@dzhechkov/harness-cli 0.3.39 → 0.3.40

package/README.md

@@ -24,9 +24,9 @@ npm install -g @dzhechkov/harness-cli    # install the CLI
 dz help                                   # see all commands
 dz pretrain                                # analyze project → auto-recommend skills/presets
 dz recommend "build API and deploy to K8s" # task advisor — decomposes your task into skills
-dz stats                                  # 28 packages, 72 skills, 5 targets, 10 presets
+dz stats                                  # 28 packages, 73 skills, 5 targets, 11 presets
 dz dashboard                              # visual panel — packages, adapters, skill packs
-dz registry                               # browse all 72 skills by category
+dz registry                               # browse all 73 skills by category
 dz registry search kubernetes             # find specific skills
 dz registry --category devops             # filter by domain
 dz downloads                              # npm weekly download stats
@@ -137,7 +137,7 @@ dz publish                                      # publish all changed packages
 
 | Preset | Skills | Description |
 |--------|--------|-------------|
-| `meta` | 3 | Development process (explore, feature-adr, knowledge-extractor) |
+| `meta` | 4 | Development process (explore, feature-adr, knowledge-extractor, design-thinking) |
 | `qe-engineer` | 8 | Quality engineering (test-gen, coverage, chaos, defect, ...) |
 | `bto` | 1 | Build-Benchmark-Test-Optimize pipeline |
 | `health` | 8 | Medical AI (diagnostics, drugs, labs, clinical decisions) |
@@ -353,7 +353,7 @@ Scans a GitHub repo for SKILL.md files, generates `dz create-skill` commands.
 ### dz registry — searchable skill index
 
 ```bash
-dz registry                    # visual panel: 72 skills in 5 categories
+dz registry                    # visual panel: 73 skills in 5 categories
 dz registry search security    # fuzzy search
 dz registry --category mcp     # filter by category
 ```
@@ -397,6 +397,55 @@ Recommended workflow: `document-checker` → `dissertation-review` → `question
 
 ---
 
+## Example: Product Discovery with Design Thinking
+
+```bash
+# Install design-thinking skill (part of meta preset)
+dz init --target claude-code --preset meta
+# Or individually:
+dz init --target claude-code --select design-thinking
+```
+
+Then in Claude Code:
+```
+"Design a mobile app for booking coworking spaces"
+→ design-thinking skill activates
+→ 6-phase protocol runs with complexity tier auto-selection
+```
+
+### 6-Phase Protocol
+
+```
+Phase 1: EMPATHIZE  → STOP gate: request user interview data + goap-research for market data
+Phase 2: DEFINE     → JTBD Canvas + CJM AS IS + Ishikawa root cause analysis
+Phase 3: IDEATE     → HADI hypotheses + Lean Canvas / Osterwalder BMC + GTM + Unit Economics
+Phase 4: PROTOTYPE  → MVP (fidelity spectrum) + CJM/VSM TO BE (labeled as hypotheses)
+Phase 5: TEST       → STOP gate: request usability test data + risk analysis + HADI validation
+Phase 6: VALIDATE   → Pilot with variance analysis: projected vs actual → Scale/Iterate/Pivot/Kill
+```
+
+### Complexity Tiers (auto-selected)
+
+| Tier | When | Phases | Integrations |
+|------|------|--------|-------------|
+| **S** | Quick user insight | 1→2→5 | explore + goap-research |
+| **M** | New feature | 1→2→3→4→5 | + frontend-design + six-thinking-hats |
+| **L** | New product | 1→2→3→4→5→6 | + qcsd-swarm + reverse-engineering-unicorn |
+| **XL** | Platform / ecosystem | All | + problem-solver (TRIZ) + analyst-manual |
+
+### Key Safeguards
+
+- **Never fabricates data** — STOP gates pause for real interview/survey/test data
+- **TO BE ≠ data** — projections labeled as hypotheses, validated via pilot (Phase 6)
+- **LTV/CAC > 10 flagged** as suspicious (Skok 2013)
+- **Loop-back protocol** — Phase 5 can invalidate Phase 2 and return upstream
+- **22 methodologies** with academic validation tiers (Strong/Moderate/Practitioner/Weak)
+- **12 validation rules** (DT-001 through DT-012) enforce quality per tier
+
+BTO benchmark: L0 Grade A (100%), L2 Opus weighted 7.58/10.
+
+---
+
 ## Self-Learning: JSONL vs AgentDB
 
 DZ Harness supports two memory backends for self-learning:
@@ -662,7 +711,7 @@ npx @dzhechkov/p-replicator init
 
 ## Status
 
-`v0.3.36` — published on npm. Also available as [Claude Plugin](#claude-plugin). Part of [DZ Harness Hub](https://github.com/djd1m/dz-harness-hub).
+`v0.3.40` — published on npm. Also available as [Claude Plugin](#claude-plugin). Part of [DZ Harness Hub](https://github.com/djd1m/dz-harness-hub).
 
 ## Claude Plugin
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dzhechkov/harness-cli",
-  "version": "0.3.39",
+  "version": "0.3.40",
   "description": "The dz CLI — install AI skills for Claude Code, Codex, OpenCode, Hermes. 11 commands, 7 presets, 4 platform adapters.",
   "type": "module",
   "license": "MIT",
@@ -37,10 +37,17 @@
     "src",
     "README.md"
   ],
+  "scripts": {
+    "build": "tsc -p tsconfig.json",
+    "test": "vitest run",
+    "test:watch": "vitest",
+    "typecheck": "tsc -p tsconfig.json --noEmit",
+    "lint": "tsc -p tsconfig.json --noEmit"
+  },
   "dependencies": {
-    "@dzhechkov/scout": "0.7.2",
-    "@dzhechkov/harness-core": "0.3.13",
-    "@dzhechkov/harness-presets": "0.2.10"
+    "@dzhechkov/harness-core": "workspace:*",
+    "@dzhechkov/harness-presets": "workspace:*",
+    "@dzhechkov/scout": "workspace:*"
   },
   "devDependencies": {
     "@types/node": "^25.6.0",
@@ -58,12 +65,5 @@
     "url": "https://github.com/djd1m/dz-harness-hub.git",
     "directory": "packages/@dzhechkov/harness-cli"
   },
-  "homepage": "https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/harness-cli#readme",
-  "scripts": {
-    "build": "tsc -p tsconfig.json",
-    "test": "vitest run",
-    "test:watch": "vitest",
-    "typecheck": "tsc -p tsconfig.json --noEmit",
-    "lint": "tsc -p tsconfig.json --noEmit"
-  }
-}
+  "homepage": "https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/harness-cli#readme"
+}