@dzhechkov/keysarium 1.4.0 → 1.5.0

package/README.md

@@ -28,10 +28,10 @@ After installation, open Claude Code in your project directory and start using s
 
 | Component | Count | Description |
 |-----------|-------|-------------|
-| **Skills** | 8 | `explore`, `frontend-design`, `goap-research`, `presentation-storyteller`, `problem-solver`, `reverse-engineering`, `bto`, `knowledge-extractor` |
+| **Skills** | 9 | `explore`, `frontend-design`, `goap-research`, `presentation-storyteller`, `problem-solver`, `reverse-engineering`, `bto`, `knowledge-extractor`, `ai-factory-mapper` |
 | **Commands** | 24 | `/casarium`, `/new-research`, `/parallel-research`, `/discovery`, `/explore-case`, `/research`, `/cjm-prototype`, `/solve`, `/architecture-phase`, `/presentation`, `/harvest`, `/brain-export`, `/brain-import`, `/bto`, `/bto-build`, `/bto-test`, `/bto-optimize`, `/bto-benchmark`, `/feature-adr`, `/init-platform`, `/learning-stats`, `/dream`, `/workers`, `/verify-chain` |
 | **Rules** | 16 | `research-quality`, `checkpoint-protocol`, `agent-swarm`, `domain-specific`, `anti-patterns`, `file-conventions`, `modular-reuse`, `feedback-loops`, `model-routing`, `trust-tiers`, `bto-quality-gates`, `background-workers`, `dream-cycles`, `reward-learning`, `witness-chain`, `feature-adr-conventions` |
-| **Shards** | 9 | Context shards for each phase: `phase-0-discovery`, `phase-1-explore`, `phase-2-research`, `phase-25-cjm`, `phase-3-solve`, `phase-4-architecture`, `phase-5-presentation`, `bto-evaluation`, `feature-adr` |
+| **Shards** | 10 | Context shards for each phase: `phase-0-discovery`, `phase-1-explore`, `phase-2-research`, `phase-25-cjm`, `phase-3-solve`, `phase-4-architecture`, `phase-5-presentation`, `phase-ai-factory`, `bto-evaluation`, `feature-adr` |
 | **Agent Templates** | 5 | `discovery-worker`, `research-worker`, `cjm-variant-worker`, `presentation-worker`, `parallel-research-orchestrator` |
 | **Library** | 4 | `phase-utils`, `agent-patterns`, `skill-loader`, `domain-templates` |
 | **Documentation** | 12 | Deployment, admin, user guide, infrastructure, architecture, flows (for Keysarium and BTO) |
@@ -95,6 +95,9 @@ claude
 
 # Start a full case study (runs all 7 phases with checkpoints)
 /casarium Analyze how AI can automate customer support in banking
+
+# Same pipeline + Cloud.ru AI Factory mapping on every phase
+/casarium --ai-factory Analyze how AI can automate customer support in banking
 ```
 
 ### Individual Phases
@@ -134,12 +137,52 @@ claude
 
 ```bash
 /casarium Как AI может автоматизировать процесс обработки обращений клиентов в банке, сократив время ответа с 4 часов до 15 минут?
+
+# Same case + AI Factory service mapping
+/casarium --ai-factory Как AI может автоматизировать процесс обработки обращений клиентов в банке, сократив время ответа с 4 часов до 15 минут?
 ```
 
 The toolkit processes cases in any language and adapts domain rules accordingly.
 
 ---
 
+## Cloud.ru AI Factory Mode (`--ai-factory`)
+
+Add the `--ai-factory` flag to `/casarium` to get full Cloud.ru Evolution AI Factory mapping integrated across all phases of the pipeline.
+
+```bash
+/casarium --ai-factory <case text>
+```
+
+### What it adds
+
+| Phase | Addition |
+|-------|----------|
+| **Phase 0** | AI Factory applicability assessment appended to `00_product_discovery.md` |
+| **Phase 1** | AI Factory context paragraph in `01_case_brief.md` |
+| **Phase 2** | Full ai-factory-mapper workflow (catalog sync + decomposition + mapping) → new artifact `02.6_ai_factory_mapping.md` |
+| **Phase 2.5** | Each CJM step annotated with the AI Factory service that handles it |
+| **Phase 3** | Gap analysis + coverage scoring (%) appended to `03_solution_strategy.md` |
+| **Phase 4** | AI Factory services named in C4 diagram + new `diagrams/ai-factory-pipeline.mermaid` |
+| **Phase 5** | Full AI Factory report (`ai_factory_analysis.md`) + "AI Factory Coverage" slide |
+
+### Additional artifacts (--ai-factory only)
+
+```
+researches/<case-slug>/
+├── 02.6_ai_factory_mapping.md          # Step→service mapping with ✅/⚠️/❌
+├── ai_factory_analysis.md              # Full analysis report
+├── ai_factory_analysis.docx            # DOCX report (if Node.js available)
+└── diagrams/
+    └── ai-factory-pipeline.mermaid     # Mermaid flowchart of the AI Factory pipeline
+```
+
+### Zero-degradation guarantee
+
+Without `--ai-factory`, the pipeline is **identical** to v1.4. The flag is purely additive — no existing artifacts are modified or removed, no phases are altered, no checkpoints are changed.
+
+---
+
 ## Domain Support
 
 The toolkit automatically detects the domain from the case description and applies domain-specific rules:
@@ -205,19 +248,23 @@ researches/<case-slug>/
 ├── 01_case_brief.md                 # Phase 1 output
 ├── 02_research_findings.md          # Phase 2 output
 ├── 02.5_trend_brief.md              # Phase 2.5 output
+├── 02.6_ai_factory_mapping.md       # Phase 2 output (--ai-factory only)
 ├── 03_solution_strategy.md          # Phase 3 output
 ├── 04_architecture.md               # Phase 4 output
 ├── 05_presentation_content.md       # Phase 5 output
 ├── 06_speaker_script.md             # Phase 5 output
 ├── 07_qa_preparation.md             # Phase 5 output
 ├── 08_executive_summary.md          # Phase 5 output (mandatory)
+├── ai_factory_analysis.md           # Phase 5 output (--ai-factory only)
+├── ai_factory_analysis.docx         # Phase 5 output (--ai-factory only, if Node.js available)
 ├── prototype/
 │   └── cjm-prototype.jsx           # Phase 2.5 React prototype
 ├── diagrams/
 │   ├── architecture-c4.mermaid
 │   ├── sequence-main-flow.mermaid
 │   ├── process-as-is.mermaid
-│   └── process-to-be.mermaid
+│   ├── process-to-be.mermaid
+│   └── ai-factory-pipeline.mermaid  # Phase 4 output (--ai-factory only)
 └── README.md
 ```
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@dzhechkov/keysarium",
-  "version": "1.4.0",
-  "description": "AI Case Research Toolkit for Claude Code — full 7-phase pipeline with feature-adr, dream cycles, background workers, multi-platform support, and reward learning",
+  "version": "1.5.0",
+  "description": "AI Case Research Toolkit for Claude Code — full 7-phase pipeline with feature-adr, dream cycles, background workers, multi-platform support, reward learning, and Cloud.ru AI Factory mapping (--ai-factory flag)",
   "main": "src/cli.js",
   "bin": {
     "keysarium": "./bin/cli.js"
@@ -25,7 +25,9 @@
     "skills",
     "pipeline",
     "keysarium",
-    "product-research"
+    "product-research",
+    "ai-factory",
+    "cloud-ru"
   ],
   "author": "dzhechko",
   "license": "MIT",

package/templates/.claude/commands/analyst-manual.md

@@ -0,0 +1,38 @@
+# Analyst Manual: Стратегический анализ с контрольными точками
+
+## Использование
+```
+/analyst-manual [тема или задача для анализа]
+```
+
+## Аргумент
+$ARGUMENTS
+
+## Действия
+
+1. **Загрузи скилл:** Прочитай `.claude/skills/analyst-manual-full/SKILL.md`
+2. **Оцени ясность задачи** (Gate: Task Clarity Assessment)
+   - Задача ясна → пропустить Explore, сформировать Task Brief
+   - Задача не ясна → Phase 1: Explore
+
+3. **Phase 1: Explore** (если нужен)
+   - Кларификация задачи, формирование Task Brief
+   - Output: `01_task_brief.md`
+   - ⏸️ **CHECKPOINT 1:** Подтверждение Task Brief + выбор verification mode
+
+4. **Phase 2: Verified Research** (goap-research-ed25519)
+   - Используй `scripts/goap_planner.py` и `scripts/ed25519_verifier.py`
+   - Режим: выбранный на CHECKPOINT 1 (moderate/strict/paranoid)
+   - Output: `02_research_findings.md`
+   - ⏸️ **CHECKPOINT 2:** Подтверждение findings
+
+5. **Phase 3: Solve** (problem-solver-enhanced)
+   - 9-модульный framework (First Principles, TRIZ, Game Theory, OODA)
+   - Output: `03_solution.md`
+   - ⏸️ **CHECKPOINT 3:** Подтверждение решения
+
+6. **Synthesis:** Финальный summary всех фаз
+   - Output: `04_final_summary.md`
+
+## Режим
+**MANUAL** — подтверждение между каждой фазой обязательно.

package/templates/.claude/commands/casarium.md

@@ -6,14 +6,28 @@
 ## Использование
 ```
 /casarium [текст кейса или ссылка]
+/casarium --ai-factory [текст кейса или ссылка]
 ```
 
+Флаг `--ai-factory`: активирует интеграцию с Cloud.ru Evolution AI Factory на всех фазах.
+Без флага: поведение полностью идентично предыдущим версиям (нулевая деградация).
+
 ## КРИТИЧЕСКОЕ ПРАВИЛО: ФАЙЛЫ СОЗДАЮТСЯ В МОМЕНТ ФАЗЫ
 В конце каждой фазы **немедленно создай** файл. Не откладывай.
 
 ## Режим работы
 Аргумент: $ARGUMENTS
 
+### Детекция флага --ai-factory
+```
+AI_FACTORY_MODE = "--ai-factory" присутствует в $ARGUMENTS
+```
+Если `AI_FACTORY_MODE = true`:
+1. Прочитай `.claude/shards/phase-ai-factory.shard.md` — это governance shard для AI Factory режима.
+2. Прочитай `.claude/skills/ai-factory-mapper/SKILL.md` — загрузи скилл.
+3. Закешируй в working memory каталог AI Factory из `.claude/skills/ai-factory-mapper/references/catalog.md`.
+4. Сообщи пользователю: "Режим --ai-factory активирован. AI Factory маппинг будет интегрирован во все фазы."
+
 Если аргумент содержит текст кейса — начинай работу. Если аргумент пустой — спроси текст кейса, тайминг, домен.
 
 ## Инициализация
@@ -21,7 +35,7 @@
 1. Определи название кейса → `CASE_NAME`
 2. Создай рабочую директорию: `researches/CASE_NAME/`
 3. Определи тайминг (часов на кейс, по умолчанию 4)
-4. Кратко объясни 7 фаз + ожидаемые артефакты
+4. Кратко объясни 7 фаз + ожидаемые артефакты (если `AI_FACTORY_MODE`, добавь AI Factory артефакты)
 5. Распредели время:
    - Phase 0: 15% | Phase 1: 5% | Phase 2: 15% | Phase 2.5: 10% ⭐ | Phase 3: 15% | Phase 4: 15% | Phase 5: 20% | Buffer: 5%
 
@@ -45,6 +59,12 @@ ARTIFACTS (researches/CASE_NAME/):
 [ ] diagrams/process-as-is.mermaid        ← Phase 3
 [ ] diagrams/process-to-be.mermaid        ← Phase 3
 [ ] README.md                   ← Phase 6
+
+# Только при --ai-factory:
+[ ] 02.6_ai_factory_mapping.md            ← Phase 2 (--ai-factory)
+[ ] diagrams/ai-factory-pipeline.mermaid  ← Phase 4 (--ai-factory)
+[ ] ai_factory_analysis.md                ← Phase 5 (--ai-factory)
+[ ] ai_factory_analysis.docx              ← Phase 5 (--ai-factory, если Node.js доступен)
 ```
 
 ## Pipeline
@@ -65,6 +85,10 @@ INPUT → DISCOVERY → EXPLORE → RESEARCH → CJM PROTO → SOLVE → ARCHITE
 - Phase 4: Встроенные шаблоны архитектуры
 - Phase 5: `.claude/skills/presentation-storyteller/SKILL.md`
 
+Если `AI_FACTORY_MODE = true`, дополнительно при инициализации (до Phase 0):
+- `.claude/skills/ai-factory-mapper/SKILL.md`
+- `.claude/skills/ai-factory-mapper/references/catalog.md` (закешировать в working memory)
+
 ## Стратегия параллелизации (Agent Swarm)
 
 Для ускорения используй Agent tool для параллельных задач:
@@ -93,14 +117,29 @@ INPUT → DISCOVERY → EXPLORE → RESEARCH → CJM PROTO → SOLVE → ARCHITE
 Последовательно выполняй фазы, в каждой:
 1. Прочитай соответствующий SKILL.md
 2. Выполни фазу, создай артефакт
-3. Покажи Checkpoint
-4. Дождись "ок" или корректировки от пользователя
-5. Перейди к следующей фазе
+3. Если `AI_FACTORY_MODE = true` — выполни AI Factory шаг для данной фазы (см. `.claude/shards/phase-ai-factory.shard.md`)
+4. Покажи Checkpoint
+5. Дождись "ок" или корректировки от пользователя
+6. Перейди к следующей фазе
 
 ## Phase 0-6: Детали
 
 Детальные инструкции для каждой фазы находятся в CLAUDE.md проекта и в SKILL.md соответствующих скиллов. Следуй им строго.
 
+### AI Factory интеграция по фазам (только при --ai-factory)
+
+| Фаза | Что добавляется |
+|------|----------------|
+| Phase 0 | Секция "AI Factory Applicability" в `00_product_discovery.md` |
+| Phase 1 | 1 параграф AI Factory контекст в `01_case_brief.md`, установить `{AI_FACTORY_SCENARIO}` |
+| Phase 2 | Запуск ai-factory-mapper фаз 1–3 → новый артефакт `02.6_ai_factory_mapping.md` |
+| Phase 2.5 | Аннотация каждого шага CJM-вариантов AI Factory сервисом (из `02.6_ai_factory_mapping.md`) |
+| Phase 3 | Запуск ai-factory-mapper фаз 4–5 → секция "AI Factory Coverage" в `03_solution_strategy.md` |
+| Phase 4 | AI Factory сервисы в C4-диаграмме + новый артефакт `diagrams/ai-factory-pipeline.mermaid` |
+| Phase 5 | Запуск ai-factory-mapper фазы 6 → `ai_factory_analysis.md` + слайд "AI Factory Coverage" |
+
+Полные инструкции — в `.claude/shards/phase-ai-factory.shard.md`.
+
 ## Checkpoint формат
 
 После каждой фазы покажи:
@@ -161,3 +200,15 @@ researches/CASE_NAME/
 - Если банк: on-premise, ФЗ-152, ЦБ, GigaChat/YandexGPT
 - Если мало времени: Quick Mode
 - Все артефакты в директории `researches/CASE_NAME/`
+
+## AI Factory Rules (только при --ai-factory)
+
+- `{AI_FACTORY_MODE}` устанавливается один раз при инициализации и не изменяется
+- AI Factory шаги **аддитивны**: они расширяют существующие артефакты, не заменяют их
+- Catalog sync (`web_search`) обязателен в Phase 2 — не пропускать
+- Все шаги workflow должны быть разбиты на 7–12 (правило ai-factory-mapper)
+- Каждый шаг должен иметь явное ✅ / ⚠️ / ❌ без "скорее всего"
+- Coverage % округляется до 5%
+- `02.6_ai_factory_mapping.md` должен быть готов до начала Phase 3
+- AI Factory работа в Phase 2 может быть запущена **параллельно** с основными research-агентами
+- Без `--ai-factory` ни один из этих шагов не выполняется и ни один файл не создаётся

package/templates/.claude/commands/feature-adr.md

@@ -3,6 +3,8 @@
 ## Использование
 ```
 /feature-adr [описание фичи или путь к issue]
+/feature-adr --full-qe [описание фичи]            # Direct Mode: полные протоколы agentic-qe
+/feature-adr --full-qe-extended [описание фичи]    # Direct Extended: полные протоколы + доп. скиллы
 ```
 
 ## Аргумент
@@ -16,6 +18,12 @@ $ARGUMENTS
 3. **Step 0 — Complexity Router:**
    - Прочитай `modules/00-complexity-router.md` и `references/complexity-matrix.md`
    - Классифицируй фичу в S/M/L/XL
+   - **Проверь agentic-qe флаги:**
+     - `--full-qe` → проверь `which aqe` или `node_modules/agentic-qe/`.
+       Если найден → `{AGENTIC_QE_MODE}=direct`. Если нет → WARN, fallback to reference.
+     - `--full-qe-extended` → то же + `{AGENTIC_QE_MODE}=direct-extended`.
+       Активирует доп. скиллы (chaos, security, performance, mutation, TDD, production-swarm).
+     - Без флагов → `{AGENTIC_QE_MODE}=reference` (condensed копии, без установки).
    - Определи `{ACTIVE_STEPS}` и `{TIME_BUDGET}`
    - Покажи Checkpoint 0 и **жди подтверждения tier**
 

package/templates/.claude/rules/trust-tiers.md

@@ -21,6 +21,11 @@
 | reverse-engineering-unicorn | 1 | Structured | SKILL.md + modules/ + references/ + examples/ |
 | bto | 1 | Structured | SKILL.md + modules/ + references/ + examples/ |
 | knowledge-extractor | 2 | Validated | /bto-test Layer 2 score 7.5, optimized 2026-03-03 |
+| analyst-manual-full | 0 | Advisory | SKILL.md only (composite orchestrator, depends on explore + goap-research + problem-solver) |
+| feature-adr | 1 | Structured | SKILL.md + modules/ + references/ + examples/ |
+| edu-site-generator | 1 | Structured | SKILL.md + modules/ + references/ + examples/ |
+| transcript-site-generator | 2 | Validated | /bto-test Layer 2 score 7.82 |
+| ai-factory-mapper | 1 | Structured | SKILL.md + references/ + assets/ + scripts/ (v1.0, апрель 2026) |
 
 ## Tier Enforcement
 

package/templates/.claude/shards/feature-adr.shard.md

@@ -19,6 +19,7 @@ Load: `.claude/skills/feature-adr/SKILL.md`
 All of S, plus:
 - `features/<slug>/01_requirements.md`
 - `features/<slug>/03_adr/001-*.md`
+- `features/<slug>/03.5_ideation_report.md` (QCSD quality swarm)
 - `features/<slug>/05_architecture.md`
 - `features/<slug>/07_code_changes/change_manifest.md`
 - `features/<slug>/diagrams/` (component diagram)
@@ -27,6 +28,7 @@ All of S, plus:
 All of M, plus:
 - `features/<slug>/02_research.md`
 - `features/<slug>/04_domain_model.md`
+- `features/<slug>/09_fleet_qe_assessment.md` (fleet QE)
 - `features/<slug>/diagrams/domain-model.mermaid`
 - `features/<slug>/diagrams/architecture-c4.mermaid`
 - `features/<slug>/diagrams/sequence-*.mermaid`
@@ -41,27 +43,70 @@ All of L (full depth on every artifact)
 | 0 | Tier classification justified with dimension scores |
 | 1 | All requirements have acceptance criteria (M+) |
 | 2 | Research findings verified, not hallucinated (L/XL) |
-| 3 | Every ADR has ≥2 alternatives (M+) |
+| 3 | Every ADR has ≥2 alternatives + shift-left testability check (M+) |
+| 3.5 | QCSD ideation: 3 core agents + GO/CONDITIONAL/NO-GO verdict (M+) |
 | 4 | Domain model compatible with existing codebase (L/XL) |
 | 5 | Mermaid diagrams valid syntax (M+) |
-| 6 | Task dependencies form valid DAG |
+| 6 | Task dependencies form valid DAG + SPARC-GOAP goal state defined |
 | 7 | Code follows existing codebase conventions |
-| 8 | No blocker findings remain, all MUST requirements pass |
+| 8 | Brutal-honesty review complete, gap loop closed, all MUST requirements pass |
+| 9 | Fleet QE: 4 agents, traceability matrix complete (L/XL) |
+
+## Agentic QE Integration
+
+Skills from [agentic-qe](https://github.com/proffesor-for-testing/agentic-qe) loaded from `references/agentic-qe/`.
+
+### Three Modes
+
+| Mode | Flag | `{AGENTIC_QE_MODE}` | Skills | Requires install |
+|------|------|---------------------|--------|-----------------|
+| Reference | (none) | `reference` | 9 core (condensed) | No |
+| Direct | `--full-qe` | `direct` | 9 core (full protocols) | `npm i -g agentic-qe` |
+| Direct Extended | `--full-qe-extended` | `direct-extended` | 15 (9 core + 6 extended) | `npm i -g agentic-qe` |
+
+### Core Skills (all modes)
+
+| Step | Skill | Protocol |
+|------|-------|----------|
+| 3 | shift-left-testing | Level 4: Risk Analysis in Design — testability questions + BDD scenarios per ADR |
+| 3.5 | qcsd-ideation-swarm | 3 core agents (HTSM + SFDIPOT + Testability) + conditional agents per flags |
+| 6 | code-goal-planner | SPARC-GOAP: Specification → Pseudocode → Architecture → Refinement → Completion |
+| 8 | brutal-honesty-review | Linus mode (code) + Ramsay mode (tests) + gap detection loop |
+| 9 (Agent 1) | qe-requirements-validation | SMART validation + traceability matrix + orphan test detection |
+| 9 (Agent 2) | risk-based-testing | Probability×Impact 5×5 + 4-tier effort allocation |
+| 9 (Agent 3) | enterprise-integration-testing | Contract testing + E2E flow validation + data consistency |
+| 9 (Agent 4) | regression-testing | Change-based test selection + impact analysis + regression pyramid |
+| 9 (shared) | qe-coverage-analysis | Risk-weighted coverage scoring + differential coverage |
+
+### Extended Skills (`--full-qe-extended` only)
+
+| Step | Skill | Condition |
+|------|-------|-----------|
+| 7 | tdd-london-chicago | Always — guides test-first coding |
+| 8 | mutation-testing | If test suite exists |
+| 8, 9 | security-testing | If `HAS_AUTH` or `HAS_EXTERNAL_API` |
+| 8, 9 | performance-testing | If `HAS_PERFORMANCE_SLA` |
+| 9 | chaos-engineering-resilience | If `HAS_INFRASTRUCTURE_CHANGE` |
+| Post-9 | qcsd-production-swarm | Advisory — feedback loops for future runs |
 
 ## Agent Swarm
 
 ### S/M tier
-Sequential execution. No parallel agents needed.
+Sequential execution. Step 3.5 spawns 3 core agents for M tier.
 
 ### L tier
 - Steps 2+3: 2 parallel agents (sonnet + opus)
-- Step 8: 3 parallel agents (sonnet × 3)
+- Step 3.5: 3-9 parallel agents (core + conditional)
+- Step 8: 3 parallel agents (brutal-honesty review panel)
+- Step 9: 4 parallel agents (fleet QE); 4-7 with `--full-qe-extended`
 
 ### XL tier
 - Steps 2+3: 2 parallel agents
-- Steps 4+5: 2 parallel agents (if Step 3 done)
+- Step 3.5: 3-9 parallel agents (core + conditional)
+- Steps 4+5: 2 parallel agents (if Step 3.5 done)
 - Step 7: N parallel agents (per module)
 - Step 8: 3 parallel agents (review panel)
+- Step 9: 4 parallel agents (fleet QE); 4-7 with `--full-qe-extended`
 
 ## Model Routing
 
@@ -70,12 +115,14 @@ Sequential execution. No parallel agents needed.
 | 0 | haiku | Simple classification |
 | 1 | sonnet | Analytical requirements |
 | 2 | sonnet | Research synthesis |
-| 3 | opus | Complex trade-off reasoning |
+| 3 | opus | Complex trade-off reasoning + shift-left |
+| 3.5 | sonnet | QCSD swarm (multiple parallel agents) |
 | 4 | opus | Domain modeling |
 | 5 | opus | System design |
-| 6 | sonnet | Task decomposition |
+| 6 | sonnet | SPARC-GOAP task decomposition |
 | 7 | opus | Code generation |
-| 8 | sonnet | Review and testing |
+| 8 | sonnet | Brutal-honesty review + gap loop |
+| 9 | sonnet | Fleet QE assessment (4 parallel agents) |
 
 ## Promise Tags
 
@@ -83,16 +130,23 @@ Sequential execution. No parallel agents needed.
 |------|---------|
 | 0 | `<promise>FEATURE_ADR_ROUTED</promise>` |
 | 1 | `<promise>FEATURE_ADR_REQUIREMENTS_GATHERED</promise>` |
-| 2-5 | `<promise>FEATURE_ADR_DESIGNED</promise>` |
+| 2-3 | `<promise>FEATURE_ADR_DESIGNED</promise>` |
+| 3.5 | `<promise>FEATURE_ADR_QUALITY_ASSESSED</promise>` |
+| 4-5 | `<promise>FEATURE_ADR_ARCHITECTED</promise>` |
 | 6 | `<promise>FEATURE_ADR_PLANNED</promise>` |
 | 7 | `<promise>FEATURE_ADR_IMPLEMENTED</promise>` |
 | 8 | `<promise>FEATURE_ADR_VERIFIED</promise>` |
+| 9 | `<promise>FEATURE_ADR_FLEET_VERIFIED</promise>` |
 
 ## Anti-Patterns to Check
 
 - Skip Step 0 → BLOCK
 - Code without plan (skip Step 6) → BLOCK
 - No QE (skip Step 8) → BLOCK
+- Skip QCSD ideation (skip Step 3.5 for M+) → BLOCK
+- Ignore NO-GO verdict from Step 3.5 → BLOCK
+- Skip fleet QE for L/XL (skip Step 9) → BLOCK
 - Over-engineer S-tier (run full pipeline for trivial change) → FLAG
 - Under-engineer XL-tier (skip ADR/DDD) → FLAG
 - ADR with only 1 alternative → FLAG
+- Gap loop skipped in Step 8 → FLAG

package/templates/.claude/shards/phase-ai-factory.shard.md

@@ -0,0 +1,109 @@
+# AI Factory Mode — Governance Shard
+
+## Activation
+This shard is active ONLY when `/casarium --ai-factory` flag is present.
+Without `--ai-factory`: this shard is completely ignored.
+
+## Skill
+Load: `.claude/skills/ai-factory-mapper/SKILL.md` at init, before Phase 0.
+Also load: `.claude/skills/ai-factory-mapper/references/catalog.md` (cache in working memory).
+
+## Variable
+`{AI_FACTORY_MODE}` = `true` — set at casarium init when flag detected.
+
+## Per-Phase Integration
+
+### Phase 0 — Discovery
+After standard JTBD + competitor analysis completes:
+- Identify which AI Factory service tiers map to each JTBD segment (Advisory, based on cached catalog.md).
+- Add section `## AI Factory Applicability` to `00_product_discovery.md`:
+  - 2–3 sentences: which platform layer (Foundation Models / ML Inference / Managed RAG / AI Agents / AI Workflows) is most relevant.
+  - No deep analysis yet — this is orientation only.
+
+### Phase 1 — Explore
+After case brief is written:
+- Add 1-paragraph note to `01_case_brief.md`: which AI Factory capabilities are likely load-bearing for the proposed solution.
+- Set `{AI_FACTORY_SCENARIO}` = concise 2–3 sentence description of the case as an AI Factory scenario (used in Phase 3).
+
+### Phase 2 — Research
+After standard research completes:
+**Run ai-factory-mapper Phases 1–3** (catalog sync + decomposition + mapping):
+1. Read `.claude/skills/ai-factory-mapper/references/catalog.md`.
+2. Run `web_search "Cloud.ru Evolution AI Factory новые сервисы {CURRENT_YEAR}"` to check for updates.
+3. Decompose `{AI_FACTORY_SCENARIO}` into 7–12 workflow steps using `decomposition-checklist.md`.
+4. Map each step → AI Factory service → ✅ / ⚠️ / ❌.
+5. Create artifact: `researches/{CASE_NAME}/02.6_ai_factory_mapping.md`.
+
+### Phase 2.5 — CJM Prototype
+In each CJM variant (A / B / C / D):
+- Annotate each CJM step with the AI Factory service that handles it (1 line per step).
+- Use the mapping from `02.6_ai_factory_mapping.md` — no re-analysis needed.
+
+### Phase 3 — Solve
+After solution strategy is drafted:
+**Run ai-factory-mapper Phases 4–5** (gap identification + coverage scoring):
+1. Enumerate all ❌ and ⚠️ steps from `02.6_ai_factory_mapping.md`.
+2. For each gap: what is missing, why, and the 5 closure options (a–e from skill).
+3. Apply `coverage-formula.md` → round to nearest 5%.
+4. Add section `## AI Factory Coverage` to `03_solution_strategy.md`:
+   - Coverage score (e.g. "~75%")
+   - Top 2–3 priority gaps with closure recommendations.
+
+### Phase 4 — Architecture
+In architecture diagrams:
+- C4 Container diagram: show AI Factory services as named external systems or containers (use their official names: "Cloud.ru Foundation Models", "Cloud.ru Managed RAG", etc.).
+- Add `diagrams/ai-factory-pipeline.mermaid` — flowchart of the solution pipeline mapped to AI Factory services (reuse Mermaid structure from ai-factory-mapper Phase 6 output).
+
+### Phase 5 — Presentation
+**Run ai-factory-mapper Phase 6** (synthesis + full output):
+1. Build structured JSON from the analysis accumulated across Phases 2–4.
+2. Generate `ai_factory_analysis.md` (Markdown report per `assets/report-template.md`).
+3. Attempt DOCX generation via `node .claude/skills/ai-factory-mapper/scripts/build_docx_report.js`.
+4. Add "AI Factory Coverage" slide to presentation (`05_presentation_content.md`):
+   - Coverage % badge, top services used, top gaps.
+5. Add "Platform Architecture" talking point to `06_speaker_script.md`.
+
+## Artifact Inventory (--ai-factory additions)
+
+| Artifact | Phase | Always? |
+|----------|-------|---------|
+| `02.6_ai_factory_mapping.md` | Phase 2 | ✅ |
+| `diagrams/ai-factory-pipeline.mermaid` | Phase 4 | ✅ |
+| `ai_factory_analysis.md` | Phase 5 | ✅ |
+| `ai_factory_analysis.docx` | Phase 5 | If Node.js + docx available |
+
+## Promise Tags
+
+| Milestone | Promise |
+|-----------|---------|
+| Phase 2 mapping done | `<promise>AI_FACTORY_MAPPED</promise>` |
+| Phase 3 gap analysis done | `<promise>AI_FACTORY_GAPS_IDENTIFIED</promise>` |
+| Phase 5 report done | `<promise>AI_FACTORY_REPORT_READY</promise>` |
+
+## Quality Gates
+
+- [ ] Catalog sync performed (web_search + catalog.md read)
+- [ ] Scenario decomposed into 7–12 steps (not more, not less)
+- [ ] Every step has ✅ / ⚠️ / ❌ (no "probably")
+- [ ] Coverage % rounded to 5%
+- [ ] `02.6_ai_factory_mapping.md` exists before Phase 3 starts
+- [ ] CJM variants annotated with AI Factory services (Phase 2.5)
+- [ ] `ai-factory-pipeline.mermaid` valid Mermaid syntax
+
+## Model Routing
+
+| Task | Model |
+|------|-------|
+| Catalog sync + decomposition | sonnet |
+| Mapping + gap analysis | sonnet |
+| Coverage scoring | haiku |
+| Report synthesis | sonnet |
+| DOCX generation | haiku (Node.js subprocess) |
+
+## Non-Degradation Contract
+
+This shard MUST NOT be loaded when `--ai-factory` is absent.
+All `--ai-factory` additions are purely additive:
+- Existing phase artifacts are extended (new sections appended), never replaced.
+- Existing checkpoints are unchanged; AI Factory checkpoint is appended at the end of Phase 2 and Phase 5 checkpoints.
+- Phase timing remains the same; AI Factory work is parallelised where possible (e.g. alongside Phase 2 research agents).

package/templates/.claude/skills/ai-factory-mapper/README.md

@@ -0,0 +1,90 @@
+# ai-factory-mapper
+
+Скилл для Claude Code / Claude Desktop, который декомпозирует любую бизнес-задачу на оптимальный пайплайн из сервисов **Cloud.ru Evolution AI Factory** (Foundation Models, ML Inference, Managed RAG, ML Finetuning, Notebooks, AI Agents, AI Workflows + 50+ MCP-серверов и 21 готовый агент).
+
+## Что делает
+
+На входе — бизнес-сценарий (агент поддержки, обработка документов, маркетинг, discovery и т.д.).
+На выходе:
+1. Декомпозиция workflow на 7–12 шагов
+2. Маппинг каждого шага на сервисы AI Factory
+3. Категоризация покрытия: ✅ Полное / ⚠️ Частичное / ❌ Нет
+4. Список gap'ов с вариантами закрытия
+5. Воспроизводимая оценка покрытия в %
+6. Mermaid-диаграмма пайплайна
+7. Готовый Markdown + DOCX-отчёт
+8. Если сценариев несколько — сводная таблица ранжирования
+
+## Философия: оркестрация, а не копирование
+
+Скилл **не дублирует** функционал других скиллов — он вызывает их через `view()`:
+- `explore` — если задача сформулирована нечётко
+- `problem-solver-enhanced` — для first-principles декомпозиции
+- `goap-research-ed25519` — для верификации актуальности каталога
+- `docx` — для генерации финального отчёта
+- `analyst-manual-full` — для комплексных кейсов с checkpoints
+
+Получает обновления этих скиллов автоматически.
+
+## Структура
+
+```
+ai-factory-mapper/
+├── SKILL.md                       # workflow и оркестрация (470 строк)
+├── references/
+│   ├── catalog.md                 # актуальный каталог AI Factory
+│   ├── decomposition-checklist.md # 10-пунктов чек-лист
+│   ├── coverage-formula.md        # воспроизводимая формула %
+│   └── pattern-library.md         # 10 типовых паттернов
+├── assets/
+│   └── report-template.md         # шаблон отчёта
+├── scripts/
+│   └── build_docx_report.js       # генератор DOCX из JSON
+└── evals/
+    ├── evals.json                 # тест-кейсы
+    ├── smoke_test_input.json      # минимальный smoke-тест
+    └── real_case_input.json       # полный тест на 5 сценариях
+```
+
+## Триггеры
+
+Скилл активируется на фразы вроде:
+- «Разложи задачу X на сервисы AI Factory»
+- «Какие сервисы Cloud.ru нужны для агента поддержки?»
+- «Можно ли реализовать X на Evolution AI Factory?»
+- «Собери пайплайн на AI Factory»
+- «Какое покрытие у сценария X сервисами Cloud.ru?»
+- «Сравни сценарии по покрытию AI Factory»
+
+## Quick test
+
+```bash
+cd ai-factory-mapper
+node scripts/build_docx_report.js evals/smoke_test_input.json /tmp/smoke.docx
+# → ✅ DOCX создан: /tmp/smoke.docx
+```
+
+Для полной проверки:
+```bash
+node scripts/build_docx_report.js evals/real_case_input.json /tmp/real.docx
+python3 <path-to-docx-skill>/scripts/office/validate.py /tmp/real.docx
+```
+
+## Maintenance
+
+Раз в 1–2 месяца обновляй `references/catalog.md`:
+1. Проверь `cloud.ru/products/evolution-ai-factory` на новые сервисы
+2. Пройдись по Evolution Agents Marketplace
+3. Обнови дату в шапке catalog.md
+
+Если появились фундаментально новые категории — добавь паттерны в `pattern-library.md`.
+
+## Dependencies
+
+- Node.js + `docx` package (`npm install -g docx`)
+- Python 3 для валидации DOCX
+- Зависит от скиллов: `explore`, `problem-solver-enhanced`, `goap-research-ed25519`, `docx`, `analyst-manual-full`
+
+## Версия
+
+v1.0 — апрель 2026