fix(reset): target the headings the shipped skill files actually have (#519)

* fix(reset): target the headings the shipped skill files actually have

Two of /reset profile's Step 3 targets had drifted from the files they
rewrite.

The 05-cv-templates.md step anchored on a section beginning
"**Profile statement templates", a line the guide has never contained
(its heading is "**Create 2-3 profile statement templates for your main
role types:**"), so the wipe found nothing: the user's role-tailored
profile statements, and any *[Used for: ...]* statements /setup Path A
extracted from archived applications, survived a reset that reported
success.

The 02-behavioral-profile.md skeleton used headings the shipped file
does not have ("Strongest Behavioral Traits", "How I Work Best", a
truncated "Growth Areas") and dropped "## Core Behavioral Drives" - the
assessment table /setup collects and /interview reads - so one reset
left the file's headings permanently different from every other fork's.

Anchor on the real heading and re-emit it in the replacement; carry the
shipped headings in order in the skeleton. 01-candidate-profile.md and
07-interview-prep.md were already correct. Two new tests derive both
checks from the shipped files, so a renamed heading fails until /reset
follows it; both fail on master.

* test(reset): place the heading guards above the __main__ guard so a direct run sees them

python tests/test_reset_command.py ran only the five old tests; unittest
discover imports the module and saw all seven, which is why CI was green.
Also drop the CHANGELOG's claim that /setup and /interview name the Core
Behavioral Drives table - neither does.

CHANGELOG.md

@@ -15,6 +15,23 @@ per-file diff commands.
 
 ### Fixed
 
+- **`/reset profile` now targets the headings the shipped skill files actually have**
+  (`.claude/commands/reset.md` Step 3, `tests/test_reset_command.py`) - two of its Step 3
+  targets had drifted. The `05-cv-templates.md` step anchored on a section beginning
+  `**Profile statement templates`, a line the guide has never contained (its heading is
+  `**Create 2-3 profile statement templates for your main role types:**`), so the wipe found
+  nothing: the user's role-tailored profile statements, and any `*[Used for: ...]*`
+  statements `/setup` Path A extracted from archived applications, survived a reset that
+  reported success. The `02-behavioral-profile.md` skeleton used headings the shipped file
+  does not have (`Strongest Behavioral Traits`, `How I Work Best`, a truncated `Growth Areas`)
+  and dropped `## Core Behavioral Drives` - the assessment table the shipped file carries - so
+  one reset left the file's headings permanently different
+  from every other fork's, with nothing to recreate the table. The anchor now names the real
+  heading and the replacement re-emits it; the skeleton carries the shipped headings in order.
+  `01-candidate-profile.md` and `07-interview-prep.md` were already correct. Two new tests
+  derive both checks from the shipped files, so a renamed heading fails until `/reset`
+  follows it; both fail on master.
+
 - **The `/apply` host-check test derives its installed-portal hosts from the skills tree
   instead of a hand-copied set** (#497, `tests/test_apply_host_check.py`) - `SHIPPED_PORTAL_HOSTS`
   was six names typed into the test and nothing tied it to anything: a portal added by