@dzhechkov/keysarium 1.5.30 → 1.5.32

package/templates/.claude/rules/agent-swarm.md

@@ -20,10 +20,8 @@ When spawning agents, use descriptive names:
 - "Phase 5 Speaker Script"
 
 ## BTO Agent Patterns
-- /bto-test: 3 parallel judge agents (Domain Expert || Critic || Completeness Auditor)
-- /bto-optimize: N parallel variant workers (mutation + evaluation)
-- /bto-optimize Round 1: 5 parallel haiku agents (variant evaluation)
-- /bto-optimize Round 3: 3×3 parallel sonnet agents (Layer 2 full panel)
+(Skill-evaluation swarms — BTO test/optimize — live in the separate `@dzhechkov/skills-bto`
+package and are not available in a Keysarium-only install.)
 
 ## Cost Optimization
 - Use model="haiku" for simple file operations, formatting, and BTO Layer 0-1 evaluation

package/templates/.claude/rules/background-workers.md

@@ -5,7 +5,7 @@
 | Trigger | Worker Type | Condition |
 |---------|------------|-----------|
 | Case completion | `consolidate` | After 3rd completed `/casarium` case in project |
-| Post-BTO test | `health-check` | After any `/bto-test` run (advisory, not enforced) |
+| Post-BTO test | `health-check` | After a BTO evaluation run, if `@dzhechkov/skills-bto` is installed (advisory, not enforced) |
 | Manual | Any | User runs `/workers start <type>` |
 
 Auto-launch triggers are ADVISORY. The system may suggest launching a worker but

package/templates/.claude/rules/dream-cycles.md

@@ -6,6 +6,7 @@ When starting a new pipeline run (`/casarium` or `/feature-adr`), the orchestrat
 
 1. Read `.keysarium/insights/trigger-state.json`
 2. Evaluate triggers using the protocol in `lib/dream-engine.md`
+   (under `init --minimal`, `lib/` is NOT installed — dream cycles are non-blocking, so skip)
 3. If any trigger is met, suggest to the user:
    ```
    Dream cycle trigger met ({reason}). Consider running /dream run for fresh insights.

package/templates/.claude/rules/feature-adr-conventions.md

@@ -8,7 +8,7 @@
 | Researching an AI case for hackathon | `/casarium` |
 | Solving a complex problem (no code) | `/solve` |
 | Designing architecture only (no code) | `/architecture-phase` |
-| Building a new skill/command | `/bto-build` |
+| Building a new skill/command | BTO build — separate package: `npx @dzhechkov/skills-bto init` |
 
 ## Output Directory
 

package/templates/.claude/rules/modular-reuse.md

@@ -24,7 +24,11 @@ They can be composed for different workflows.
 Shared logic lives in lib/ directory:
 - lib/phase-utils.md: Common phase utilities
 - lib/agent-patterns.md: Agent spawning patterns
-- lib/checkpoint-template.md: Checkpoint formatting
+- lib/skill-loader.md: Skill loading conventions
+- lib/domain-templates.md: Domain-specific templates
+
+Under `init --minimal`, `lib/` is NOT installed; treat these modules as absent and skip the
+optional behaviour they describe rather than failing.
 
 ## Extending the System
 To add a new phase:

package/templates/.claude/rules/reward-learning.md

@@ -9,6 +9,9 @@ Govern how the Keysarium pipeline integrates with the Reward-Calibrated Learning
 Read `lib/memory-protocol.md` for the full protocol specification.
 Read `lib/reward-tracker.md` for analytics and pattern detection.
 
+Under `init --minimal`, `lib/` is NOT installed; memory operations are non-blocking, so skip them
+silently when these files are absent.
+
 ## When to Call memory_query()
 
 **Trigger:** At the START of every pipeline phase (Phase 0 through Phase 5).

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

@@ -1,12 +1,17 @@
 # Trust Tier System
 
+> **BTO evaluation is a SEPARATE package.** Keysarium installs no `/bto*` slash commands — the
+> BTO evaluator ships as `@dzhechkov/skills-bto` (`npx @dzhechkov/skills-bto init`). Where this
+> file refers to a "BTO evaluation", it means running that package. Tier promotion is therefore
+> optional: without it, skills stay at the tier their structure earns (Tier 0/1).
+
 ## Tier Definitions
 
 | Tier | Label | Requirements | Promotion Path |
 |------|-------|-------------|----------------|
 | Tier 3 | Verified | Eval test suites with deterministic validation | — (highest) |
-| Tier 2 | Validated | Passed /bto-test with Layer 2 score ≥ 7.0 | Run /bto-test, score ≥ 8.5 on Layer 2 |
-| Tier 1 | Structured | SKILL.md + references/ or modules/ | Run /bto-test, score ≥ 7.0 on Layer 2 |
+| Tier 2 | Validated | Passed a BTO evaluation with Layer 2 score ≥ 7.0 | Run a BTO evaluation, score ≥ 8.5 on Layer 2 |
+| Tier 1 | Structured | SKILL.md + references/ or modules/ | Run a BTO evaluation, score ≥ 7.0 on Layer 2 |
 | Tier 0 | Advisory | Basic SKILL.md only | Add references/, examples/, structured output |
 
 ## Current Skill Tiers
@@ -19,24 +24,23 @@
 | problem-solver-enhanced | 1 | Structured | Comprehensive SKILL.md with TRIZ framework |
 | presentation-storyteller | 1 | Structured | SKILL.md + references/ |
 | 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 |
+| knowledge-extractor | 2 | Validated | BTO evaluation 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 |
+| transcript-site-generator | 2 | Validated | BTO evaluation Layer 2 score 7.82 |
 | ai-factory-mapper | 1 | Structured | SKILL.md + references/ + assets/ + scripts/ (v1.0, апрель 2026) |
 
 ## Tier Enforcement
 
 - Tier 0 skills: Flag with warning when loaded in production pipeline
-- Tier 1 skills: Standard usage, recommend /bto-test for promotion
+- Tier 1 skills: Standard usage, recommend a BTO evaluation for promotion
 - Tier 2 skills: Full confidence, include BTO score in metadata
 - Tier 3 skills: Highest confidence, deterministic validation available
 
 ## Promotion Protocol
 
-1. Run `/bto-test .claude/skills/<name>/`
+1. Install the evaluator (`npx @dzhechkov/skills-bto init`), then run its BTO test on `.claude/skills/<name>/`
 2. If Layer 2 score ≥ 7.0 → promote to Tier 2, record score in SKILL.md
 3. If Layer 2 score ≥ 8.5 + deterministic eval tests exist → promote to Tier 3
 4. Record promotion date and score in SKILL.md frontmatter

package/templates/.claude/skills/edu-site-generator/SKILL.md

@@ -10,7 +10,7 @@ trust_tier: 1
 
 # edu-site-generator — Gamified Educational Site Generator
 
-<!-- Trust Tier: 1 — Structured | Path to Tier 2: Run /bto-test for self-evaluation -->
+<!-- Trust Tier: 1 — Structured | Path to Tier 2: run a BTO evaluation (separate package: npx @dzhechkov/skills-bto) -->
 
 > Generate a complete gamified educational SPA from documentation/content, optimized for GitHub Pages deployment.
 

package/templates/.claude/skills/explore/SKILL.md

@@ -10,7 +10,7 @@ description: >
   provide solutions until task is fully explored.
 trust_tier: 1
 trust_tier_label: "Structured"
-trust_tier_path: "Run /bto-test to promote to Tier 2"
+trust_tier_path: "Run a BTO evaluation from the separate package @dzhechkov/skills-bto to promote to Tier 2"
 ---
 
 # Explore: Adaptive Task Clarification

package/templates/.claude/skills/feature-adr/SKILL.md

@@ -11,7 +11,7 @@ description: >
   "implement feature", "/feature-adr".
 trust_tier: 0
 trust_tier_label: "Advisory"
-trust_tier_path: "Run /bto-test to promote to Tier 1"
+trust_tier_path: "Run a BTO evaluation from the separate package @dzhechkov/skills-bto to promote to Tier 1"
 agentic_qe_version: "7.5.1"
 agentic_qe_source: "https://github.com/proffesor-for-testing/agentic-qe"
 agentic_qe_skills_core: 9
@@ -253,6 +253,7 @@ features/<feature-slug>/
 │   └── change_manifest.md             ← List of modified files
 ├── 08_qe_report.md                    ← Always (brutal-honesty review)
 ├── 09_fleet_qe_assessment.md          ← L/XL only (fleet assessment)
+├── 10_delivery_review.md              ← Opt-in (Step 10 Delivery Gate verdict + findings)
 ├── diagrams/                          ← M+ only
 │   ├── architecture-c4.mermaid
 │   ├── sequence-*.mermaid
@@ -614,4 +615,5 @@ NOT running one loud: a skipped gate shows as `not-run` by construction instead
 checklist to it is the cheapest way to harden orchestrator judgment). Gate sources: challenge-panel → its
 verdict exists; claim-check → its JSON counts (`high-findings` vs `clean`); discrimination → the
 `dz discrimination-check` aggregate; amendments → every `AM-N` row carries its `→ test` and it was checked;
-fleet → the 09 artifact (L/XL only, else `—`).
+fleet → the 09 artifact (L/XL only, else `—`); delivery → the 10_delivery_review.md Verdict
+(`ready|blocked|errored`, `n/a` when the gate was not requested).

package/templates/.claude/skills/feature-adr/modules/10-delivery-gate.md

@@ -39,9 +39,9 @@ surfaces the findings **UNVALIDATED** — never silently dropped, never silently
 ### 3. Machine-checkable hand-off criterion
 
 Write `features/<slug>/10_delivery_review.md`:
-- **## Verdict** — `hand-off: ready | blocked` (ready ⇔ 0 BLOCKER and 0 unwaived HIGH, cross-validation complete)
+- **## Verdict** — `hand-off: ready | blocked | errored` (ready ⇔ 0 BLOCKER and 0 HIGH, ALL planes returned a usable result, cross-validation complete; `errored` = the gate itself failed — advisory, documented). Waivers: not in v1 — a HIGH is a HIGH.
 - **## Findings** — table: severity | plane | title | where | why | crossValidated
-- **## Hand-off criterion** — machine-checkable rows: `0 BLOCKER: PASS/FAIL(n)`, `0 unwaived HIGH: PASS/FAIL(n)`.
+- **## Hand-off criterion** — machine-checkable rows: `0 BLOCKER: PASS/FAIL(n)`, `0 HIGH: PASS/FAIL(n)` (waivers: not in v1).
   Projects with a merge-request flow add THEIR OWN rows here (`CI terminal: …`, `draft→ready: …`) — these are
   **document rows the owner fills**, never API calls made by the pipeline. No merge-request flow ⇒ the rows
   stay `—`.
@@ -52,12 +52,16 @@ Write `features/<slug>/10_delivery_review.md`:
 1. **Findings only.** Step 10 NEVER posts to a VCS host, tracker, or any external service. Publishing a
    review anywhere is a separate, explicit user instruction.
 2. **Advisory.** `hand-off: blocked` is a report, not an abort (a false gate kills trust).
-3. **Cross-family.** The planes run on the other model family than the coder (the Step-8 rule) — a model
-   must not deliver-gate its own code.
+3. **Cross-family (honest v1 scope).** The guarantee holds when the coder was Codex (Claude planes review
+   it — genuinely cross-family). A Claude-coded run gets Claude planes too — SAME family — because codex
+   planes are unsupported in v1 (a plane is a data-returning stage; the codex wrapper returns a stub, which
+   the codex-routing-honesty rule forbids). The degradation is recorded loudly: `crossFamily: false` in the
+   result and the review doc — run an independent cross-family review manually for the full guarantee.
 4. **Cost control.** One gate per hand-off, not per commit. A stack of related changes gets one Step-10 pass
    on the combined diff.
 
 ## Promise tag
 
-`<promise>FEATURE_ADR_DELIVERY_GATED</promise>` — and the `🚦 Gates:` line gains `delivery ready|blocked`
-(derived from the review doc's Verdict, `n/a` when the gate was not requested).
+`<promise>FEATURE_ADR_DELIVERY_GATED</promise>` — emitted ONLY when the gate ran AND `10_delivery_review.md`
+actually landed (the workflow probes the file; a verdict without its doc never claims the tag). The `🚦 Gates:`
+line gains `delivery ready|blocked|errored` (`n/a` when the gate was not requested).

package/templates/.claude/skills/frontend-design/SKILL.md

@@ -4,7 +4,7 @@ description: Create distinctive, production-grade frontend interfaces with high
 license: Complete terms in LICENSE.txt
 trust_tier: 0
 trust_tier_label: "Advisory"
-trust_tier_path: "Add references/ directory and run /bto-test to promote to Tier 1"
+trust_tier_path: "Add references/ directory and run a BTO evaluation from the separate package @dzhechkov/skills-bto to promote to Tier 1"
 ---
 
 This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.

package/templates/.claude/skills/goap-research-ed25519/SKILL.md

@@ -3,7 +3,7 @@ name: goap-research-ed25519
 description: GOAP research system with Ed25519 provenance and tamper-evidence under pinned trusted-issuer keys. Use for high-stakes research that needs cited sources, explicit confidence, signed audit trails, or cryptographic proof of who signed a fact. Ed25519 does not prove truthfulness or prevent hallucination.
 trust_tier: 1
 trust_tier_label: "Structured"
-trust_tier_path: "Run /bto-test to promote to Tier 2"
+trust_tier_path: "Run a BTO evaluation from the separate package @dzhechkov/skills-bto to promote to Tier 2"
 ---
 
 # GOAP Research with Ed25519 Provenance

package/templates/.claude/skills/knowledge-extractor/SKILL.md

@@ -9,7 +9,7 @@ trust_tier: 2
 trust_tier_label: "Validated"
 bto_score: 7.5
 bto_date: "2026-03-03"
-trust_tier_path: "Run /bto-test, score >= 8.5 + eval tests for Tier 3"
+trust_tier_path: "Run a BTO evaluation from the separate package @dzhechkov/skills-bto, score >= 8.5 + eval tests for Tier 3"
 ---
 
 # Knowledge Extractor
@@ -227,7 +227,7 @@ Category-to-agent mapping (see `references/artifact-categories.md`):
 | memory_query() | Pipeline start | Load historical harvest patterns |
 | memory_store() | After user checkpoint | Store harvest reward data |
 | brain-export | N/A (passive) | Findings JSON is brain-compatible schema |
-| BTO | Post-harvest | Placed skills can be evaluated via `/bto-test` |
+| BTO | Post-harvest | Placed skills can be evaluated with the separate package `npx @dzhechkov/skills-bto` |
 | dream cycles | Pipeline end | Update trigger-state.json |
 | /harvest command | Entry point | Thin wrapper loads this skill |
 

package/templates/.claude/skills/knowledge-extractor/modules/04-integrate.md

@@ -144,7 +144,7 @@ Placed artifacts:
 Gate pass rate: {rate}%
 Memory reward stored: {score} ({label})
 
-Run /bto-test on placed skills for promotion to Tier 2.
+Run a BTO evaluation (separate package: `npx @dzhechkov/skills-bto`) on placed skills for promotion to Tier 2.
 ═══════════════════════════════════════════════════════
 ```
 

package/templates/.claude/skills/knowledge-extractor/references/maturity-model.md

@@ -10,7 +10,7 @@ and in TOOLKIT_HARVEST.md entries so consumers know how much trust to place in t
 |-------|-------|----------|-------|
 | Alpha | Alpha | First extraction, untested. Used in exactly 1 project. No validation. | 🔴 |
 | Beta | Beta | Used in 2+ projects. Basic validation. May have rough edges. | 🟡 |
-| Stable | Stable | Used in 3+ projects. Proven track record. Passed /bto-test or equivalent. | 🟢 |
+| Stable | Stable | Used in 3+ projects. Proven track record. Passed a BTO evaluation (separate package: `@dzhechkov/skills-bto`) or equivalent. | 🟢 |
 
 ## Promotion Protocol
 
@@ -34,7 +34,7 @@ Promotion action:
 Required evidence (ALL of the following):
 - Used in 3 or more distinct projects (verified by `used_in` list).
 - At least one of the following validation signals exists:
-  - Passed `/bto-test` Layer 2 evaluation with score >= 7.0.
+  - Passed a BTO Layer 2 evaluation (separate package: `@dzhechkov/skills-bto`) with score >= 7.0.
   - Has a documented test case in a `references/` or `examples/` directory.
   - Was reviewed and approved by a second human reviewer in a harvest session.
 
@@ -48,7 +48,7 @@ Promotion action:
 
 A stable or beta finding may be demoted if evidence of unreliability emerges:
 - A project reports the finding caused errors or required significant modification.
-- A `/bto-test` run scores the finding below 5.0.
+- A BTO evaluation run (separate package: `@dzhechkov/skills-bto`) scores the finding below 5.0.
 
 Demotion action:
 1. Downgrade maturity by one level (stable -> beta, beta -> alpha).

package/templates/.claude/skills/presentation-storyteller/SKILL.md

@@ -11,7 +11,7 @@ description: >
   storytelling", "презентация со скриптами", "sales deck", "pitch deck", "продающая презентация".
 trust_tier: 1
 trust_tier_label: "Structured"
-trust_tier_path: "Run /bto-test to promote to Tier 2"
+trust_tier_path: "Run a BTO evaluation from the separate package @dzhechkov/skills-bto to promote to Tier 2"
 ---
 
 # Presentation Storyteller: Sales Decks with Verified Sources

package/templates/.claude/skills/problem-solver-enhanced/SKILL.md

@@ -3,7 +3,7 @@ name: problem-solver-enhanced
 description: Elite problem-solving system combining first principles thinking, game theory, root cause analysis, systematic frameworks AND TRIZ inventive principles for solving complex challenges. Use when facing complex challenges with unclear solutions, strategic decisions with multiple stakeholders, problems requiring breakthrough (not incremental) solutions, trade-offs that seem impossible to resolve, competitive scenarios requiring game-theoretic analysis, system design problems, or any situation requiring both analytical rigor and inventive thinking beyond surface-level solutions.
 trust_tier: 1
 trust_tier_label: "Structured"
-trust_tier_path: "Run /bto-test to promote to Tier 2"
+trust_tier_path: "Run a BTO evaluation from the separate package @dzhechkov/skills-bto to promote to Tier 2"
 ---
 
 # Elite Problem Solver (Enhanced with TRIZ)

package/templates/.claude/skills/reverse-engineering-unicorn/SKILL.md

@@ -3,7 +3,7 @@ name: reverse-engineering-unicorn
 description: Reverse engineer any company into a launch playbook with clickable CJM prototype. Triggers on "проанализируй компанию", "reverse engineer", "разбери бизнес-модель", "playbook запуска".
 trust_tier: 1
 trust_tier_label: "Structured"
-trust_tier_path: "Run /bto-test to promote to Tier 2"
+trust_tier_path: "Run a BTO evaluation from the separate package @dzhechkov/skills-bto to promote to Tier 2"
 ---
 
 # Reverse Engineering Unicorn v2

package/templates/CLAUDE.md

@@ -31,19 +31,17 @@
 
 /analyst-manual [тема/задача]       — Стратегический анализ с checkpoint'ами (explore → research → solve)
 
-/bto [путь или описание]           — Build-Test-Optimize полный цикл
-/bto-build [описание]              — Генерация нового скилла/команды
-/bto-benchmark [путь]              — Детерминистический бенчмаркинг артефакта
-/bto-test [путь]                   — Мульти-агентная оценка артефакта
-/bto-optimize [путь]               — Эволюционная оптимизация промптов
-
 /learning-stats [--domain X] [--phase N] — Reward learning аналитика
 ```
 
+> Это ВСЕ команды, которые ставит этот пакет (19 файлов в `.claude/commands/`).
+> Оценка и оптимизация скиллов (BTO) — отдельный пакет, слэш-команд здесь нет:
+> `npx @dzhechkov/skills-bto init`
+
 ## Структура проекта
 
 ```
-product-keysarium-2026/
+<ваш-проект>/
 ├── CLAUDE.md                       ← Этот файл (мастер-инструкции)
 ├── TOOLKIT_HARVEST.md              ← Трекер знаний для извлечения
 ├── .claude/
@@ -61,11 +59,8 @@ product-keysarium-2026/
 │   │   ├── harvest.md              ← /harvest — извлечение знаний
 │   │   ├── brain-export.md         ← /brain-export — экспорт portable brain
 │   │   ├── brain-import.md         ← /brain-import — импорт знаний
-│   │   ├── bto.md                  ← /bto — Build-Test-Optimize pipeline
-│   │   ├── bto-build.md            ← /bto-build — генерация артефактов
-│   │   ├── bto-test.md             ← /bto-test — мульти-агентная оценка
-│   │   ├── bto-optimize.md         ← /bto-optimize — оптимизация промптов
 │   │   ├── feature-adr.md          ← /feature-adr — adaptive feature development
+│   │   ├── analyst-manual.md       ← /analyst-manual — стратегический анализ
 │   │   ├── init-platform.md        ← /init-platform — мульти-платформенная генерация
 │   │   ├── learning-stats.md       ← /learning-stats — reward learning аналитика
 │   │   ├── workers.md              ← /workers — управление фоновыми воркерами
@@ -79,10 +74,8 @@ product-keysarium-2026/
 │   │   ├── phase-4-architecture.shard.md
 │   │   ├── phase-5-presentation.shard.md
 │   │   ├── phase-ai-factory.shard.md  ← AI Factory mode (только при --ai-factory)
-│   │   ├── bto-evaluation.shard.md
 │   │   └── feature-adr.shard.md
 │   └── skills/                     ← Навыки (building blocks)
-│       ├── bto/                    ← Build-Test-Optimize (мульти-агентная оценка)
 │       ├── explore/                ← Адаптивная кларификация задач
 │       ├── frontend-design/        ← Дизайн фронтенда
 │       ├── goap-research-ed25519/  ← GOAP research + crypto verification
@@ -92,12 +85,20 @@ product-keysarium-2026/
 │       ├── feature-adr/            ← Adaptive feature development (9 steps, S/M/L/XL)
 │       ├── knowledge-extractor/   ← Knowledge harvesting (5 agents, 7 categories, 8 gates)
 │       ├── analyst-manual-full/  ← Композитный аналитик (explore + research + solve, manual checkpoints)
+│       ├── edu-site-generator/   ← Gamified educational SPA из документации
+│       ├── transcript-site-generator/ ← Транскрипт → интерактивный static site
 │       └── ai-factory-mapper/    ← Маппинг сценариев на Cloud.ru Evolution AI Factory (v1.0)
 ├── lib/                            ← Библиотечные модули
+│   ├── phase-utils.md              ← Утилиты фаз
+│   ├── agent-patterns.md           ← Паттерны agent swarm
+│   ├── skill-loader.md             ← Загрузка скиллов
+│   ├── domain-templates.md         ← Доменные шаблоны
 │   ├── background-workers.md       ← Протокол фоновых воркеров
 │   ├── memory-protocol.md          ← Протокол memory_query / memory_store
 │   ├── reward-tracker.md           ← Аналитика и обнаружение паттернов
 │   ├── dream-engine.md             ← DreamEngine: concept graph + insight generation
+│   ├── witness-chain.md            ← Witness chain (tamper-evidence)
+│   ├── judge-attestation.md        ← Аттестация судей
 │   ├── platform-adapters.md        ← Реестр платформенных адаптеров
 │   ├── platform-templates/         ← Шаблоны для генерации конфигов
 │   │   ├── cursor.md               ← Cursor (.cursorrules)
@@ -108,17 +109,6 @@ product-keysarium-2026/
 │       ├── health-check.md          ← Проверка здоровья системы
 │       ├── brain-export.md          ← Фоновый экспорт brain
 │       └── dream-cycle.md           ← Dream cycle воркер (concept graph + insights)
-├── packages/                       ← npm пакеты
-│   ├── dz-keysarium/              ← @dzhechkov/keysarium (research pipeline)
-│   ├── dz-skills-bto/             ← @dzhechkov/skills-bto (BTO evaluation)
-│   ├── dz-feature-adr/            ← @dzhechkov/skills-feature-adr (feature development)
-│   └── dz-keysarium-core/         ← @dzhechkov/keysarium-core (shared framework)
-│       ├── governance/             ← Constitution + shards + checkpoints
-│       ├── memory/                 ← Learning protocol + reward + dream engine
-│       ├── orchestration/          ← Queen protocol + topologies + workers + routing
-│       ├── verification/           ← Witness chain + judge attestation + audit trail
-│       ├── trust-tiers/            ← 4-tier classification + promotion
-│       └── platform/               ← Multi-platform adapters (Cursor, OpenCode, Copilot)
 ├── features/                       ← Директории фич (/feature-adr output)
 │   └── [feature-slug]/             ← Каждая фича изолирована
 └── researches/                     ← Директории исследований
@@ -169,7 +159,7 @@ DISCOVERY → EXPLORE  → RESEARCH → CJM PROTO    → SOLVE    → ARCHITECTU
 7. **Всё в researches/<slug>/** — не засоряем корень
 8. **Governance shards** — каждая фаза загружает свой shard из `.claude/shards/`
 9. **Model routing** — haiku для Layer 0-1, sonnet для research/judges, opus для creative work
-10. **Trust tiers** — скиллы классифицированы (Tier 0-3), повышение через `/bto-test`
+10. **Trust tiers** — скиллы классифицированы (Tier 0-3); повышение требует оценки из отдельного пакета `@dzhechkov/skills-bto` (в этом пакете команд `/bto*` нет)
 11. **`--ai-factory` флаг полностью аддитивен** — без флага поведение идентично предыдущим версиям; с флагом — маппинг на Cloud.ru AI Factory интегрируется во все фазы через `phase-ai-factory.shard.md`
 
 ## Governance System
@@ -190,7 +180,7 @@ DISCOVERY → EXPLORE  → RESEARCH → CJM PROTO    → SOLVE    → ARCHITECTU
 | Tier | Label | Требования |
 |------|-------|-----------|
 | 3 | Verified | Eval test suites + deterministic validation |
-| 2 | Validated | /bto-test Layer 2 score >= 7.0 |
+| 2 | Validated | BTO-оценка (пакет `@dzhechkov/skills-bto`): Layer 2 score >= 7.0 |
 | 1 | Structured | SKILL.md + references/ or modules/ |
 | 0 | Advisory | Только SKILL.md |
 
@@ -288,12 +278,6 @@ reverse-engineering-unicorn (оркестратор)
         ├── explore
         └── goap-research-ed25519
 
-bto (Build-Test-Optimize)
-  ├── explore (кларификация в BUILD модуле)
-  ├── modules/build.md (генерация артефактов)
-  ├── modules/test.md (мульти-агентная оценка: 3 судьи)
-  └── modules/optimize.md (эволюционная оптимизация)
-
 feature-adr (Adaptive Feature Development)
   ├── explore (кларификация требований)
   ├── problem-solver-enhanced (trade-off анализ для ADR)
@@ -310,17 +294,13 @@ knowledge-extractor (извлечение знаний)
   └── templates/ (artifact-card, harvest-report)
 ```
 
-## BTO — Build-Benchmark-Test-Optimize
+## BTO — Build-Benchmark-Test-Optimize (ОТДЕЛЬНЫЙ ПАКЕТ)
 
 Система мульти-агентной оценки и оптимизации скиллов/команд (4-module pipeline).
 
-```
-/bto [путь]           — Полный цикл: BUILD → BENCHMARK → TEST → OPTIMIZE
-/bto-build [описание] — Генерация нового скилла/команды
-/bto-benchmark [путь] — Детерминистический бенчмаркинг артефакта
-/bto-test [путь]      — Оценка: Layer 0 (детерм.) → Layer 1 (haiku) → Layer 2 (3 судьи)
-/bto-optimize [путь]  — Эволюционная оптимизация за 3 раунда
-```
+**Этот пакет её НЕ ставит.** Ни скилла `bto/`, ни команд `/bto*` в установке Keysarium нет —
+их поставляет `@dzhechkov/skills-bto`. Раздел ниже оставлен как справка: он описывает, что вы
+получите, если поставите тот пакет (см. «Standalone пакет» в конце раздела).
 
 ### Архитектура оценки (TEST)
 

package/templates/docs/continuous-learning-guide.md

@@ -1,5 +1,11 @@
 # Непрерывное обучение в Keysarium — Полное руководство
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 > Как данные, генерируемые в ходе продуктовых исследований, превращаются в улучшения системы.
 
 ## Содержание

package/templates/docs/feature-adr/05-user-guide.md

@@ -1,5 +1,11 @@
 # Руководство пользователя @dzhechkov/skills-feature-adr
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 > Полное руководство по использованию адаптивного pipeline для разработки фич любой сложности.
 
 ---

package/templates/docs/improvement-directions.md

@@ -1,5 +1,11 @@
 # Направления улучшений Keysarium & Skills-BTO
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 > Результат deep research по репозиториям [Ruflo](https://github.com/ruvnet/ruflo), [Agentic QE](https://github.com/proffesor-for-testing/agentic-qe) и статье [The Portable Orchestra](https://qualityforge.substack.com/p/the-portable-orchestra) (Dragan Spiridonov).
 >
 > Дата исследования: 2026-03-01

package/templates/docs/keysarium/01-deployment-guide.md

@@ -1,5 +1,11 @@
 # Руководство по развёртыванию Product Keysarium 2026
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 ## Содержание
 
 1. [Предварительные требования](#1-предварительные-требования)

package/templates/docs/keysarium/02-admin-guide.md

@@ -1,5 +1,11 @@
 # Руководство администратора Product Keysarium 2026
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 Это руководство описывает настройку, кастомизацию и обслуживание системы Product Keysarium 2026. Предназначено для администраторов, которые управляют скиллами, командами, правилами, хуками и пайплайном исследований.
 
 ---

package/templates/docs/keysarium/03-user-guide.md

@@ -1,5 +1,11 @@
 # Руководство пользователя Product Keysarium 2026
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 Это руководство описывает, как использовать Product Keysarium 2026 для проведения AI-исследований на Кейсариумах и хакатонах. Предназначено для конечных пользователей -- участников команд.
 
 ---

package/templates/docs/keysarium/05-architecture.md

@@ -1,5 +1,11 @@
 # 05. Архитектура и принципы Product Keysarium 2026
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 ## Содержание
 
 1. [Общая архитектура системы](#общая-архитектура-системы)

package/templates/docs/keysarium/06-user-flows.md

@@ -1,5 +1,11 @@
 # 06. Пользовательские и административные flow
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 ## Содержание
 
 1. [User Flow: Полный пайплайн (/casarium)](#user-flow-полный-пайплайн)

package/templates/docs/keysarium-core/02-functionality.md

@@ -1,5 +1,11 @@
 # Функциональность @dzhechkov/keysarium-core
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 > Полный справочник по всем протоколам, алгоритмам и JSON-схемам фреймворка.
 
 ## Содержание

package/templates/docs/keysarium-core/03-deployment-guide.md

@@ -1,5 +1,11 @@
 # Руководство по развёртыванию @dzhechkov/keysarium-core
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 ## Содержание
 
 1. [Предварительные требования](#1-предварительные-требования)

package/templates/docs/keysarium-core/04-admin-guide.md

@@ -1,5 +1,11 @@
 # Руководство администратора @dzhechkov/keysarium-core
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 Практическое руководство по администрированию, мониторингу и обслуживанию фреймворка keysarium-core. Описывает управление модулями, памятью, воркерами, dream cycles, witness chain, trust tiers и резервным копированием.
 
 ---

package/templates/docs/skills-bto/01-deployment-guide.md

@@ -1,5 +1,11 @@
 # Руководство по развёртыванию @dzhechkov/skills-bto
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 ## Содержание
 
 1. [Предварительные требования](#1-предварительные-требования)

package/templates/docs/skills-bto/02-admin-guide.md

@@ -1,5 +1,11 @@
 # Руководство администратора @dzhechkov/skills-bto
 
+> **`/bto*` commands are NOT part of @dzhechkov/keysarium.** The BTO evaluator
+> (Build-Benchmark-Test-Optimize) ships as a SEPARATE npm package. Install it first —
+> `npx @dzhechkov/skills-bto init` — otherwise every `/bto…` command referenced below will
+> not resolve in your project.
+
+
 Это руководство описывает управление, настройку и обслуживание BTO skill pack. Предназначено для администраторов, которые управляют компонентами BTO, настраивают quality gates, конфигурируют панели судей и контролируют качество оценки.
 
 ---