@dzhechkov/harness-cli 0.3.39 → 0.3.41
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/README.md +58 -5
- package/dist/bin.js +0 -0
- 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,
|
|
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
|
|
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` |
|
|
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) |
|
|
@@ -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:
|
|
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
|
```
|
|
@@ -397,6 +397,59 @@ Recommended workflow: `document-checker` → `dissertation-review` → `question
|
|
|
397
397
|
|
|
398
398
|
---
|
|
399
399
|
|
|
400
|
+
## Example: Product Discovery with Design Thinking
|
|
401
|
+
|
|
402
|
+
```bash
|
|
403
|
+
# With self-learning (recommended — remembers HADI patterns, JTBD insights across sessions):
|
|
404
|
+
dz setup --target claude-code --preset meta
|
|
405
|
+
dz setup --target claude-code --preset meta --memory agentdb # + semantic search
|
|
406
|
+
|
|
407
|
+
# Or without self-learning:
|
|
408
|
+
dz init --target claude-code --preset meta
|
|
409
|
+
# Or individually:
|
|
410
|
+
dz setup --target claude-code --select design-thinking
|
|
411
|
+
```
|
|
412
|
+
|
|
413
|
+
Then in Claude Code:
|
|
414
|
+
```
|
|
415
|
+
"Design a mobile app for booking coworking spaces"
|
|
416
|
+
→ design-thinking skill activates
|
|
417
|
+
→ 6-phase protocol runs with complexity tier auto-selection
|
|
418
|
+
```
|
|
419
|
+
|
|
420
|
+
### 6-Phase Protocol
|
|
421
|
+
|
|
422
|
+
```
|
|
423
|
+
Phase 1: EMPATHIZE → STOP gate: request user interview data + goap-research for market data
|
|
424
|
+
Phase 2: DEFINE → JTBD Canvas + CJM AS IS + Ishikawa root cause analysis
|
|
425
|
+
Phase 3: IDEATE → HADI hypotheses + Lean Canvas / Osterwalder BMC + GTM + Unit Economics
|
|
426
|
+
Phase 4: PROTOTYPE → MVP (fidelity spectrum) + CJM/VSM TO BE (labeled as hypotheses)
|
|
427
|
+
Phase 5: TEST → STOP gate: request usability test data + risk analysis + HADI validation
|
|
428
|
+
Phase 6: VALIDATE → Pilot with variance analysis: projected vs actual → Scale/Iterate/Pivot/Kill
|
|
429
|
+
```
|
|
430
|
+
|
|
431
|
+
### Complexity Tiers (auto-selected)
|
|
432
|
+
|
|
433
|
+
| Tier | When | Phases | Integrations |
|
|
434
|
+
|------|------|--------|-------------|
|
|
435
|
+
| **S** | Quick user insight | 1→2→5 | explore + goap-research |
|
|
436
|
+
| **M** | New feature | 1→2→3→4→5 | + frontend-design + six-thinking-hats |
|
|
437
|
+
| **L** | New product | 1→2→3→4→5→6 | + qcsd-swarm + reverse-engineering-unicorn |
|
|
438
|
+
| **XL** | Platform / ecosystem | All | + problem-solver (TRIZ) + analyst-manual |
|
|
439
|
+
|
|
440
|
+
### Key Safeguards
|
|
441
|
+
|
|
442
|
+
- **Never fabricates data** — STOP gates pause for real interview/survey/test data
|
|
443
|
+
- **TO BE ≠ data** — projections labeled as hypotheses, validated via pilot (Phase 6)
|
|
444
|
+
- **LTV/CAC > 10 flagged** as suspicious (Skok 2013)
|
|
445
|
+
- **Loop-back protocol** — Phase 5 can invalidate Phase 2 and return upstream
|
|
446
|
+
- **22 methodologies** with academic validation tiers (Strong/Moderate/Practitioner/Weak)
|
|
447
|
+
- **12 validation rules** (DT-001 through DT-012) enforce quality per tier
|
|
448
|
+
|
|
449
|
+
BTO benchmark: L0 Grade A (100%), L2 Opus weighted 7.58/10.
|
|
450
|
+
|
|
451
|
+
---
|
|
452
|
+
|
|
400
453
|
## Self-Learning: JSONL vs AgentDB
|
|
401
454
|
|
|
402
455
|
DZ Harness supports two memory backends for self-learning:
|
|
@@ -662,7 +715,7 @@ npx @dzhechkov/p-replicator init
|
|
|
662
715
|
|
|
663
716
|
## Status
|
|
664
717
|
|
|
665
|
-
`v0.3.
|
|
718
|
+
`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).
|
|
666
719
|
|
|
667
720
|
## Claude Plugin
|
|
668
721
|
|
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.
|
|
3
|
+
"version": "0.3.41",
|
|
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/
|
|
42
|
-
"@dzhechkov/harness-
|
|
43
|
-
"@dzhechkov/
|
|
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
|
-
|
|
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
|
+
}
|