@dzhechkov/keysarium 1.5.2 → 1.5.4

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dzhechkov/keysarium",
-  "version": "1.5.2",
+  "version": "1.5.4",
   "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": {

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

@@ -28,11 +28,11 @@ description: >
 
 | Когда нужен | Какой скилл вызвать | Как |
 |---|---|---|
-| Задача сформулирована расплывчато | `explore` | `view /mnt/skills/user/explore/SKILL.md` |
-| Нужна first-principles декомпозиция на шаги | `problem-solver-enhanced` | `view /mnt/skills/user/problem-solver-enhanced/SKILL.md` |
-| Нужна верификация новинок каталога / источников | `goap-research-ed25519` | `view /mnt/skills/user/goap-research-ed25519/SKILL.md` |
-| Комплексный анализ с checkpoints | `analyst-manual-full` | `view /mnt/skills/user/analyst-manual-full/SKILL.md` |
-| Финальный DOCX-отчёт | `docx` (public) | `view /mnt/skills/public/docx/SKILL.md` |
+| Задача сформулирована расплывчато | `explore` | `view .claude/skills/explore/SKILL.md` |
+| Нужна first-principles декомпозиция на шаги | `problem-solver-enhanced` | `view .claude/skills/problem-solver-enhanced/SKILL.md` |
+| Нужна верификация новинок каталога / источников | `goap-research-ed25519` | `view .claude/skills/goap-research-ed25519/SKILL.md` |
+| Комплексный анализ с checkpoints | `analyst-manual-full` | `view .claude/skills/analyst-manual-full/SKILL.md` |
+| Финальный DOCX-отчёт | `docx` (public, host-provided) | `view /mnt/skills/public/docx/SKILL.md` |
 
 **Правило:** сначала прочитай SKILL.md нужного скилла, потом следуй его инструкциям. Не переписывай его логику в этот SKILL.md.
 
@@ -109,7 +109,7 @@ ai-factory-mapper/
 1. Есть ли у пользователя конкретный сценарий с описанием цели, пользователя, входа, выхода?
 2. Или это общий запрос «как сделать X на AI Factory»?
 
-Если второе — **прочитай `/mnt/skills/user/explore/SKILL.md` и следуй его инструкциям** для уточнения. Не пытайся угадать.
+Если второе — **прочитай `.claude/skills/explore/SKILL.md` и следуй его инструкциям** для уточнения. Не пытайся угадать.
 
 Если задача ясна (например, даётся список сценариев с описанием, как в примере ниже) — переходи к Phase 1.
 
@@ -125,7 +125,7 @@ ai-factory-mapper/
 1. **ВСЕГДА** прочитай `references/catalog.md` — это базовый справочник, но он может устареть.
 2. **ВСЕГДА** сделай `web_search` с запросом `Cloud.ru Evolution AI Factory новые сервисы <текущий_год>` и `Cloud.ru новые MCP серверы <текущий_год>`, чтобы проверить свежие анонсы. Каталог обновляется быстро — пропуск этого шага приводит к ложным gap'ам.
 3. Если пользователь явно указал «используй только актуальные данные» или работа критическая (enterprise-продукт, внешний клиент) — вызови `goap-research-ed25519`:
-   - Прочитай `/mnt/skills/user/goap-research-ed25519/SKILL.md`
+   - Прочитай `.claude/skills/goap-research-ed25519/SKILL.md`
    - Цель: `goal_type="verified_exploratory"`, тема — «Cloud.ru Evolution AI Factory current services catalog»
 4. Зафиксируй в working memory перечень сервисов на момент анализа (это важно для воспроизводимости оценок).
 
@@ -138,7 +138,7 @@ ai-factory-mapper/
 
 **Для каждого сценария:**
 
-1. Прочитай `/mnt/skills/user/problem-solver-enhanced/SKILL.md` — это базовая методология декомпозиции. **Применяй модули 1 (First Principles) и 6 (Contradiction Analysis) как минимум.**
+1. Прочитай `.claude/skills/problem-solver-enhanced/SKILL.md` — это базовая методология декомпозиции. **Применяй модули 1 (First Principles) и 6 (Contradiction Analysis) как минимум.**
 
 2. Открой `references/decomposition-checklist.md` и пройди по каждому из 10 пунктов:
    - Ingest — откуда/в каком формате приходит вход

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

@@ -1,3 +1,13 @@
+---
+name: edu-site-generator
+description: >
+  Generate a complete gamified educational single-page app from documentation or content,
+  optimized for GitHub Pages deployment. Produces a learning site with modules, interactive
+  examples, and progress mechanics. Triggers on "generate edu site from [docs]", "create
+  learning site [topic]", "build educational app [topic]".
+trust_tier: 1
+---
+
 # edu-site-generator — Gamified Educational Site Generator
 
 <!-- Trust Tier: 1 — Structured | Path to Tier 2: Run /bto-test for self-evaluation -->

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

@@ -216,6 +216,7 @@ After Step 8 (or Step 9 for L/XL) completes, verify:
 | `{COMPLEXITY_TIER}` | Step 0 | All steps | S/M/L/XL |
 | `{ACTIVE_STEPS}` | Step 0 | Orchestrator | list[int] |
 | `{TIME_BUDGET}` | Step 0 | All steps | dict |
+| `{LEARNED_PATTERNS}` | Step 0 | Step 1 (brief); Steps 8-9 do their own namespace recalls | list[pattern] (Direct modes only) |
 | `{REQUIREMENTS}` | Step 1 | Steps 2-9 | structured |
 | `{RESEARCH_FINDINGS}` | Step 2 | Steps 3-5 | structured |
 | `{ADR_DECISIONS}` | Step 3 | Steps 3.5-7 | list[ADR] |
@@ -342,18 +343,38 @@ Step 0 (Complexity Router) checks:
 3. If flag + installed → set `{AGENTIC_QE_MODE}` = `direct` or `direct-extended`
 4. If flag present but not installed → WARN and fall back to reference mode
 
+### Pattern memory loop (Direct modes)
+
+When `{AGENTIC_QE_MODE}` = `direct` | `direct-extended`, the pipeline runs a recall → store cycle
+over agentic-qe's MCP pattern memory (`namespace: "learning"`, `fleet_init` first):
+
+- **Step 0** — `memory_query("patterns/feature-adr/*")` **plus** `dz recall --json` over the durable
+  dz store → merged top-3 set `{LEARNED_PATTERNS}`; Step 1 folds them into the requirements brief as advisory lessons.
+- **Step 8** — recalls `patterns/feature-adr/qe/*` to prime the review checklist; after the gap loop
+  closes, stores a `qe-outcome` record in aqe **and** the same lesson via `dz teach` (durable).
+- **Step 9** — recalls `patterns/feature-adr/fleet/*` to prime agent focus; after the fleet verdict,
+  stores a `fleet-qe-finding` in aqe **and** the same lesson via `dz teach`.
+
+**Two stores by design:** the aqe kv store is *ephemeral across MCP-server restarts* (janitor/TTL —
+observed live), so it serves fast in-session semantic recall; the dz lexical store
+(`dz teach`/`dz recall`) is the durable half that survives to the next day. All calls are
+non-blocking — an error or empty result never stalls the pipeline. This layer is
+**distinct from the Keysarium reward layer** installed by `--with-learning`: it uses agentic-qe MCP
+memory + the dz store, is gated on Direct modes only, and never touches `.keysarium/memory/`.
+
 ### What changes with `--full-qe`
 
 Full agentic-qe protocols for the same 9 core skills. No new agents, just deeper methodology.
 
 | Step | Reference Mode (default) | Direct Mode (`--full-qe`) |
 |------|--------------------------|---------------------------|
+| Step 0 | Standard routing | + pattern recall → `{LEARNED_PATTERNS}` |
 | Step 3 | Condensed shift-left protocol | Full Level 1-4 shift-left with BDD generators |
 | Step 3.5 | 3 core + flag-based conditionals | Full QCSD swarm with all 9 agents + DDD mapping |
 | Step 6 | SPARC-GOAP goal state analysis | Full agent with milestone tracking + success metrics |
 | Step 7 | Standard code generation | Standard code generation (no change) |
-| Step 8 | Brutal-honesty 3-mode review | Full calibration levels (1-3) + evidence protocol |
-| Step 9 | 4 agents with condensed protocols | 4 agents with full agentic-qe protocols |
+| Step 8 | Brutal-honesty 3-mode review | Full calibration levels (1-3) + evidence protocol + QE pattern recall/store |
+| Step 9 | 4 agents with condensed protocols | 4 agents with full agentic-qe protocols + fleet pattern recall/store |
 
 ### What `--full-qe-extended` adds on top
 
@@ -399,7 +420,7 @@ npx @dzhechkov/skills-feature-adr init --with-learning --knowledge-extractor
 | Flag | Installs | Purpose |
 |------|----------|---------|
 | (none) | Core skill + command + rules + shard | Feature development pipeline |
-| `--with-learning` | + `lib/memory-protocol.md`, `lib/reward-tracker.md`, `.claude/rules/reward-learning.md` | Pipeline learns from checkpoint feedback |
+| `--with-learning` | + `lib/memory-protocol.md`, `lib/reward-tracker.md`, `.claude/rules/reward-learning.md` | Installs the shared **Keysarium learning layer** (Phases 0-5, `.keysarium/memory/`). The feature-adr pipeline itself does not yet wire `memory_query`/`memory_store` into its Steps 0-9 — this layer applies only if you also run the Keysarium pipeline. A separate loop exists: in Direct modes (`--full-qe`/`--full-qe-extended`) the pipeline wires **agentic-qe MCP** pattern memory into Steps 0/8/9 — see "Pattern memory loop (Direct modes)" above. |
 | `--knowledge-extractor` | + `.claude/skills/knowledge-extractor/`, `.claude/commands/harvest.md` | Extract reusable patterns after feature completion |
 
 > **Note:** If `@dzhechkov/keysarium` is already installed, these flags are not needed — keysarium includes all learning and extraction capabilities.

package/templates/.claude/skills/feature-adr/modules/00-complexity-router.md

@@ -57,12 +57,16 @@ Load `references/complexity-matrix.md` for the full matrix. Summary:
 | 0 Complexity Router | ✓ | ✓ | ✓ | ✓ |
 | 1 Requirements | ✓ light | ✓ | ✓ | ✓ |
 | 2 Research | - | - | ✓ | ✓ |
-| 3 ADR | - | ✓ (1 ADR) | ✓ (N ADRs) | ✓ (N ADRs) |
+| 3 ADR + Shift-Left | - | ✓ (1 ADR) | ✓ (N ADRs) | ✓ (N ADRs) |
+| 3.5 QCSD Ideation Swarm | - | ✓ | ✓ | ✓ |
 | 4 DDD | - | - | ✓ | ✓ |
 | 5 Architecture | - | ✓ light | ✓ | ✓ |
 | 6 Implementation Plan | ✓ inline | ✓ | ✓ | ✓ |
 | 7 Code | ✓ | ✓ | ✓ | ✓ |
-| 8 QE | ✓ smoke | ✓ | ✓ | ✓ full |
+| 8 QE + Brutal Honesty | ✓ smoke | ✓ | ✓ | ✓ full |
+| 9 Fleet QE Assessment | - | - | ✓ | ✓ |
+
+> Steps 3.5 (M+) and 9 (L/XL) are mandatory — skipping them is a BLOCK per the shard Anti-Patterns.
 
 ### 5. Calculate Time Budget
 
@@ -75,6 +79,23 @@ Load `references/complexity-matrix.md` for the full matrix. Summary:
 
 R = Requirements, P = Planning (ADR+DDD+Arch), I = Implementation, Q = QE
 
+### 6. Pattern Recall (Direct Mode only)
+
+Runs after tier classification, only when `{AGENTIC_QE_MODE}` = `direct` | `direct-extended`
+(set during Step 0 flag detection per SKILL.md: `--full-qe`/`--full-qe-extended` + agentic-qe installed). Non-blocking — an error or empty result must never stall the pipeline.
+
+1. If the aqe fleet is not yet initialized this session, call `mcp__agentic-qe__fleet_init` first (required before any other aqe MCP tool).
+2. Call `mcp__agentic-qe__memory_query({ pattern: "patterns/feature-adr/*", namespace: "learning", limit: 5 })`.
+3. ALSO query the **durable half** of the loop — the dz lexical store:
+   `dz recall "<feature domain keywords>" --json --limit 5` (CLI; works wherever dz is set up).
+   Why both: the aqe kv store is **ephemeral across MCP-server restarts** (janitor/TTL — observed
+   live: a record survived hours, not days), so aqe serves in-session semantic recall while the
+   dz store is the durable memory the loop can trust tomorrow.
+4. Merge both result sets, dedupe by content, select the top 3 by confidence/reward → set `{LEARNED_PATTERNS}`.
+5. Reference mode, no hits, or errors (either store) → `{LEARNED_PATTERNS}` = `[]` or the surviving half; proceed normally.
+
+Step 1 folds `{LEARNED_PATTERNS}` into the requirements brief as "lessons from previous features" — advisory context only, never requirements themselves. Why here: Step 0 is the one point where recall can be keyed to the feature's phase and domain — per-prompt hook auto-injection cannot see which pipeline step is running.
+
 ## Output
 
 Set the following variables:
@@ -84,6 +105,7 @@ Set the following variables:
 {ACTIVE_STEPS} = [0, 1, 6, 7, 8]  # example for S
 {TIME_BUDGET} = { requirements: 2, planning: 0, implementation: 10, qe: 3 }
 {DIMENSION_SCORES} = { files: 1, domains: 1, integrations: 1, breaking: 1, models: 1, crosscutting: 1 }
+{LEARNED_PATTERNS} = [ ... ]  # top-3 by confidence from memory_query; [] in reference mode / no hits / error
 ```
 
 Create artifact: `features/<slug>/00_complexity_assessment.md`
@@ -92,7 +114,7 @@ Create artifact: `features/<slug>/00_complexity_assessment.md`
 
 ```
 ═══════════════════════════════════════════════════════
-⏸️ STEP 0/8: Complexity Router Complete
+⏸️ STEP 0: Complexity Router Complete
 <promise>FEATURE_ADR_ROUTED</promise>
 Tier: {COMPLEXITY_TIER} | Active Steps: {ACTIVE_STEPS}
 

package/templates/.claude/skills/feature-adr/modules/01-requirements.md

@@ -29,6 +29,12 @@ Read: .claude/skills/explore/SKILL.md
 Use the explore skill to clarify ambiguous requirements through adaptive questioning.
 For S-tier: skip explore, extract requirements directly from description.
 
+### 1.5 Fold Learned Patterns (Direct modes only)
+
+If `{LEARNED_PATTERNS}` is non-empty (set by Step 0's Pattern Recall), fold each into the
+requirements brief as an advisory "lesson from previous features" — context that informs
+elicitation, never a requirement itself. Empty/absent → skip silently.
+
 ### 2. Identify Stakeholders
 
 | Question | Why |

package/templates/.claude/skills/feature-adr/modules/08-qe.md

@@ -56,6 +56,19 @@ For critical user flows:
 - Test with realistic data volumes
 - Test failure recovery scenarios
 
+### 2.5 QE Pattern Recall (Direct Mode only)
+
+When `{AGENTIC_QE_MODE}` = `direct` | `direct-extended`, before the brutal-honesty review starts,
+recall prior QE outcomes for similar work:
+
+```
+mcp__agentic-qe__memory_query({ pattern: "patterns/feature-adr/qe/*", namespace: "learning", limit: 5 })
+// If this session resumed directly at Step 8, call fleet_init first (as in Steps 0/9).
+```
+
+Use the results to prime the review checklist — e.g. recurring gap types, dimensions that historically
+produced blockers. Non-blocking: empty result or error → proceed with the standard checklist.
+
 ### 3. Code Review via Brutal Honesty Review (M+)
 
 > Load: `references/agentic-qe/brutal-honesty-review.md`
@@ -193,6 +206,38 @@ Compile all findings into a structured report:
 ✅ READY FOR MERGE | ❌ NEEDS FIXES | ⚠️ CONDITIONAL APPROVAL
 ```
 
+### 8. QE Pattern Store (Direct Mode only)
+
+When `{AGENTIC_QE_MODE}` = `direct` | `direct-extended`, after the gap loop is closed and the verdict is set:
+
+```
+mcp__agentic-qe__memory_store({
+  key: "patterns/feature-adr/qe/{timestamp}",
+  namespace: "learning",
+  value: {
+    pattern: "<one-sentence lesson from this QE run>",
+    confidence: <honest 0-1 derived from the gap loop>,
+    type: "qe-outcome",
+    metadata: { tier: "{COMPLEXITY_TIER}", gaps_found: <N>, verdict: "<READY|NEEDS_FIXES|CONDITIONAL>" }
+  },
+  persist: true
+})
+```
+
+Confidence must be honest — derived from the gap loop, never a fabricated 1.0
+(e.g. zero gaps in one iteration ≈ 0.9; gaps remaining after 3 iterations ≤ 0.4).
+
+Then persist the SAME lesson durably (the aqe kv store is ephemeral across MCP-server
+restarts — observed live; the dz lexical store is the half that survives):
+
+```
+dz teach "<the same one-sentence lesson>" --reward <same confidence> --domain feature-adr \
+  --type <success-pattern if verdict READY, else lesson-learned>
+```
+
+Non-blocking: if `dz` is not on PATH or the command fails, note it and proceed.
+Non-blocking: a write failure is logged and the pipeline continues.
+
 ## Output
 
 Create `features/<slug>/08_qe_report.md` with full QE report.

package/templates/.claude/skills/feature-adr/modules/09-fleet-qe.md

@@ -263,6 +263,47 @@ are added — the same fleet runs with deeper methodology from the full skill fi
 | Agent 3 | Condensed enterprise-integration | Full hierarchical fleet + QCSD flags |
 | Agent 4 | Condensed regression-testing | Full change-based + historical + time-budget strategies |
 
+## Pattern Memory Loop (Direct Modes)
+
+When `{AGENTIC_QE_MODE}` = `direct` | `direct-extended`, Step 9 runs a recall → store cycle over
+agentic-qe pattern memory. Non-blocking: errors or empty results never stall the assessment.
+(`fleet_init` was called in Step 0; call it first if this session resumed at Step 9.)
+
+**Before fleet assembly** — prime agent focus areas:
+
+```
+mcp__agentic-qe__memory_query({ pattern: "patterns/feature-adr/fleet/*", namespace: "learning", limit: 5 })
+```
+
+Fold recurring findings (e.g. traceability chains that historically break, risk categories that recur)
+into each agent's scope brief.
+
+**After the fleet verdict** — store the finding for future pipeline runs:
+
+```
+mcp__agentic-qe__memory_store({
+  key: "patterns/feature-adr/fleet/{timestamp}",
+  namespace: "learning",
+  value: {
+    pattern: "<one-sentence lesson from this assessment>",
+    confidence: <honest 0-1 from gap synthesis — never a fabricated 1.0>,
+    type: "fleet-qe-finding",
+    metadata: { tier: "{COMPLEXITY_TIER}", verdict: "{FLEET_QE_VERDICT}", agents_used: <4-7>, remediation_count: <N> }
+  },
+  persist: true
+})
+```
+
+Then persist the SAME finding durably via the dz lexical store (the aqe kv store is
+ephemeral across MCP-server restarts — the dz half survives):
+
+```
+dz teach "<the same one-sentence lesson>" --reward <same confidence> --domain feature-adr \
+  --type <success-pattern if COMPLETE, else lesson-learned>
+```
+
+Non-blocking: if `dz` is unavailable or fails, note it and proceed.
+
 ## Direct Extended Mode (`--full-qe-extended`)
 
 When `{AGENTIC_QE_MODE}` = `direct-extended`, Step 9 gets everything from
@@ -282,7 +323,7 @@ These agents are spawned alongside Agents 1-4 in the same message.
 
 After Step 9 completes, if `--full-qe-extended` is active:
 1. Load `qcsd-production-swarm` feedback loop patterns
-2. Store Fleet QE findings in memory for future pipeline runs
+2. Store Fleet QE findings via the Pattern Memory Loop above (`patterns/feature-adr/fleet/{timestamp}`)
 3. Flag production health risks for monitoring post-deploy
 4. Advisory: suggest post-deploy monitoring checklist
 

package/templates/.claude/skills/feature-adr/references/complexity-matrix.md

@@ -79,39 +79,44 @@ Skipped: 2, 3, 4, 5
 ### Tier M (Score 9-13)
 
 ```
-Active:  0 → 1 → 3(1 ADR) → 5(light) → 6 → 7 → 8
-Skipped: 2, 4
+Active:  0 → 1 → 3(1 ADR) → 3.5 → 5(light) → 6 → 7 → 8
+Skipped: 2, 4, 9
 ```
 
 **Step adaptations:**
 - Step 3: Single ADR for the main architectural decision
+- Step 3.5: QCSD ideation swarm — 3 core agents + GO/CONDITIONAL/NO-GO verdict (mandatory for M+ — skipping is a BLOCK)
 - Step 5: Component diagram only, no full C4
 
 ### Tier L (Score 14-19)
 
 ```
-Active:  0 → 1 → [2 ‖ 3] → [4 ‖ 5] → 6 → 7 → 8
-Parallel groups: (2,3) and (4,5)
+Active:  0 → 1 → [2 ‖ 3] → 3.5 → [4 ‖ 5] → 6 → 7 → 8 → 9
+Parallel groups: (2,3) and (4,5); Step 3.5 runs after Step 3, Step 9 after Step 8
 ```
 
 **Step adaptations:**
 - Step 2: Research analogues in codebase and external patterns
 - Step 3: Multiple ADRs for each significant decision
+- Step 3.5: QCSD ideation swarm — 3-9 parallel agents + GO/CONDITIONAL/NO-GO verdict (mandatory for M+ — skipping is a BLOCK)
 - Step 4: Bounded contexts + ubiquitous language
 - Step 5: Full C4 (Context + Container + Component)
 - Step 8: Unit + integration tests + code review
+- Step 9: Fleet QE assessment — 4 parallel agents (traceability ‖ risk ‖ integration ‖ regression) (mandatory for L/XL — skipping is a BLOCK)
 
 ### Tier XL (Score 20-24)
 
 ```
-Active:  0 → 1 → [2 ‖ 3] → [4 ‖ 5] → 6 → 7(parallel) → 8(full)
-Parallel groups: (2,3), (4,5), (7 per module)
+Active:  0 → 1 → [2 ‖ 3] → 3.5 → [4 ‖ 5] → 6 → 7(parallel) → 8(full) → 9
+Parallel groups: (2,3), (4,5 — after 3.5), (7 per module)
 ```
 
 **Step adaptations:**
 - All steps at full depth
+- Step 3.5: QCSD ideation swarm — 3-9 parallel agents + GO/CONDITIONAL/NO-GO verdict (mandatory for M+ — skipping is a BLOCK)
 - Step 7: Multiple parallel agents, one per module/domain
 - Step 8: Full QE — unit + integration + e2e + performance + security review
+- Step 9: Fleet QE assessment — 4 parallel agents (4-7 with `--full-qe-extended`) (mandatory for L/XL — skipping is a BLOCK)
 
 ---
 

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

@@ -36,8 +36,8 @@ presentation/
 
 | Phase | Skill | Path | Purpose |
 |-------|-------|------|---------|
-| 1. Explore | `explore` | `/mnt/skills/user/explore/SKILL.md` | Уточнение задачи |
-| 2. Research | `goap-research-ed25519` | `/mnt/skills/user/goap-research-ed25519/SKILL.md` | Верифицированные источники |
+| 1. Explore | `explore` | `.claude/skills/explore/SKILL.md` | Уточнение задачи |
+| 2. Research | `goap-research-ed25519` | `.claude/skills/goap-research-ed25519/SKILL.md` | Верифицированные источники |
 
 ## Workflow Overview
 
@@ -72,7 +72,7 @@ presentation/
 
 ## Phase 1: Explore (Presentation Brief)
 
-**Load:** `view("/mnt/skills/user/explore/SKILL.md")`
+**Load:** `view(".claude/skills/explore/SKILL.md")`
 
 **Key Questions for Presentations:**
 
@@ -104,7 +104,7 @@ presentation/
 
 ## Phase 2: Research (Verified Sources)
 
-**Load:** `view("/mnt/skills/user/goap-research-ed25519/SKILL.md")`
+**Load:** `view(".claude/skills/goap-research-ed25519/SKILL.md")`
 
 **Research Actions for Presentations:**
 

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

@@ -46,7 +46,7 @@ SKILL.md (this file — orchestrator)
 | Skill | Modules | Purpose |
 |-------|---------|---------|
 | `explore` | Pre-flight | Clarify vague requests |
-| `goap-research` | M1-M5 (DEEP) | Adaptive research: A* + OODA |
+| `goap-research-ed25519` | M1-M5 (DEEP) | Adaptive research: A* + OODA |
 | `goap-research-ed25519` | M1-M5 (VERIFIED) | + Ed25519 crypto verification |
 | `problem-solver-enhanced` | M3,M4,M5 (DEEP) | Game Theory, TRIZ, 2nd-Order |
 | `frontend-design` | M2.5 (DEEP) | Production-grade CJM prototype design |
@@ -186,12 +186,12 @@ After CHECKPOINT 6:
 
 ```
 M0:   explore
-M1:   goap-research → goap-research-ed25519
-M2:   goap-research + references/jtbd-canvas.md
+M1:   goap-research-ed25519
+M2:   goap-research-ed25519 + references/jtbd-canvas.md
 M2.5: frontend-design + examples/noom-cjm-example.md (GENERATES new .jsx)
-M3:   goap-research + problem-solver-enhanced [GT, TRIZ, 2nd-Order]
-M4:   goap-research + problem-solver-enhanced [FP, TRIZ] + references/industry-benchmarks.md
-M5:   goap-research + problem-solver-enhanced [2nd-Order, TRIZ]
+M3:   goap-research-ed25519 + problem-solver-enhanced [GT, TRIZ, 2nd-Order]
+M4:   goap-research-ed25519 + problem-solver-enhanced [FP, TRIZ] + references/industry-benchmarks.md
+M5:   goap-research-ed25519 + problem-solver-enhanced [2nd-Order, TRIZ]
 M6:   brutal-honesty-review [Bach + Ramsay]
 Post: presentation-storyteller / md2pptx / idea2prd-manual
 ```

package/templates/.claude/skills/reverse-engineering-unicorn/modules/01-intelligence.md

@@ -38,7 +38,7 @@
 
 ### 🔵 Режим DEEP
 
-> ⚙️ **Перед началом:** `view(/mnt/skills/user/goap-research/SKILL.md)`
+> ⚙️ **Перед началом:** `view(.claude/skills/goap-research-ed25519/SKILL.md)`
 > Примени GOAP-методологию вместо статического списка.
 
 **Phase 1 — State Assessment:**
@@ -110,7 +110,7 @@ confidence = base_reliability × recency_factor
 ### 🟣 Режим VERIFIED (Ed25519)
 
 > ⚙️ **Перед началом:** 
-> 1. `view(/mnt/skills/user/goap-research-ed25519/SKILL.md)`
+> 1. `view(.claude/skills/goap-research-ed25519/SKILL.md)`
 > 2. Установи зависимости:
 > ```bash
 > pip install cryptography --break-system-packages
@@ -118,8 +118,8 @@ confidence = base_reliability × recency_factor
 > 3. Запусти инициализацию:
 > ```python
 > # Скопируй и запусти скрипт из:
-> # /mnt/skills/user/goap-research-ed25519/scripts/ed25519_verifier.py
-> # /mnt/skills/user/goap-research-ed25519/scripts/goap_planner.py
+> # .claude/skills/goap-research-ed25519/scripts/ed25519_verifier.py
+> # .claude/skills/goap-research-ed25519/scripts/goap_planner.py
 > ```
 
 **Всё из режима DEEP, плюс:**
@@ -278,7 +278,7 @@ Chain integrity: ✅ All N facts signed, 0 breaks
 
 | Скилл | Режим | Как используется |
 |-------|-------|-----------------|
-| `goap-research` | DEEP | GOAP-методология: State → Actions → A* → OODA |
+| `goap-research-ed25519` | DEEP | GOAP-методология: State → Actions → A* → OODA |
 | `goap-research-ed25519` | VERIFIED | + Ed25519 подписи + citation chain + trusted issuers |
 
 **Не используются в Module 1** (но релевантны позже):
@@ -320,7 +320,7 @@ Chain integrity: ✅ All N facts signed, 0 breaks
 |---------|----|----|--------|
 | Research protocol | Один режим, статический список | Три режима: QUICK/DEEP/VERIFIED | Адаптация под задачу |
 | Confidence Score | X/5 ручной | Формула с base_reliability × recency × verification | Объективная метрика |
-| External skills | Нет | goap-research, goap-research-ed25519 | Reuse проверенных методологий |
+| External skills | Нет | goap-research-ed25519 | Reuse проверенных методологий |
 | Output columns | 3 (Параметр, Значение, Источник) | 4 (+Confidence) | Прозрачность доверия к данным |
 | Verification | "НЕ НАЙДЕНО" | + Verification Ledger, audit trail, chain integrity | Auditability |
 | Checkpoint actions | 4 варианта | 6 вариантов (+переключение режима) | Гибкость mid-flight |

package/templates/.claude/skills/reverse-engineering-unicorn/modules/02-product-customers.md

@@ -37,7 +37,7 @@
 ### 🔵 Режим DEEP
 
 > ⚙️ **Загрузи:**
-> 1. `view(/mnt/skills/user/goap-research/SKILL.md)` — адаптивный поиск отзывов
+> 1. `view(.claude/skills/goap-research-ed25519/SKILL.md)` — адаптивный поиск отзывов
 > 2. `view(references/jtbd-canvas.md)` — JTBD framework + примеры
 
 **GOAP State Assessment:**
@@ -73,7 +73,7 @@ sample_size_factor: 1.0 (≥20 reviews), 0.8 (10-19), 0.5 (<10)
 
 ### 🟣 Режим VERIFIED
 
-> ⚙️ **Дополнительно:** `view(/mnt/skills/user/goap-research-ed25519/SKILL.md)`
+> ⚙️ **Дополнительно:** `view(.claude/skills/goap-research-ed25519/SKILL.md)`
 
 Всё из DEEP, плюс:
 - Каждая цитата клиента подписывается с `source_url_hash`
@@ -194,7 +194,7 @@ sample_size_factor: 1.0 (≥20 reviews), 0.8 (10-19), 0.5 (<10)
 
 | Скилл | Режим | Как используется |
 |-------|-------|-----------------|
-| `goap-research` | DEEP | Адаптивный поиск отзывов: A* по платформам + OODA при пустых results |
+| `goap-research-ed25519` | DEEP | Адаптивный поиск отзывов: A* по платформам + OODA при пустых results |
 | `goap-research-ed25519` | VERIFIED | + верификация существования цитат по URL |
 | `references/jtbd-canvas.md` | ALL | Шаблон JTBD с примерами (Noom) |
 

package/templates/.claude/skills/reverse-engineering-unicorn/modules/025-cjm-prototype.md

@@ -99,7 +99,7 @@ why_now: [из M2 Section E — 4 фактора]
 
 ### Step 3: Generate React Prototype
 
-> ⚙️ `view(/mnt/skills/public/frontend-design/SKILL.md)` — для design quality
+> ⚙️ `view(.claude/skills/frontend-design/SKILL.md)` — для design quality
 > ⚙️ `view(examples/noom-cjm-example.md)` — few-shot: структура .jsx
 
 **Создай один .jsx файл** со следующей архитектурой:

package/templates/.claude/skills/reverse-engineering-unicorn/modules/03-market-competition.md

@@ -40,8 +40,8 @@
 ### 🔵 Режим DEEP
 
 > ⚙️ **Загрузи перед началом:**
-> 1. `view(/mnt/skills/user/goap-research/SKILL.md)` — для рыночного research
-> 2. `view(/mnt/skills/user/problem-solver-enhanced/SKILL.md)` — Modules 4, 5, 6 — для конкурентного анализа
+> 1. `view(.claude/skills/goap-research-ed25519/SKILL.md)` — для рыночного research
+> 2. `view(.claude/skills/problem-solver-enhanced/SKILL.md)` — Modules 4, 5, 6 — для конкурентного анализа
 
 #### PHASE A: GOAP Market Research
 
@@ -159,7 +159,7 @@ Incumbent  │  (-2, +1)    |  (0, +2)       │  Ценовая война
 
 ### 🟣 Режим VERIFIED (Ed25519)
 
-> ⚙️ **Дополнительно:** `view(/mnt/skills/user/goap-research-ed25519/SKILL.md)`
+> ⚙️ **Дополнительно:** `view(.claude/skills/goap-research-ed25519/SKILL.md)`
 
 Всё из режима DEEP, плюс:
 
@@ -348,7 +348,7 @@ Technical: "Хотим [A], но это ухудшает [B]"
 
 | Скилл | Режим | Как используется | Какие модули скилла |
 |-------|-------|-----------------|-------------------|
-| `goap-research` | DEEP | Адаптивный market research: A* → OODA | Phases 1-4 |
+| `goap-research-ed25519` | DEEP | Адаптивный market research: A* → OODA | Phases 1-4 |
 | `goap-research-ed25519` | VERIFIED | + Ed25519 verification для TAM/SAM числ | Extended Phase 4 |
 | `problem-solver-enhanced` | DEEP | **Module 4:** Game Theory — payoff matrix, Nash equilibrium | PS Module 4 |
 | `problem-solver-enhanced` | DEEP | **Module 5:** Second-Order Thinking — competitive reactions | PS Module 5 |

package/templates/.claude/skills/reverse-engineering-unicorn/modules/04-business-finance.md

@@ -41,8 +41,8 @@
 ### 🔵 Режим DEEP
 
 > ⚙️ **Загрузи:**
-> 1. `view(/mnt/skills/user/goap-research/SKILL.md)` — адаптивный research
-> 2. `view(/mnt/skills/user/problem-solver-enhanced/SKILL.md)` — Modules 1, 6
+> 1. `view(.claude/skills/goap-research-ed25519/SKILL.md)` — адаптивный research
+> 2. `view(.claude/skills/problem-solver-enhanced/SKILL.md)` — Modules 1, 6
 
 #### PHASE A: GOAP Financial Research
 
@@ -111,7 +111,7 @@ Physical: "Команда должна быть БОЛЬШОЙ (для скор
 
 ### 🟣 Режим VERIFIED
 
-> ⚙️ **Дополнительно:** `view(/mnt/skills/user/goap-research-ed25519/SKILL.md)`
+> ⚙️ **Дополнительно:** `view(.claude/skills/goap-research-ed25519/SKILL.md)`
 
 Всё из DEEP, плюс:
 - Все benchmark числа подписываются с source_hash + issuer verification
@@ -258,7 +258,7 @@ Physical: "Команда должна быть БОЛЬШОЙ (для скор
 
 | Скилл | Режим | Как используется |
 |-------|-------|-----------------|
-| `goap-research` | DEEP | Адаптивный поиск benchmarks + salary data |
+| `goap-research-ed25519` | DEEP | Адаптивный поиск benchmarks + salary data |
 | `goap-research-ed25519` | VERIFIED | Верификация финансовых чисел (threshold 0.95 strict) |
 | `problem-solver-enhanced` M1 | DEEP | First Principles: деконструкция каждого допущения |
 | `problem-solver-enhanced` M6 | DEEP | TRIZ: разрешение pricing / team / CAC противоречий |

package/templates/.claude/skills/reverse-engineering-unicorn/modules/05-growth-engine.md

@@ -39,8 +39,8 @@
 ### 🔵 Режим DEEP
 
 > ⚙️ **Загрузи:**
-> 1. `view(/mnt/skills/user/goap-research/SKILL.md)` — адаптивный research
-> 2. `view(/mnt/skills/user/problem-solver-enhanced/SKILL.md)` — Modules 5, 6
+> 1. `view(.claude/skills/goap-research-ed25519/SKILL.md)` — адаптивный research
+> 2. `view(.claude/skills/problem-solver-enhanced/SKILL.md)` — Modules 5, 6
 
 #### PHASE A: GOAP Growth Research
 
@@ -116,7 +116,7 @@ Physical: "Продукт должен быть ПРОСТЫМ (для onboardin
 
 ### 🟣 Режим VERIFIED
 
-> ⚙️ **Дополнительно:** `view(/mnt/skills/user/goap-research-ed25519/SKILL.md)`
+> ⚙️ **Дополнительно:** `view(.claude/skills/goap-research-ed25519/SKILL.md)`
 
 Всё из DEEP, плюс:
 - Traffic estimates, follower counts подписываются
@@ -262,7 +262,7 @@ Step 5: [Flywheel / Data Moat] ──→ усиливает Step 2-3
 
 | Скилл | Режим | Как используется |
 |-------|-------|-----------------|
-| `goap-research` | DEEP | Адаптивный поиск traffic data, marketing channels |
+| `goap-research-ed25519` | DEEP | Адаптивный поиск traffic data, marketing channels |
 | `goap-research-ed25519` | VERIFIED | Верификация traffic estimates, follower counts |
 | `problem-solver-enhanced` M5 | DEEP | Second-Order Thinking: feedback loops, tipping points, competitive reactions |
 | `problem-solver-enhanced` M6 | DEEP | TRIZ: moat engineering через разрешение growth contradictions |

package/templates/.claude/skills/reverse-engineering-unicorn/modules/06-playbook-synthesis.md

@@ -37,7 +37,7 @@
 ### 🔵 Режим DEEP
 
 > ⚙️ **После формирования плана, загрузи:**
-> `view(/mnt/skills/user/brutal-honesty-review/SKILL.md)`
+> `view(.claude/skills/brutal-honesty-review/SKILL.md)`
 > Применяй **Bach Mode (BS-detection)** к финальному playbook.
 
 #### BS-Detection Quality Gate

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

@@ -1,3 +1,13 @@
+---
+name: transcript-site-generator
+description: >
+  Generate a modern, interactive, mobile-friendly, SEO-optimized static website from a
+  transcript or YouTube video link, ready for GitHub Pages deployment with zero build step.
+  Triggers on "generate transcript site from [content]", "create interactive transcript
+  [topic]", "build transcript website from YouTube [url]".
+trust_tier: 2
+---
+
 # transcript-site-generator — Interactive Transcript Site Generator
 
 <!-- Trust Tier: 2 — Validated | BTO Layer 2 Score: 7.82/10 | Promoted: 2026-03-05 -->