docs(curator): rewrite 'agent-created' definition for post-#19621 beh…

[Aman113114-IITD]

…avior

PR #19621 restricted the 'created_by=agent' marker to the background self-improvement review fork. Foreground 'skill_manage(action="create")' calls no longer mark the skill as agent-created, so the curator's candidate set now follows a 3-condition rule, not 2:

1. not in .bundled_manifest
2. not in .hub/lock.json
3. .usage.json has 'created_by': 'agent' (or legacy 'agent_created': true)

Update the section to reflect the new behavior, add a quick-reference table contrasting creation paths, and document the '(not resolved)' run-summary text users see when the candidate set is empty.

Refs #29017

What does this PR do?

Related Issue

Fixes #

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✨ New feature (non-breaking change that adds functionality)
• 🔒 Security fix
• 📝 Documentation update
• ✅ Tests (adding or improving test coverage)
• ♻️ Refactor (no behavior change)
• 🎯 New skill (bundled or hub)

Changes Made

How to Test

Checklist

Code

• I've read the Contributing Guide
• My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
• I searched for existing PRs to make sure this isn't a duplicate
• My PR contains only changes related to this fix/feature (no unrelated commits)
• I've run pytest tests/ -q and all tests pass
• I've added tests for my changes (required for bug fixes, strongly encouraged for features)
• I've tested on my platform:

Documentation & Housekeeping

• I've updated relevant documentation (README, docs/, docstrings) — or N/A
• I've updated cli-config.yaml.example if I added/changed config keys — or N/A
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A
• I've considered cross-platform impact (Windows, macOS) per the compatibility guide — or N/A
• I've updated tool descriptions/schemas if I changed tool behavior — or N/A

For New Skills

• This skill is broadly useful to most users (if bundled) — see Contributing Guide
• SKILL.md follows the standard format (frontmatter, trigger conditions, steps, pitfalls)
• No external dependencies that aren't already available (prefer stdlib, curl, existing Hermes tools)
• I've tested the skill end-to-end: hermes --toolsets skills -q "Use the X skill to do Y"

Screenshots / Logs

[alt-glitch]

Duplicate of #29018 — both rewrite the curator 'agent-created' definition for #29017. Same file (curator.md), same content.

[teknium1]

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

Evidence:

• The current docs now state the three eligibility conditions for curator-managed skills: not in .bundled_manifest, not in .hub/lock.json, and .usage.json has created_by: "agent" or legacy agent_created: true (website/docs/user-guide/features/curator.md:143).
• The docs explain that only the background self-improvement review fork sets this marker, while foreground skill_manage(action="create") skills and hand-written skills are intentionally not curator-managed (website/docs/user-guide/features/curator.md:151, website/docs/user-guide/features/curator.md:157, website/docs/user-guide/features/curator.md:161).
• The (not resolved) no-candidates report text is documented in the same page (website/docs/user-guide/features/curator.md:247).
• The implementation matches the docs: tools/skill_usage.py:449 checks the provenance marker, and tools/skill_manager_tool.py:1083 only marks skills when is_background_review() is true.
• The duplicate discussion pointed to docs(curator): align 'agent-created' definition with actual provenance semantics #29018, and main contains the docs implementation in 549a69a925a799001cab63a4244b8e486c8c2ab4, which is contained in v2026.6.5.