fix: resolve __SPECKIT_COMMAND_*__ refs in preset skill rendering (#2717) (#2718)

* fix: resolve __SPECKIT_COMMAND_*__ refs in preset skill rendering (#2717)

The preset skill layer mirrors command templates into SKILL.md files but
only ran resolve_skill_placeholders(), leaving command cross-references as
raw __SPECKIT_COMMAND_<NAME>__ placeholders instead of rendering them as
/speckit-<cmd> the way CommandRegistrar.register_commands() does. As a
result, presets that override core commands under the agent skill layer
(e.g. Claude --ai-skills) leaked the raw tokens into SKILL.md.

Add a shared PresetManager._resolve_skill_command_refs() helper that maps
the agent's invoke separator to IntegrationBase.resolve_command_refs(), and
call it right after resolve_skill_placeholders() in every preset
skill-rendering path: _register_skills() (install), the _reconcile_skills()
override-restoration block, and both _unregister_skills() restore paths.
This mirrors register_commands() and addresses the path divergence flagged
in #1976.

Add regression tests covering the install and restore paths.

AI assistance: authored with Claude Code (Anthropic) — analysis, patch, and
tests. Verified via the existing pytest suite plus a manual CLI install and
remove cycle on a Claude --ai-skills project.

* test: cover reconcile-override and extension restore command-ref paths (#2718 review)

Copilot review flagged that the install and core-template restore paths
gained regression tests, but the reconcile project-override branch and the
extension-backed restore branch were uncovered. Add focused tests for both:

- test_reconcile_override_skill_resolves_command_refs: a project override
  wins after preset removal; _reconcile_skills must render command refs.
- test_extension_restore_resolves_command_refs: a skill restored from an
  extension command body must also render command refs.

Both fail on main and pass with the fix in 8dd93c0.