@dzhechkov/harness-cli 0.3.114 → 0.3.116
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 +10 -8
- package/package.json +1 -1
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 ~125 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 # 37 packages, 125 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 125 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
|
|
@@ -191,7 +191,7 @@ npx @dzhechkov/keysarium init # 7-phase research + comman
|
|
|
191
191
|
- Need a **themed set** that works together → `--preset`
|
|
192
192
|
- Need a **full pipeline** with commands and governance → `npx`
|
|
193
193
|
|
|
194
|
-
### Skill Packs (
|
|
194
|
+
### Skill Packs (11 packs · 125 skills)
|
|
195
195
|
|
|
196
196
|
Each pack is an npm package — click through for the **full per-skill documentation** (what each skill does + how to trigger it). Install a whole pack with `dz install <pkg>`, or pick skills with `dz init --select` / a `--preset`.
|
|
197
197
|
|
|
@@ -206,6 +206,8 @@ Each pack is an npm package — click through for the **full per-skill documenta
|
|
|
206
206
|
| [@dzhechkov/skills-academic](https://www.npmjs.com/package/@dzhechkov/skills-academic) | 5 | Thesis-defense toolkit — dissertation review, questions, doc-check, defense eval |
|
|
207
207
|
| [@dzhechkov/skills-news](https://www.npmjs.com/package/@dzhechkov/skills-news) | 3 | *dz-original* — news digests (`news-digest`) + delta watches (`news-monitor`) + bundled `goap-research-ed25519` verified-research backend (mandatory) |
|
|
208
208
|
| [@dzhechkov/skills-idea2prd](https://www.npmjs.com/package/@dzhechkov/skills-idea2prd) | 1 | *dz-original* — `idea2prd-manual`: idea/problem → PRD+ADR+DDD+C4+Pseudocode+Tests+Completion (9 checkpoints); bundles the analyst trio as a sources.json-tracked vendor ([ADR-0001](https://github.com/djd1m/dz-harness-hub/blob/main/docs/adr/0001-skill-canonicalization-and-dependency-model.md)) |
|
|
209
|
+
| [@dzhechkov/skills-reverse-engineering](https://www.npmjs.com/package/@dzhechkov/skills-reverse-engineering) | 1 | *dz-original* — `reverse-engineering-unicorn`: company → launch playbook (+CJM) via 6-module QUICK/DEEP/VERIFIED pipeline; canonical home that resolved the keysarium↔p-replicator drift ([ADR-0001](https://github.com/djd1m/dz-harness-hub/blob/main/docs/adr/0001-skill-canonicalization-and-dependency-model.md)) |
|
|
210
|
+
| [@dzhechkov/skills-presentation-storyteller](https://www.npmjs.com/package/@dzhechkov/skills-presentation-storyteller) | 1 | *dz-original* — `presentation-storyteller`: selling deck + verified sources + slide-by-slide speaker script; referenced (not vendored) by reverse-engineering-unicorn's Post-M6 step ([ADR-0001](https://github.com/djd1m/dz-harness-hub/blob/main/docs/adr/0001-skill-canonicalization-and-dependency-model.md)) |
|
|
209
211
|
|
|
210
212
|
### Available Presets (12)
|
|
211
213
|
|
|
@@ -259,7 +261,7 @@ Get the whole set with `dz init --target claude-code --preset meta`, or pick one
|
|
|
259
261
|
|
|
260
262
|
> **A skill and its npx toolkit are not duplicates — they're a graduation.** Several skills (e.g. `feature-adr`, `design-thinking`) exist BOTH as a skill inside a `dz` preset AND as a standalone `npx` package. The preset's SKILL.md is **fully functional on its own** (the whole methodology — modules + references — travels with it, and it auto-activates by description), and it's the only way to compile that capability to the **non-Claude platforms** (Codex/OpenCode/Hermes/OpenClaude) via `dz`. The npx package adds **project-level runtime governance** around the same skill: a slash command, governance rules, a context shard, and (for feature-adr) reward-learning + `/harvest`. So: pick the **skill/preset** for a working capability across platforms; pick the **npx toolkit** when you want it as a governed, command-driven fixture of one project.
|
|
261
263
|
|
|
262
|
-
## All Commands (
|
|
264
|
+
## All Commands (35)
|
|
263
265
|
|
|
264
266
|
```
|
|
265
267
|
dz setup --target <name> [--preset <name>] [--select id,id,...] [--skills-dir <dir>] [--memory agentdb] [--no-memory] [--no-hooks] [--install-driver] [--force]
|
|
@@ -344,7 +346,7 @@ dz scout --since 2026-05-01 # only recent repos
|
|
|
344
346
|
**Radar mode** (`dz scout`) scans **11 sources** in parallel (GitHub + npm + HN + MCP Registry + Glama + OSSInsight + Smithery + Semantic Scholar + arXiv + ECC + AgentBox):
|
|
345
347
|
1. **Detects skill format** — SKILL.md, plugin.json, .claude/skills/, .claude-plugin/, MCP manifests
|
|
346
348
|
2. **Scores relevance** — format (40%) + stars (30%) + recency (20%) + novelty (10%)
|
|
347
|
-
3. **Compares against our
|
|
349
|
+
3. **Compares against our 37 packages** — finds skills we don't have
|
|
348
350
|
4. **Recommends** — integrate (score ≥70) / monitor (40-69 + ≥50 stars) / skip
|
|
349
351
|
|
|
350
352
|
**Deep analyst mode** (`dz scout --deep`) goes further for top-scored repos:
|
|
@@ -485,7 +487,7 @@ Scans a GitHub repo for SKILL.md files, generates `dz create-skill` commands.
|
|
|
485
487
|
### dz registry — searchable skill index
|
|
486
488
|
|
|
487
489
|
```bash
|
|
488
|
-
dz registry # visual panel:
|
|
490
|
+
dz registry # visual panel: 125 skills in 8 categories
|
|
489
491
|
dz registry search security # fuzzy search
|
|
490
492
|
dz registry --category mcp # filter by category
|
|
491
493
|
```
|
|
@@ -995,7 +997,7 @@ npx @dzhechkov/p-replicator init
|
|
|
995
997
|
|
|
996
998
|
## Status
|
|
997
999
|
|
|
998
|
-
`v0.3.
|
|
1000
|
+
`v0.3.116` — published on npm. Also available as [Claude Plugin](#claude-plugin). Part of [DZ Harness Hub](https://github.com/djd1m/dz-harness-hub).
|
|
999
1001
|
|
|
1000
1002
|
## Claude Plugin
|
|
1001
1003
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@dzhechkov/harness-cli",
|
|
3
|
-
"version": "0.3.
|
|
3
|
+
"version": "0.3.116",
|
|
4
4
|
"description": "The dz CLI — install AI skills for Claude Code, Codex, OpenCode, Hermes, OpenClaude, GitHub Copilot. 34 commands, 12 presets, 6 platform targets.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|