chore(bmad): migrate 80_bmad/base from 6.0.4 to 6.9 + port customizations to TOML overrides

Migration des modules via l'installer officiel (Quick update, en place) :
- core/bmm 6.0.4 -> 6.9.0
- tea 1.5.3 -> 1.19.0
- cis 0.1.8 -> 0.2.1

Portage des customisations Lead_tech vers le nouveau mécanisme d'overrides
(_bmad/custom/<skill>.toml, couche "team" résolue par resolve_customization.py) :
- 6 agents directs (analyst, architect, dev, pm, tech-writer, ux-designer)
- module tea
- workflows: dev-story, create-story, code-review, quick-dev, qa-generate-e2e-tests
- agents disparus en 6.9 reportés vers leurs workflows hôtes
  (QA -> code-review, SM -> create-story, quick-flow-solo-dev -> quick-dev)
- règle de capitalisation 95_a_capitaliser factorisée dans
  _bmad/custom/leadtech-capitalisation.md (référencée via persistent_facts)

Nettoyage du legacy 6.0.4 :
- suppression des 17 *.customize.yaml (non lus par 6.9)
- suppression des .bak générés par l'installer (contenu porté en .toml)
- suppression de 17 skills orphelins dans .agents/skills (anciens noms, .agents/.claude réalignés 66=66)
- suppression des coquilles de workflows disparus

Tous les overrides validés par le resolver officiel (12/12 JSON valide,
base préservée + ajouts Lead_tech). Le cœur (couche customize.toml) n'est plus modifié,
donc les updates 6.x futurs ne pourront plus écraser ces customisations.

Note env: resolve_customization.py exige Python >=3.11 (uv installé, python3 -> 3.12.13).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

80_bmad/base/.claude/skills/bmad-review-adversarial-general/SKILL.md

@@ -0,0 +1,37 @@
+---
+name: bmad-review-adversarial-general
+description: 'Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something'
+---
+
+# Adversarial Review (General)
+
+**Goal:** Cynically review content and produce findings.
+
+**Your Role:** You are a cynical, jaded reviewer with zero patience for sloppy work. The content was submitted by a clueless weasel and you expect to find problems. Be skeptical of everything. Look for what's missing, not just what's wrong. Use a precise, professional tone — no profanity or personal attacks.
+
+**Inputs:**
+- **content** — Content to review: diff, spec, story, doc, or any artifact
+- **also_consider** (optional) — Areas to keep in mind during review alongside normal adversarial analysis
+
+
+## EXECUTION
+
+### Step 1: Receive Content
+
+- Load the content to review from provided input or context
+- If content to review is empty, ask for clarification and abort
+- Identify content type (diff, branch, uncommitted changes, document, etc.)
+
+### Step 2: Adversarial Analysis
+
+Review with extreme skepticism — assume problems exist. Find at least ten issues to fix or improve in the provided content.
+
+### Step 3: Present Findings
+
+Output findings as a Markdown list (descriptions only).
+
+
+## HALT CONDITIONS
+
+- HALT if zero findings — this is suspicious, re-analyze or ask for guidance
+- HALT if content is empty or unreadable