implement: call the Skill tool for tdd and code-review

implement still said "use /tdd" and "use /code-review", the bare
/skill-style prose that #878 replaced everywhere else with an explicit
Skill tool call (the convention in .agents/invocation.md). Both targets
are model-invoked, so the call is allowed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

.changeset/implement-skill-tool-wording.md

@@ -0,0 +1,5 @@
+---
+"mattpocock-skills": patch
+---
+
+`implement` now tells the agent to call the Skill tool with `tdd` and `code-review`, instead of the bare `/tdd` and `/code-review` prose that the other skills dropped in #878. A `/skill` mention in prose does not reliably load the skill.

docs/engineering/implement.md

@@ -77,7 +77,7 @@ The agent resolves `#2` against whatever numbered list it can see. In a fresh se
 ## It's working if
 
 - The session opens by reading the ticket or spec and restating what it will build, rather than asking you what to build.
-- You can see an actual `/tdd` invocation in the trace, not just tests appearing in the diff.
+- You can see an actual `tdd` Skill tool call in the trace, not just tests appearing in the diff.
 - Typechecks and single test files run repeatedly during the run, and the full suite runs once near the end.
 - The run reaches a commit on your current branch without you prompting it to carry on.
 - The diff is one ticket's worth of change: a vertical slice through every layer, not several tickets swept together.

skills/engineering/implement/SKILL.md

@@ -6,10 +6,10 @@ disable-model-invocation: true
 
 Implement the work described by the user in the spec or tickets.
 
-Use /tdd where possible, at pre-agreed seams.
+Where possible, call the Skill tool with "tdd" to build at pre-agreed seams.
 
 Run typechecking regularly, single test files regularly, and the full test suite once at the end.
 
-Once done, use /code-review to review the work.
+Once done, call the Skill tool with "code-review" to review the work.
 
 Commit your work to the current branch.