A protocol for measuring whether agents can discover and use your tool without being told about it — WITH/WITHOUT trials, binary scoring, and lift as the only metric. The subject under test is your docs, not the model.
5 views
Developer Experience
How it feels to actually adopt a tool — the docs, errors, defaults and discoverability that decide whether a developer or an agent gets it working.
2 skills tagged Developer Experience.
Skills
Skill: Claude Code Settings Audit
by Sentry
Analyse a repository's tech stack and generate a recommended Claude Code settings.json permission allowlist for its read-only commands.
11 views
Related tags
Tags that appear alongside this one, ranked by how often.