@dzhechkov/harness-cli 0.3.38 → 0.3.40

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.
Files changed (3) hide show
  1. package/README.md +64 -11
  2. package/dist/bin.js +0 -0
  3. package/package.json +13 -13
package/README.md CHANGED
@@ -24,9 +24,9 @@ npm install -g @dzhechkov/harness-cli # install the CLI
24
24
  dz help # see all commands
25
25
  dz pretrain # analyze project → auto-recommend skills/presets
26
26
  dz recommend "build API and deploy to K8s" # task advisor — decomposes your task into skills
27
- dz stats # 28 packages, 72 skills, 5 targets, 10 presets
27
+ dz stats # 28 packages, 73 skills, 5 targets, 11 presets
28
28
  dz dashboard # visual panel — packages, adapters, skill packs
29
- dz registry # browse all 72 skills by category
29
+ dz registry # browse all 73 skills by category
30
30
  dz registry search kubernetes # find specific skills
31
31
  dz registry --category devops # filter by domain
32
32
  dz downloads # npm weekly download stats
@@ -137,7 +137,7 @@ dz publish # publish all changed packages
137
137
 
138
138
  | Preset | Skills | Description |
139
139
  |--------|--------|-------------|
140
- | `meta` | 3 | Development process (explore, feature-adr, knowledge-extractor) |
140
+ | `meta` | 4 | Development process (explore, feature-adr, knowledge-extractor, design-thinking) |
141
141
  | `qe-engineer` | 8 | Quality engineering (test-gen, coverage, chaos, defect, ...) |
142
142
  | `bto` | 1 | Build-Benchmark-Test-Optimize pipeline |
143
143
  | `health` | 8 | Medical AI (diagnostics, drugs, labs, clinical decisions) |
@@ -147,7 +147,7 @@ dz publish # publish all changed packages
147
147
  | `devops` | 27 | DevOps skills (terraform, kubernetes, c4-architecture, risk-assessment, ...) |
148
148
  | `web3` | 12 | Web3/DeFi (quicknode, zerion, symbiosis, bankr, veil, neynar, ...) |
149
149
  | `mcp` | 16 | MCP servers (agentdb, brave-search, gmail, gitlab, comfyui, notion, ...) |
150
- | `academic` | 3 | Thesis defense (dissertation-review, question-generator, document-checker) |
150
+ | `academic` | 5 | Thesis defense (review, questions, doc-check, live defense + answer eval) |
151
151
 
152
152
  ### Standalone Packages (install via npx, no dz CLI needed)
153
153
 
@@ -353,7 +353,7 @@ Scans a GitHub repo for SKILL.md files, generates `dz create-skill` commands.
353
353
  ### dz registry — searchable skill index
354
354
 
355
355
  ```bash
356
- dz registry # visual panel: 72 skills in 5 categories
356
+ dz registry # visual panel: 73 skills in 5 categories
357
357
  dz registry search security # fuzzy search
358
358
  dz registry --category mcp # filter by category
359
359
  ```
@@ -383,13 +383,66 @@ Three skills auto-activate in Claude Code:
383
383
 
384
384
  | Skill | What it does |
385
385
  |-------|-------------|
386
- | `dissertation-review` | Evaluates thesis against ГЭК criteria (research/project format), generates summary with strengths, weaknesses, and preliminary grade |
387
- | `question-generator` | Generates 6 questions (basic methodological → practical → critical) with expected answer keywords and difficulty levels |
388
- | `document-checker` | Validates package completeness: thesis, supervisor review, external review, presentation, antiplagiat report |
386
+ | `document-checker` | Validates package completeness: thesis, supervisor review, external review, presentation |
387
+ | `dissertation-review` | Evaluates thesis against ГЭК criteria (research/project format), generates summary |
388
+ | `question-generator` | Generates 6 questions (basic critical) with expected answer keywords |
389
+ | `defense-evaluator` | Analyzes live defense transcript — structure, topic coverage, delivery quality |
390
+ | `answer-assessor` | Evaluates Q&A answers — completeness, depth, alignment with reviewer remarks |
389
391
 
390
- Skills contain **only evaluation criteria and methodology** from public guidelines no student data. Student materials are processed only at runtime when applying skills to specific files.
392
+ **Live defense support:** Feed real-time transcript from speech-to-text (e.g., Whisper + VB-Cable on Windows) defense-evaluator and answer-assessor analyze as the defense progresses.
391
393
 
392
- Recommended workflow: `document-checker` `dissertation-review` `question-generator`
394
+ Skills contain **only evaluation criteria and methodology** — no student data.
395
+
396
+ Recommended workflow: `document-checker` → `dissertation-review` → `question-generator` → `defense-evaluator` → `answer-assessor`
397
+
398
+ ---
399
+
400
+ ## Example: Product Discovery with Design Thinking
401
+
402
+ ```bash
403
+ # Install design-thinking skill (part of meta preset)
404
+ dz init --target claude-code --preset meta
405
+ # Or individually:
406
+ dz init --target claude-code --select design-thinking
407
+ ```
408
+
409
+ Then in Claude Code:
410
+ ```
411
+ "Design a mobile app for booking coworking spaces"
412
+ → design-thinking skill activates
413
+ → 6-phase protocol runs with complexity tier auto-selection
414
+ ```
415
+
416
+ ### 6-Phase Protocol
417
+
418
+ ```
419
+ Phase 1: EMPATHIZE → STOP gate: request user interview data + goap-research for market data
420
+ Phase 2: DEFINE → JTBD Canvas + CJM AS IS + Ishikawa root cause analysis
421
+ Phase 3: IDEATE → HADI hypotheses + Lean Canvas / Osterwalder BMC + GTM + Unit Economics
422
+ Phase 4: PROTOTYPE → MVP (fidelity spectrum) + CJM/VSM TO BE (labeled as hypotheses)
423
+ Phase 5: TEST → STOP gate: request usability test data + risk analysis + HADI validation
424
+ Phase 6: VALIDATE → Pilot with variance analysis: projected vs actual → Scale/Iterate/Pivot/Kill
425
+ ```
426
+
427
+ ### Complexity Tiers (auto-selected)
428
+
429
+ | Tier | When | Phases | Integrations |
430
+ |------|------|--------|-------------|
431
+ | **S** | Quick user insight | 1→2→5 | explore + goap-research |
432
+ | **M** | New feature | 1→2→3→4→5 | + frontend-design + six-thinking-hats |
433
+ | **L** | New product | 1→2→3→4→5→6 | + qcsd-swarm + reverse-engineering-unicorn |
434
+ | **XL** | Platform / ecosystem | All | + problem-solver (TRIZ) + analyst-manual |
435
+
436
+ ### Key Safeguards
437
+
438
+ - **Never fabricates data** — STOP gates pause for real interview/survey/test data
439
+ - **TO BE ≠ data** — projections labeled as hypotheses, validated via pilot (Phase 6)
440
+ - **LTV/CAC > 10 flagged** as suspicious (Skok 2013)
441
+ - **Loop-back protocol** — Phase 5 can invalidate Phase 2 and return upstream
442
+ - **22 methodologies** with academic validation tiers (Strong/Moderate/Practitioner/Weak)
443
+ - **12 validation rules** (DT-001 through DT-012) enforce quality per tier
444
+
445
+ BTO benchmark: L0 Grade A (100%), L2 Opus weighted 7.58/10.
393
446
 
394
447
  ---
395
448
 
@@ -658,7 +711,7 @@ npx @dzhechkov/p-replicator init
658
711
 
659
712
  ## Status
660
713
 
661
- `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).
714
+ `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).
662
715
 
663
716
  ## Claude Plugin
664
717
 
package/dist/bin.js CHANGED
File without changes
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@dzhechkov/harness-cli",
3
- "version": "0.3.38",
3
+ "version": "0.3.40",
4
4
  "description": "The dz CLI — install AI skills for Claude Code, Codex, OpenCode, Hermes. 11 commands, 7 presets, 4 platform adapters.",
5
5
  "type": "module",
6
6
  "license": "MIT",
@@ -37,10 +37,17 @@
37
37
  "src",
38
38
  "README.md"
39
39
  ],
40
+ "scripts": {
41
+ "build": "tsc -p tsconfig.json",
42
+ "test": "vitest run",
43
+ "test:watch": "vitest",
44
+ "typecheck": "tsc -p tsconfig.json --noEmit",
45
+ "lint": "tsc -p tsconfig.json --noEmit"
46
+ },
40
47
  "dependencies": {
41
- "@dzhechkov/harness-core": "0.3.13",
42
- "@dzhechkov/scout": "0.7.2",
43
- "@dzhechkov/harness-presets": "0.2.10"
48
+ "@dzhechkov/harness-core": "workspace:*",
49
+ "@dzhechkov/harness-presets": "workspace:*",
50
+ "@dzhechkov/scout": "workspace:*"
44
51
  },
45
52
  "devDependencies": {
46
53
  "@types/node": "^25.6.0",
@@ -58,12 +65,5 @@
58
65
  "url": "https://github.com/djd1m/dz-harness-hub.git",
59
66
  "directory": "packages/@dzhechkov/harness-cli"
60
67
  },
61
- "homepage": "https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/harness-cli#readme",
62
- "scripts": {
63
- "build": "tsc -p tsconfig.json",
64
- "test": "vitest run",
65
- "test:watch": "vitest",
66
- "typecheck": "tsc -p tsconfig.json --noEmit",
67
- "lint": "tsc -p tsconfig.json --noEmit"
68
- }
69
- }
68
+ "homepage": "https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/harness-cli#readme"
69
+ }