chore: re-sync agent skills to upstream mattpocock/skills

Local snapshots dated 2026-09-16; upstream has moved on since. Refreshes
7 SKILL.md files (code-review, diagnosing-bugs, implement, tdd, grilling,
handoff, teach): tracker-doc references generalized, CONTEXT.md renamed
GLOSSARY.md, implement gains ticket-fetch step + Skill-tool invocation,
grilling question wording rule, handoff names the OS temp dir, teach
workspace-path resolution + quiz answer-position rules, tdd seam notes.
find-skills (vercel-labs) and prototype already current. Skill updates
take effect next session (discovery runs at startup).

agent/skills/diagnosing-bugs/SKILL.md

@@ -7,7 +7,7 @@ description: Diagnosis loop for hard bugs and performance regressions. Use when
 
 A discipline for hard bugs. Skip phases only when explicitly justified.
 
-When exploring the codebase, read `CONTEXT.md` (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.
+When exploring the codebase, read `GLOSSARY.md` (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.
 
 ## Redact
 
@@ -122,7 +122,7 @@ A correct seam is one where the test exercises the **real bug pattern** as it oc
 If a correct seam exists:
 
 1. Turn the minimised repro into a failing test at that seam.
-2. Watch it fail.
+2. Watch it fail. If you forced the red by mutating code or a fixture, `diff` against a pristine copy to prove the mutation landed before you trust it.
 3. Apply the fix.
 4. Watch it pass.
 5. Re-run the Phase 1 feedback loop against the original (un-minimised) scenario.