@dzhechkov/harness-cli 0.3.102 → 0.3.104
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 +8 -6
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -6,7 +6,7 @@ The **`dz`** CLI — the main entry point to the DZ Harness Hub. Install AI skil
|
|
|
6
6
|
|
|
7
7
|
> **`dz` is a package manager + cross-compiler for your AI agent harness.** Write a skill once in one canonical form; `dz` installs it into any agent's harness, holds it to a quality bar, and lets the harness learn over time.
|
|
8
8
|
|
|
9
|
-
**The problem.** You accumulate ~
|
|
9
|
+
**The problem.** You accumulate ~121 skills (design-thinking, QE, devops, web3, MCP, academic…). Five pains follow:
|
|
10
10
|
|
|
11
11
|
1. **Every agent wants a different layout.** Claude Code reads `.claude/skills/`, Codex `.codex/`, OpenCode/Hermes/OpenClaude their own. Hand-maintaining N copies is sync hell.
|
|
12
12
|
2. **Skills arrive from many upstream repos** — they must be *canonicalized* (brought to one form) and kept in sync without losing provenance.
|
|
@@ -58,9 +58,9 @@ dz help # see all commands
|
|
|
58
58
|
dz pretrain # analyze project files → recommend by tech stack
|
|
59
59
|
dz recommend "build API and deploy to K8s" # keyword match → skills + toolkits
|
|
60
60
|
dz recommend "work on this project" # generic? → auto-runs pretrain → recommends by stack
|
|
61
|
-
dz stats #
|
|
61
|
+
dz stats # 34 packages, 121 skills, 6 targets, 12 presets
|
|
62
62
|
dz dashboard # visual panel — packages, adapters, skill packs
|
|
63
|
-
dz registry # browse all
|
|
63
|
+
dz registry # browse all 121 skills by category
|
|
64
64
|
dz registry search kubernetes # find specific skills
|
|
65
65
|
dz registry --category devops # filter by domain
|
|
66
66
|
dz downloads # npm weekly download stats
|
|
@@ -102,6 +102,7 @@ dz info --id terraform # detailed info about a skill
|
|
|
102
102
|
# "Review this PR" → pr-review skill activates
|
|
103
103
|
# "Design an API" → api-design skill activates
|
|
104
104
|
# "Fix this CI" → ci-fix skill activates
|
|
105
|
+
# "Сделай AI-дайджест за февраль" → news-digest (cited report); "what's new since last week" → news-monitor (delta)
|
|
105
106
|
```
|
|
106
107
|
|
|
107
108
|
### Phase 4: Create (build your own skills)
|
|
@@ -186,7 +187,7 @@ npx @dzhechkov/keysarium init # 7-phase research + comman
|
|
|
186
187
|
- Need a **themed set** that works together → `--preset`
|
|
187
188
|
- Need a **full pipeline** with commands and governance → `npx`
|
|
188
189
|
|
|
189
|
-
### Available Presets (
|
|
190
|
+
### Available Presets (12)
|
|
190
191
|
|
|
191
192
|
| Preset | Skills | Description |
|
|
192
193
|
|--------|--------|-------------|
|
|
@@ -201,6 +202,7 @@ npx @dzhechkov/keysarium init # 7-phase research + comman
|
|
|
201
202
|
| `web3` | 12 | Web3/DeFi (quicknode, zerion, symbiosis, bankr, veil, neynar, ...) |
|
|
202
203
|
| `mcp` | 16 | MCP servers (agentdb, brave-search, gmail, gitlab, comfyui, notion, ...) |
|
|
203
204
|
| `academic` | 5 | Thesis defense (review, questions, doc-check, live defense + answer eval) |
|
|
205
|
+
| `news` | 2 | News & monitoring (news-digest cited reports + news-monitor delta watches) |
|
|
204
206
|
|
|
205
207
|
#### What the `meta` skills do & how to trigger them
|
|
206
208
|
|
|
@@ -321,7 +323,7 @@ dz scout --since 2026-05-01 # only recent repos
|
|
|
321
323
|
**Radar mode** (`dz scout`) scans **11 sources** in parallel (GitHub + npm + HN + MCP Registry + Glama + OSSInsight + Smithery + Semantic Scholar + arXiv + ECC + AgentBox):
|
|
322
324
|
1. **Detects skill format** — SKILL.md, plugin.json, .claude/skills/, .claude-plugin/, MCP manifests
|
|
323
325
|
2. **Scores relevance** — format (40%) + stars (30%) + recency (20%) + novelty (10%)
|
|
324
|
-
3. **Compares against our
|
|
326
|
+
3. **Compares against our 34 packages** — finds skills we don't have
|
|
325
327
|
4. **Recommends** — integrate (score ≥70) / monitor (40-69 + ≥50 stars) / skip
|
|
326
328
|
|
|
327
329
|
**Deep analyst mode** (`dz scout --deep`) goes further for top-scored repos:
|
|
@@ -462,7 +464,7 @@ Scans a GitHub repo for SKILL.md files, generates `dz create-skill` commands.
|
|
|
462
464
|
### dz registry — searchable skill index
|
|
463
465
|
|
|
464
466
|
```bash
|
|
465
|
-
dz registry # visual panel:
|
|
467
|
+
dz registry # visual panel: 121 skills in 8 categories
|
|
466
468
|
dz registry search security # fuzzy search
|
|
467
469
|
dz registry --category mcp # filter by category
|
|
468
470
|
```
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@dzhechkov/harness-cli",
|
|
3
|
-
"version": "0.3.
|
|
3
|
+
"version": "0.3.104",
|
|
4
4
|
"description": "The dz CLI — install AI skills for Claude Code, Codex, OpenCode, Hermes, OpenClaude, GitHub Copilot. 32 commands, 11 presets, 6 platform targets.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|
|
@@ -47,7 +47,7 @@
|
|
|
47
47
|
"@dzhechkov/skills-meta": "^0.9.0",
|
|
48
48
|
"@dzhechkov/skills-academic": "^0.3.0",
|
|
49
49
|
"@dzhechkov/skills-ecc": "^0.1.0",
|
|
50
|
-
"@dzhechkov/harness-core": "0.3.
|
|
50
|
+
"@dzhechkov/harness-core": "0.3.34"
|
|
51
51
|
},
|
|
52
52
|
"devDependencies": {
|
|
53
53
|
"@types/node": "^25.6.0",
|