- Area: Skills\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: org\n- Heads-up: no"}