Capture native self-assessment improvement

docs/self-scoping/README.md

@@ -17,6 +17,11 @@ instead of relying on memory or screenshots.
   generation still collapses repo-scoping's native surfaces under the forbidden
   provider-routing capability, but its source set no longer includes
   `var/checkouts/` contamination.
+- `assessments/repo-scoping-post-wp0016-native-2026-05-15.json` captures the
+  first deterministic challenger after native candidate generation recovery. It
+  matches every expected capability in the golden profile and has no known
+  provider-routing regression, while still leaving generated candidates pending
+  review with quality-gate signals.
 - `workflow.md` explains how to run challenger assessments, interpret outcomes,
   and decide whether to update the golden profile or fix the engine.
 - `outcomes/` stores append-only reviewer decisions created from side-by-side

docs/self-scoping/assessments/repo-scoping-post-wp0016-native-2026-05-15.md

@@ -0,0 +1,33 @@
+# Self-Scoping Comparison: repo-scoping-challenger-run-1
+
+- Status: `candidate_improvement`
+- Golden profile: `repo-scoping-golden-profile-v1`
+- Target repo: `repo-scoping`
+- Summary: Assessment covers the golden profile without known regression patterns.
+
+## Missing Expected Capabilities
+- None
+
+## Forbidden Native Capabilities Present
+- None
+
+## Known Regression Patterns
+- None
+
+## Misplaced Features
+- None
+
+## Matched Expected Capabilities
+- Explore Dependency And Impact Graphs
+- Generate And Maintain SCOPE.md
+- Generate Reviewable Candidate Characteristics
+- Index Source Content With Provenance
+- Provide Scope Context To Downstream Agents
+- Register And Track Repositories
+- Review And Approve Candidate Characteristics
+- Scan Repositories Into Observed Facts
+- Search Compare And Export Approved Profiles
+
+## Review Hints
+- Candidate appears better than the known golden checks.
+- Human or agentic review should still confirm source evidence quality.