@dzhechkov/keysarium 1.5.2 → 1.5.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/package.json +1 -1
- package/templates/.claude/skills/ai-factory-mapper/SKILL.md +8 -8
- package/templates/.claude/skills/edu-site-generator/SKILL.md +10 -0
- package/templates/.claude/skills/feature-adr/SKILL.md +1 -1
- package/templates/.claude/skills/feature-adr/modules/00-complexity-router.md +7 -3
- package/templates/.claude/skills/feature-adr/references/complexity-matrix.md +11 -6
- package/templates/.claude/skills/presentation-storyteller/SKILL.md +4 -4
- package/templates/.claude/skills/reverse-engineering-unicorn/SKILL.md +6 -6
- package/templates/.claude/skills/reverse-engineering-unicorn/modules/01-intelligence.md +6 -6
- package/templates/.claude/skills/reverse-engineering-unicorn/modules/02-product-customers.md +3 -3
- package/templates/.claude/skills/reverse-engineering-unicorn/modules/025-cjm-prototype.md +1 -1
- package/templates/.claude/skills/reverse-engineering-unicorn/modules/03-market-competition.md +4 -4
- package/templates/.claude/skills/reverse-engineering-unicorn/modules/04-business-finance.md +4 -4
- package/templates/.claude/skills/reverse-engineering-unicorn/modules/05-growth-engine.md +4 -4
- package/templates/.claude/skills/reverse-engineering-unicorn/modules/06-playbook-synthesis.md +1 -1
- package/templates/.claude/skills/transcript-site-generator/SKILL.md +10 -0
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@dzhechkov/keysarium",
|
|
3
|
-
"version": "1.5.
|
|
3
|
+
"version": "1.5.3",
|
|
4
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)",
|
|
5
5
|
"main": "src/cli.js",
|
|
6
6
|
"bin": {
|
|
@@ -28,11 +28,11 @@ description: >
|
|
|
28
28
|
|
|
29
29
|
| Когда нужен | Какой скилл вызвать | Как |
|
|
30
30
|
|---|---|---|
|
|
31
|
-
| Задача сформулирована расплывчато | `explore` | `view /
|
|
32
|
-
| Нужна first-principles декомпозиция на шаги | `problem-solver-enhanced` | `view /
|
|
33
|
-
| Нужна верификация новинок каталога / источников | `goap-research-ed25519` | `view /
|
|
34
|
-
| Комплексный анализ с checkpoints | `analyst-manual-full` | `view /
|
|
35
|
-
| Финальный DOCX-отчёт | `docx` (public) | `view /mnt/skills/public/docx/SKILL.md` |
|
|
31
|
+
| Задача сформулирована расплывчато | `explore` | `view .claude/skills/explore/SKILL.md` |
|
|
32
|
+
| Нужна first-principles декомпозиция на шаги | `problem-solver-enhanced` | `view .claude/skills/problem-solver-enhanced/SKILL.md` |
|
|
33
|
+
| Нужна верификация новинок каталога / источников | `goap-research-ed25519` | `view .claude/skills/goap-research-ed25519/SKILL.md` |
|
|
34
|
+
| Комплексный анализ с checkpoints | `analyst-manual-full` | `view .claude/skills/analyst-manual-full/SKILL.md` |
|
|
35
|
+
| Финальный DOCX-отчёт | `docx` (public, host-provided) | `view /mnt/skills/public/docx/SKILL.md` |
|
|
36
36
|
|
|
37
37
|
**Правило:** сначала прочитай SKILL.md нужного скилла, потом следуй его инструкциям. Не переписывай его логику в этот SKILL.md.
|
|
38
38
|
|
|
@@ -109,7 +109,7 @@ ai-factory-mapper/
|
|
|
109
109
|
1. Есть ли у пользователя конкретный сценарий с описанием цели, пользователя, входа, выхода?
|
|
110
110
|
2. Или это общий запрос «как сделать X на AI Factory»?
|
|
111
111
|
|
|
112
|
-
Если второе — **прочитай
|
|
112
|
+
Если второе — **прочитай `.claude/skills/explore/SKILL.md` и следуй его инструкциям** для уточнения. Не пытайся угадать.
|
|
113
113
|
|
|
114
114
|
Если задача ясна (например, даётся список сценариев с описанием, как в примере ниже) — переходи к Phase 1.
|
|
115
115
|
|
|
@@ -125,7 +125,7 @@ ai-factory-mapper/
|
|
|
125
125
|
1. **ВСЕГДА** прочитай `references/catalog.md` — это базовый справочник, но он может устареть.
|
|
126
126
|
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.
|
|
127
127
|
3. Если пользователь явно указал «используй только актуальные данные» или работа критическая (enterprise-продукт, внешний клиент) — вызови `goap-research-ed25519`:
|
|
128
|
-
- Прочитай
|
|
128
|
+
- Прочитай `.claude/skills/goap-research-ed25519/SKILL.md`
|
|
129
129
|
- Цель: `goal_type="verified_exploratory"`, тема — «Cloud.ru Evolution AI Factory current services catalog»
|
|
130
130
|
4. Зафиксируй в working memory перечень сервисов на момент анализа (это важно для воспроизводимости оценок).
|
|
131
131
|
|
|
@@ -138,7 +138,7 @@ ai-factory-mapper/
|
|
|
138
138
|
|
|
139
139
|
**Для каждого сценария:**
|
|
140
140
|
|
|
141
|
-
1. Прочитай
|
|
141
|
+
1. Прочитай `.claude/skills/problem-solver-enhanced/SKILL.md` — это базовая методология декомпозиции. **Применяй модули 1 (First Principles) и 6 (Contradiction Analysis) как минимум.**
|
|
142
142
|
|
|
143
143
|
2. Открой `references/decomposition-checklist.md` и пройди по каждому из 10 пунктов:
|
|
144
144
|
- Ingest — откуда/в каком формате приходит вход
|
|
@@ -1,3 +1,13 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: edu-site-generator
|
|
3
|
+
description: >
|
|
4
|
+
Generate a complete gamified educational single-page app from documentation or content,
|
|
5
|
+
optimized for GitHub Pages deployment. Produces a learning site with modules, interactive
|
|
6
|
+
examples, and progress mechanics. Triggers on "generate edu site from [docs]", "create
|
|
7
|
+
learning site [topic]", "build educational app [topic]".
|
|
8
|
+
trust_tier: 1
|
|
9
|
+
---
|
|
10
|
+
|
|
1
11
|
# edu-site-generator — Gamified Educational Site Generator
|
|
2
12
|
|
|
3
13
|
<!-- Trust Tier: 1 — Structured | Path to Tier 2: Run /bto-test for self-evaluation -->
|
|
@@ -399,7 +399,7 @@ npx @dzhechkov/skills-feature-adr init --with-learning --knowledge-extractor
|
|
|
399
399
|
| Flag | Installs | Purpose |
|
|
400
400
|
|------|----------|---------|
|
|
401
401
|
| (none) | Core skill + command + rules + shard | Feature development pipeline |
|
|
402
|
-
| `--with-learning` | + `lib/memory-protocol.md`, `lib/reward-tracker.md`, `.claude/rules/reward-learning.md` |
|
|
402
|
+
| `--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. |
|
|
403
403
|
| `--knowledge-extractor` | + `.claude/skills/knowledge-extractor/`, `.claude/commands/harvest.md` | Extract reusable patterns after feature completion |
|
|
404
404
|
|
|
405
405
|
> **Note:** If `@dzhechkov/keysarium` is already installed, these flags are not needed — keysarium includes all learning and extraction capabilities.
|
|
@@ -57,12 +57,16 @@ Load `references/complexity-matrix.md` for the full matrix. Summary:
|
|
|
57
57
|
| 0 Complexity Router | ✓ | ✓ | ✓ | ✓ |
|
|
58
58
|
| 1 Requirements | ✓ light | ✓ | ✓ | ✓ |
|
|
59
59
|
| 2 Research | - | - | ✓ | ✓ |
|
|
60
|
-
| 3 ADR | - | ✓ (1 ADR) | ✓ (N ADRs) | ✓ (N ADRs) |
|
|
60
|
+
| 3 ADR + Shift-Left | - | ✓ (1 ADR) | ✓ (N ADRs) | ✓ (N ADRs) |
|
|
61
|
+
| 3.5 QCSD Ideation Swarm | - | ✓ | ✓ | ✓ |
|
|
61
62
|
| 4 DDD | - | - | ✓ | ✓ |
|
|
62
63
|
| 5 Architecture | - | ✓ light | ✓ | ✓ |
|
|
63
64
|
| 6 Implementation Plan | ✓ inline | ✓ | ✓ | ✓ |
|
|
64
65
|
| 7 Code | ✓ | ✓ | ✓ | ✓ |
|
|
65
|
-
| 8 QE | ✓ smoke | ✓ | ✓ | ✓ full |
|
|
66
|
+
| 8 QE + Brutal Honesty | ✓ smoke | ✓ | ✓ | ✓ full |
|
|
67
|
+
| 9 Fleet QE Assessment | - | - | ✓ | ✓ |
|
|
68
|
+
|
|
69
|
+
> Steps 3.5 (M+) and 9 (L/XL) are mandatory — skipping them is a BLOCK per the shard Anti-Patterns.
|
|
66
70
|
|
|
67
71
|
### 5. Calculate Time Budget
|
|
68
72
|
|
|
@@ -92,7 +96,7 @@ Create artifact: `features/<slug>/00_complexity_assessment.md`
|
|
|
92
96
|
|
|
93
97
|
```
|
|
94
98
|
═══════════════════════════════════════════════════════
|
|
95
|
-
⏸️ STEP 0
|
|
99
|
+
⏸️ STEP 0: Complexity Router Complete
|
|
96
100
|
<promise>FEATURE_ADR_ROUTED</promise>
|
|
97
101
|
Tier: {COMPLEXITY_TIER} | Active Steps: {ACTIVE_STEPS}
|
|
98
102
|
|
|
@@ -79,39 +79,44 @@ Skipped: 2, 3, 4, 5
|
|
|
79
79
|
### Tier M (Score 9-13)
|
|
80
80
|
|
|
81
81
|
```
|
|
82
|
-
Active: 0 → 1 → 3(1 ADR) → 5(light) → 6 → 7 → 8
|
|
83
|
-
Skipped: 2, 4
|
|
82
|
+
Active: 0 → 1 → 3(1 ADR) → 3.5 → 5(light) → 6 → 7 → 8
|
|
83
|
+
Skipped: 2, 4, 9
|
|
84
84
|
```
|
|
85
85
|
|
|
86
86
|
**Step adaptations:**
|
|
87
87
|
- Step 3: Single ADR for the main architectural decision
|
|
88
|
+
- Step 3.5: QCSD ideation swarm — 3 core agents + GO/CONDITIONAL/NO-GO verdict (mandatory for M+ — skipping is a BLOCK)
|
|
88
89
|
- Step 5: Component diagram only, no full C4
|
|
89
90
|
|
|
90
91
|
### Tier L (Score 14-19)
|
|
91
92
|
|
|
92
93
|
```
|
|
93
|
-
Active: 0 → 1 → [2 ‖ 3] → [4 ‖ 5] → 6 → 7 → 8
|
|
94
|
-
Parallel groups: (2,3) and (4,5)
|
|
94
|
+
Active: 0 → 1 → [2 ‖ 3] → 3.5 → [4 ‖ 5] → 6 → 7 → 8 → 9
|
|
95
|
+
Parallel groups: (2,3) and (4,5); Step 3.5 runs after Step 3, Step 9 after Step 8
|
|
95
96
|
```
|
|
96
97
|
|
|
97
98
|
**Step adaptations:**
|
|
98
99
|
- Step 2: Research analogues in codebase and external patterns
|
|
99
100
|
- Step 3: Multiple ADRs for each significant decision
|
|
101
|
+
- Step 3.5: QCSD ideation swarm — 3-9 parallel agents + GO/CONDITIONAL/NO-GO verdict (mandatory for M+ — skipping is a BLOCK)
|
|
100
102
|
- Step 4: Bounded contexts + ubiquitous language
|
|
101
103
|
- Step 5: Full C4 (Context + Container + Component)
|
|
102
104
|
- Step 8: Unit + integration tests + code review
|
|
105
|
+
- Step 9: Fleet QE assessment — 4 parallel agents (traceability ‖ risk ‖ integration ‖ regression) (mandatory for L/XL — skipping is a BLOCK)
|
|
103
106
|
|
|
104
107
|
### Tier XL (Score 20-24)
|
|
105
108
|
|
|
106
109
|
```
|
|
107
|
-
Active: 0 → 1 → [2 ‖ 3] → [4 ‖ 5] → 6 → 7(parallel) → 8(full)
|
|
108
|
-
Parallel groups: (2,3), (4,5), (7 per module)
|
|
110
|
+
Active: 0 → 1 → [2 ‖ 3] → 3.5 → [4 ‖ 5] → 6 → 7(parallel) → 8(full) → 9
|
|
111
|
+
Parallel groups: (2,3), (4,5 — after 3.5), (7 per module)
|
|
109
112
|
```
|
|
110
113
|
|
|
111
114
|
**Step adaptations:**
|
|
112
115
|
- All steps at full depth
|
|
116
|
+
- Step 3.5: QCSD ideation swarm — 3-9 parallel agents + GO/CONDITIONAL/NO-GO verdict (mandatory for M+ — skipping is a BLOCK)
|
|
113
117
|
- Step 7: Multiple parallel agents, one per module/domain
|
|
114
118
|
- Step 8: Full QE — unit + integration + e2e + performance + security review
|
|
119
|
+
- Step 9: Fleet QE assessment — 4 parallel agents (4-7 with `--full-qe-extended`) (mandatory for L/XL — skipping is a BLOCK)
|
|
115
120
|
|
|
116
121
|
---
|
|
117
122
|
|
|
@@ -36,8 +36,8 @@ presentation/
|
|
|
36
36
|
|
|
37
37
|
| Phase | Skill | Path | Purpose |
|
|
38
38
|
|-------|-------|------|---------|
|
|
39
|
-
| 1. Explore | `explore` |
|
|
40
|
-
| 2. Research | `goap-research-ed25519` |
|
|
39
|
+
| 1. Explore | `explore` | `.claude/skills/explore/SKILL.md` | Уточнение задачи |
|
|
40
|
+
| 2. Research | `goap-research-ed25519` | `.claude/skills/goap-research-ed25519/SKILL.md` | Верифицированные источники |
|
|
41
41
|
|
|
42
42
|
## Workflow Overview
|
|
43
43
|
|
|
@@ -72,7 +72,7 @@ presentation/
|
|
|
72
72
|
|
|
73
73
|
## Phase 1: Explore (Presentation Brief)
|
|
74
74
|
|
|
75
|
-
**Load:** `view("/
|
|
75
|
+
**Load:** `view(".claude/skills/explore/SKILL.md")`
|
|
76
76
|
|
|
77
77
|
**Key Questions for Presentations:**
|
|
78
78
|
|
|
@@ -104,7 +104,7 @@ presentation/
|
|
|
104
104
|
|
|
105
105
|
## Phase 2: Research (Verified Sources)
|
|
106
106
|
|
|
107
|
-
**Load:** `view("/
|
|
107
|
+
**Load:** `view(".claude/skills/goap-research-ed25519/SKILL.md")`
|
|
108
108
|
|
|
109
109
|
**Research Actions for Presentations:**
|
|
110
110
|
|
|
@@ -46,7 +46,7 @@ SKILL.md (this file — orchestrator)
|
|
|
46
46
|
| Skill | Modules | Purpose |
|
|
47
47
|
|-------|---------|---------|
|
|
48
48
|
| `explore` | Pre-flight | Clarify vague requests |
|
|
49
|
-
| `goap-research` | M1-M5 (DEEP) | Adaptive research: A* + OODA |
|
|
49
|
+
| `goap-research-ed25519` | M1-M5 (DEEP) | Adaptive research: A* + OODA |
|
|
50
50
|
| `goap-research-ed25519` | M1-M5 (VERIFIED) | + Ed25519 crypto verification |
|
|
51
51
|
| `problem-solver-enhanced` | M3,M4,M5 (DEEP) | Game Theory, TRIZ, 2nd-Order |
|
|
52
52
|
| `frontend-design` | M2.5 (DEEP) | Production-grade CJM prototype design |
|
|
@@ -186,12 +186,12 @@ After CHECKPOINT 6:
|
|
|
186
186
|
|
|
187
187
|
```
|
|
188
188
|
M0: explore
|
|
189
|
-
M1: goap-research
|
|
190
|
-
M2: goap-research + references/jtbd-canvas.md
|
|
189
|
+
M1: goap-research-ed25519
|
|
190
|
+
M2: goap-research-ed25519 + references/jtbd-canvas.md
|
|
191
191
|
M2.5: frontend-design + examples/noom-cjm-example.md (GENERATES new .jsx)
|
|
192
|
-
M3: goap-research + problem-solver-enhanced [GT, TRIZ, 2nd-Order]
|
|
193
|
-
M4: goap-research + problem-solver-enhanced [FP, TRIZ] + references/industry-benchmarks.md
|
|
194
|
-
M5: goap-research + problem-solver-enhanced [2nd-Order, TRIZ]
|
|
192
|
+
M3: goap-research-ed25519 + problem-solver-enhanced [GT, TRIZ, 2nd-Order]
|
|
193
|
+
M4: goap-research-ed25519 + problem-solver-enhanced [FP, TRIZ] + references/industry-benchmarks.md
|
|
194
|
+
M5: goap-research-ed25519 + problem-solver-enhanced [2nd-Order, TRIZ]
|
|
195
195
|
M6: brutal-honesty-review [Bach + Ramsay]
|
|
196
196
|
Post: presentation-storyteller / md2pptx / idea2prd-manual
|
|
197
197
|
```
|
|
@@ -38,7 +38,7 @@
|
|
|
38
38
|
|
|
39
39
|
### 🔵 Режим DEEP
|
|
40
40
|
|
|
41
|
-
> ⚙️ **Перед началом:** `view(/
|
|
41
|
+
> ⚙️ **Перед началом:** `view(.claude/skills/goap-research-ed25519/SKILL.md)`
|
|
42
42
|
> Примени GOAP-методологию вместо статического списка.
|
|
43
43
|
|
|
44
44
|
**Phase 1 — State Assessment:**
|
|
@@ -110,7 +110,7 @@ confidence = base_reliability × recency_factor
|
|
|
110
110
|
### 🟣 Режим VERIFIED (Ed25519)
|
|
111
111
|
|
|
112
112
|
> ⚙️ **Перед началом:**
|
|
113
|
-
> 1. `view(/
|
|
113
|
+
> 1. `view(.claude/skills/goap-research-ed25519/SKILL.md)`
|
|
114
114
|
> 2. Установи зависимости:
|
|
115
115
|
> ```bash
|
|
116
116
|
> pip install cryptography --break-system-packages
|
|
@@ -118,8 +118,8 @@ confidence = base_reliability × recency_factor
|
|
|
118
118
|
> 3. Запусти инициализацию:
|
|
119
119
|
> ```python
|
|
120
120
|
> # Скопируй и запусти скрипт из:
|
|
121
|
-
> # /
|
|
122
|
-
> # /
|
|
121
|
+
> # .claude/skills/goap-research-ed25519/scripts/ed25519_verifier.py
|
|
122
|
+
> # .claude/skills/goap-research-ed25519/scripts/goap_planner.py
|
|
123
123
|
> ```
|
|
124
124
|
|
|
125
125
|
**Всё из режима DEEP, плюс:**
|
|
@@ -278,7 +278,7 @@ Chain integrity: ✅ All N facts signed, 0 breaks
|
|
|
278
278
|
|
|
279
279
|
| Скилл | Режим | Как используется |
|
|
280
280
|
|-------|-------|-----------------|
|
|
281
|
-
| `goap-research` | DEEP | GOAP-методология: State → Actions → A* → OODA |
|
|
281
|
+
| `goap-research-ed25519` | DEEP | GOAP-методология: State → Actions → A* → OODA |
|
|
282
282
|
| `goap-research-ed25519` | VERIFIED | + Ed25519 подписи + citation chain + trusted issuers |
|
|
283
283
|
|
|
284
284
|
**Не используются в Module 1** (но релевантны позже):
|
|
@@ -320,7 +320,7 @@ Chain integrity: ✅ All N facts signed, 0 breaks
|
|
|
320
320
|
|---------|----|----|--------|
|
|
321
321
|
| Research protocol | Один режим, статический список | Три режима: QUICK/DEEP/VERIFIED | Адаптация под задачу |
|
|
322
322
|
| Confidence Score | X/5 ручной | Формула с base_reliability × recency × verification | Объективная метрика |
|
|
323
|
-
| External skills | Нет | goap-research
|
|
323
|
+
| External skills | Нет | goap-research-ed25519 | Reuse проверенных методологий |
|
|
324
324
|
| Output columns | 3 (Параметр, Значение, Источник) | 4 (+Confidence) | Прозрачность доверия к данным |
|
|
325
325
|
| Verification | "НЕ НАЙДЕНО" | + Verification Ledger, audit trail, chain integrity | Auditability |
|
|
326
326
|
| Checkpoint actions | 4 варианта | 6 вариантов (+переключение режима) | Гибкость mid-flight |
|
package/templates/.claude/skills/reverse-engineering-unicorn/modules/02-product-customers.md
CHANGED
|
@@ -37,7 +37,7 @@
|
|
|
37
37
|
### 🔵 Режим DEEP
|
|
38
38
|
|
|
39
39
|
> ⚙️ **Загрузи:**
|
|
40
|
-
> 1. `view(/
|
|
40
|
+
> 1. `view(.claude/skills/goap-research-ed25519/SKILL.md)` — адаптивный поиск отзывов
|
|
41
41
|
> 2. `view(references/jtbd-canvas.md)` — JTBD framework + примеры
|
|
42
42
|
|
|
43
43
|
**GOAP State Assessment:**
|
|
@@ -73,7 +73,7 @@ sample_size_factor: 1.0 (≥20 reviews), 0.8 (10-19), 0.5 (<10)
|
|
|
73
73
|
|
|
74
74
|
### 🟣 Режим VERIFIED
|
|
75
75
|
|
|
76
|
-
> ⚙️ **Дополнительно:** `view(/
|
|
76
|
+
> ⚙️ **Дополнительно:** `view(.claude/skills/goap-research-ed25519/SKILL.md)`
|
|
77
77
|
|
|
78
78
|
Всё из DEEP, плюс:
|
|
79
79
|
- 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)
|
|
|
194
194
|
|
|
195
195
|
| Скилл | Режим | Как используется |
|
|
196
196
|
|-------|-------|-----------------|
|
|
197
|
-
| `goap-research` | DEEP | Адаптивный поиск отзывов: A* по платформам + OODA при пустых results |
|
|
197
|
+
| `goap-research-ed25519` | DEEP | Адаптивный поиск отзывов: A* по платформам + OODA при пустых results |
|
|
198
198
|
| `goap-research-ed25519` | VERIFIED | + верификация существования цитат по URL |
|
|
199
199
|
| `references/jtbd-canvas.md` | ALL | Шаблон JTBD с примерами (Noom) |
|
|
200
200
|
|
|
@@ -99,7 +99,7 @@ why_now: [из M2 Section E — 4 фактора]
|
|
|
99
99
|
|
|
100
100
|
### Step 3: Generate React Prototype
|
|
101
101
|
|
|
102
|
-
> ⚙️ `view(/
|
|
102
|
+
> ⚙️ `view(.claude/skills/frontend-design/SKILL.md)` — для design quality
|
|
103
103
|
> ⚙️ `view(examples/noom-cjm-example.md)` — few-shot: структура .jsx
|
|
104
104
|
|
|
105
105
|
**Создай один .jsx файл** со следующей архитектурой:
|
package/templates/.claude/skills/reverse-engineering-unicorn/modules/03-market-competition.md
CHANGED
|
@@ -40,8 +40,8 @@
|
|
|
40
40
|
### 🔵 Режим DEEP
|
|
41
41
|
|
|
42
42
|
> ⚙️ **Загрузи перед началом:**
|
|
43
|
-
> 1. `view(/
|
|
44
|
-
> 2. `view(/
|
|
43
|
+
> 1. `view(.claude/skills/goap-research-ed25519/SKILL.md)` — для рыночного research
|
|
44
|
+
> 2. `view(.claude/skills/problem-solver-enhanced/SKILL.md)` — Modules 4, 5, 6 — для конкурентного анализа
|
|
45
45
|
|
|
46
46
|
#### PHASE A: GOAP Market Research
|
|
47
47
|
|
|
@@ -159,7 +159,7 @@ Incumbent │ (-2, +1) | (0, +2) │ Ценовая война
|
|
|
159
159
|
|
|
160
160
|
### 🟣 Режим VERIFIED (Ed25519)
|
|
161
161
|
|
|
162
|
-
> ⚙️ **Дополнительно:** `view(/
|
|
162
|
+
> ⚙️ **Дополнительно:** `view(.claude/skills/goap-research-ed25519/SKILL.md)`
|
|
163
163
|
|
|
164
164
|
Всё из режима DEEP, плюс:
|
|
165
165
|
|
|
@@ -348,7 +348,7 @@ Technical: "Хотим [A], но это ухудшает [B]"
|
|
|
348
348
|
|
|
349
349
|
| Скилл | Режим | Как используется | Какие модули скилла |
|
|
350
350
|
|-------|-------|-----------------|-------------------|
|
|
351
|
-
| `goap-research` | DEEP | Адаптивный market research: A* → OODA | Phases 1-4 |
|
|
351
|
+
| `goap-research-ed25519` | DEEP | Адаптивный market research: A* → OODA | Phases 1-4 |
|
|
352
352
|
| `goap-research-ed25519` | VERIFIED | + Ed25519 verification для TAM/SAM числ | Extended Phase 4 |
|
|
353
353
|
| `problem-solver-enhanced` | DEEP | **Module 4:** Game Theory — payoff matrix, Nash equilibrium | PS Module 4 |
|
|
354
354
|
| `problem-solver-enhanced` | DEEP | **Module 5:** Second-Order Thinking — competitive reactions | PS Module 5 |
|
|
@@ -41,8 +41,8 @@
|
|
|
41
41
|
### 🔵 Режим DEEP
|
|
42
42
|
|
|
43
43
|
> ⚙️ **Загрузи:**
|
|
44
|
-
> 1. `view(/
|
|
45
|
-
> 2. `view(/
|
|
44
|
+
> 1. `view(.claude/skills/goap-research-ed25519/SKILL.md)` — адаптивный research
|
|
45
|
+
> 2. `view(.claude/skills/problem-solver-enhanced/SKILL.md)` — Modules 1, 6
|
|
46
46
|
|
|
47
47
|
#### PHASE A: GOAP Financial Research
|
|
48
48
|
|
|
@@ -111,7 +111,7 @@ Physical: "Команда должна быть БОЛЬШОЙ (для скор
|
|
|
111
111
|
|
|
112
112
|
### 🟣 Режим VERIFIED
|
|
113
113
|
|
|
114
|
-
> ⚙️ **Дополнительно:** `view(/
|
|
114
|
+
> ⚙️ **Дополнительно:** `view(.claude/skills/goap-research-ed25519/SKILL.md)`
|
|
115
115
|
|
|
116
116
|
Всё из DEEP, плюс:
|
|
117
117
|
- Все benchmark числа подписываются с source_hash + issuer verification
|
|
@@ -258,7 +258,7 @@ Physical: "Команда должна быть БОЛЬШОЙ (для скор
|
|
|
258
258
|
|
|
259
259
|
| Скилл | Режим | Как используется |
|
|
260
260
|
|-------|-------|-----------------|
|
|
261
|
-
| `goap-research` | DEEP | Адаптивный поиск benchmarks + salary data |
|
|
261
|
+
| `goap-research-ed25519` | DEEP | Адаптивный поиск benchmarks + salary data |
|
|
262
262
|
| `goap-research-ed25519` | VERIFIED | Верификация финансовых чисел (threshold 0.95 strict) |
|
|
263
263
|
| `problem-solver-enhanced` M1 | DEEP | First Principles: деконструкция каждого допущения |
|
|
264
264
|
| `problem-solver-enhanced` M6 | DEEP | TRIZ: разрешение pricing / team / CAC противоречий |
|
|
@@ -39,8 +39,8 @@
|
|
|
39
39
|
### 🔵 Режим DEEP
|
|
40
40
|
|
|
41
41
|
> ⚙️ **Загрузи:**
|
|
42
|
-
> 1. `view(/
|
|
43
|
-
> 2. `view(/
|
|
42
|
+
> 1. `view(.claude/skills/goap-research-ed25519/SKILL.md)` — адаптивный research
|
|
43
|
+
> 2. `view(.claude/skills/problem-solver-enhanced/SKILL.md)` — Modules 5, 6
|
|
44
44
|
|
|
45
45
|
#### PHASE A: GOAP Growth Research
|
|
46
46
|
|
|
@@ -116,7 +116,7 @@ Physical: "Продукт должен быть ПРОСТЫМ (для onboardin
|
|
|
116
116
|
|
|
117
117
|
### 🟣 Режим VERIFIED
|
|
118
118
|
|
|
119
|
-
> ⚙️ **Дополнительно:** `view(/
|
|
119
|
+
> ⚙️ **Дополнительно:** `view(.claude/skills/goap-research-ed25519/SKILL.md)`
|
|
120
120
|
|
|
121
121
|
Всё из DEEP, плюс:
|
|
122
122
|
- Traffic estimates, follower counts подписываются
|
|
@@ -262,7 +262,7 @@ Step 5: [Flywheel / Data Moat] ──→ усиливает Step 2-3
|
|
|
262
262
|
|
|
263
263
|
| Скилл | Режим | Как используется |
|
|
264
264
|
|-------|-------|-----------------|
|
|
265
|
-
| `goap-research` | DEEP | Адаптивный поиск traffic data, marketing channels |
|
|
265
|
+
| `goap-research-ed25519` | DEEP | Адаптивный поиск traffic data, marketing channels |
|
|
266
266
|
| `goap-research-ed25519` | VERIFIED | Верификация traffic estimates, follower counts |
|
|
267
267
|
| `problem-solver-enhanced` M5 | DEEP | Second-Order Thinking: feedback loops, tipping points, competitive reactions |
|
|
268
268
|
| `problem-solver-enhanced` M6 | DEEP | TRIZ: moat engineering через разрешение growth contradictions |
|
package/templates/.claude/skills/reverse-engineering-unicorn/modules/06-playbook-synthesis.md
CHANGED
|
@@ -37,7 +37,7 @@
|
|
|
37
37
|
### 🔵 Режим DEEP
|
|
38
38
|
|
|
39
39
|
> ⚙️ **После формирования плана, загрузи:**
|
|
40
|
-
> `view(/
|
|
40
|
+
> `view(.claude/skills/brutal-honesty-review/SKILL.md)`
|
|
41
41
|
> Применяй **Bach Mode (BS-detection)** к финальному playbook.
|
|
42
42
|
|
|
43
43
|
#### BS-Detection Quality Gate
|
|
@@ -1,3 +1,13 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: transcript-site-generator
|
|
3
|
+
description: >
|
|
4
|
+
Generate a modern, interactive, mobile-friendly, SEO-optimized static website from a
|
|
5
|
+
transcript or YouTube video link, ready for GitHub Pages deployment with zero build step.
|
|
6
|
+
Triggers on "generate transcript site from [content]", "create interactive transcript
|
|
7
|
+
[topic]", "build transcript website from YouTube [url]".
|
|
8
|
+
trust_tier: 2
|
|
9
|
+
---
|
|
10
|
+
|
|
1
11
|
# transcript-site-generator — Interactive Transcript Site Generator
|
|
2
12
|
|
|
3
13
|
<!-- Trust Tier: 2 — Validated | BTO Layer 2 Score: 7.82/10 | Promoted: 2026-03-05 -->
|