docs(curator): align 'agent-created' definition with actual provenance semantics

[Twanislas]

Summary

The curator docs stated that any skill not bundled/hub-installed was "agent-created" — including foreground-created skills and hand-written ones. Since PR #19621, the curator requires an explicit created_by: "agent" marker in .usage.json, which only the background self-improvement review fork sets.

Closes #29017.

Changes

1. Rewrite "What agent-created means" section

Before (stale): claimed all non-bundled/non-hub skills were curated — including foreground skill_manage(create) calls and hand-written skills.

After: documents the actual 3-step eligibility check:

1. Not bundled
2. Not hub-installed
3. created_by: "agent" or agent_created: true in .usage.json

Explains that only the background review fork sets this marker, and that foreground-created skills are intentionally excluded (user-directed by design). Warns that hand-written skills are NOT curated.

2. Add note on (not resolved) display in reports

When no agent-created candidates exist, the LLM pass is skipped and the report shows Model: (not resolved) via (not resolved) with Duration: 0s. This is expected behavior, not a config error. Added a :::note callout in the Per-run reports section.

3. Link to provenance internals

References tools/skill_provenance.py (write-origin ContextVar) and mark_agent_created() so users who want to understand the mechanism can trace the code.

Files changed

• website/docs/user-guide/features/curator.md: +45 −21 lines

Verification

No code changes — docs only. The provenance semantics described match the current behavior in:

• tools/skill_provenance.py — BACKGROUND_REVIEW ContextVar, is_background_review()
• tools/skill_manager_tool.py — mark_agent_created() gate at line 782
• tools/skill_usage.py — _is_curator_managed_record(), list_agent_created_skill_names()

[teknium1]

This docs update is already present on current main, so I'm closing this as implemented. This is an automated hermes-sweeper review.

Evidence:

• website/docs/user-guide/features/curator.md:137 now documents the explicit .usage.json eligibility check, including created_by: "agent" / agent_created: true.
• website/docs/user-guide/features/curator.md:151 explains that foreground-created skills are user-directed and not curator-managed; website/docs/user-guide/features/curator.md:155 covers hand-written skills.
• website/docs/user-guide/features/curator.md:241 documents the expected (not resolved) report display when there are no candidates.
• The implementation matches the docs: tools/skill_usage.py:449 checks the provenance marker, and tools/skill_manager_tool.py:967 only marks creates from the background review fork.
• Shipped on main in 549a69a925a799001cab63a4244b8e486c8c2ab4, which is contained in v2026.6.5.