@dzhechkov/harness-cli 0.3.154 → 0.3.158
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 +38 -7
- 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 ~167 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.
|
|
@@ -95,6 +95,36 @@ dz verify && dz doctor # check health
|
|
|
95
95
|
Re-running is safe (existing files are skipped unless `--force`). Targets: `claude-code`, `codex`,
|
|
96
96
|
`opencode`, `hermes`, `openclaude`, `copilot`.
|
|
97
97
|
|
|
98
|
+
### Target coverage — which coder/agent maps to which `--target`
|
|
99
|
+
|
|
100
|
+
Don't see your tool below? Two fallbacks: if it reads `CLAUDE.md`/`.claude/` use `--target claude-code`;
|
|
101
|
+
otherwise `dz bundle --select <ids> --out <dir>` gives a portable tree of **raw `SKILL.md`** files you can
|
|
102
|
+
point any tool at (a skill is just Markdown). Dedicated targets are on the [roadmap](https://github.com/djd1m/dz-harness-hub/blob/main/docs/target-expansion-research.md).
|
|
103
|
+
|
|
104
|
+
**✅ Shipped native targets** (each compiles to the tool's own layout):
|
|
105
|
+
|
|
106
|
+
| Coder / agent | `--target` | Emits |
|
|
107
|
+
|---------------|-----------|-------|
|
|
108
|
+
| Claude Code | `claude-code` | `CLAUDE.md` + `.claude/skills/` |
|
|
109
|
+
| OpenAI Codex CLI | `codex` | `.agents/skills/` |
|
|
110
|
+
| OpenCode | `opencode` | `.opencode/skills/` |
|
|
111
|
+
| Hermes Agent | `hermes` | `.hermes/skills/` |
|
|
112
|
+
| OpenClaude *(incl. the "OpenClaw"/Claw-Code fork — it mirrors Claude Code)* | `openclaude` | `.openclaude/skills/` |
|
|
113
|
+
| GitHub Copilot | `copilot` | `.github/instructions/*.instructions` |
|
|
114
|
+
|
|
115
|
+
**🗺️ On the roadmap** (verified rules-formats — see the research doc):
|
|
116
|
+
|
|
117
|
+
| Coder(s) / agent | planned `--target` | reads | priority |
|
|
118
|
+
|------------------|--------------------|-------|----------|
|
|
119
|
+
| **~15 tools that read a root `AGENTS.md`** (Cursor, Zed, Warp, Aider, goose, Gemini CLI, RooCode, Kilo, Junie, Trae, Augment, Devin, **pi**, Windsurf…) | `agents-md` | root `AGENTS.md` (plain MD) | **#1** — one target, ~15 tools |
|
|
120
|
+
| Cursor | `cursor` | `.cursor/rules/*.mdc` | #2 |
|
|
121
|
+
| Gemini CLI / Code Assist | `gemini` | `GEMINI.md` | #3 |
|
|
122
|
+
| Windsurf | `windsurf` | `.windsurf/rules/*.md` *(→ `.devin/rules/` rebrand)* | #4 |
|
|
123
|
+
| Cline · Continue · Kiro | `cline` · `continue` · `kiro` | `.clinerules/` · `.continue/rules/` · `.kiro/steering/` | mid |
|
|
124
|
+
|
|
125
|
+
**❌ No target applies:** `nemoclaw` (NVIDIA agent-safety runtime — not a code editor, no rules file) ·
|
|
126
|
+
`v0` (UI-only, no repo file). *(`pi` is a real coder but reads `AGENTS.md` → covered by `agents-md`.)*
|
|
127
|
+
|
|
98
128
|
> **"Nothing installs" / "no skills found"?** Update the CLI:
|
|
99
129
|
> `cd /tmp && npm i -g @dzhechkov/harness-cli@latest`. Older global installs couldn't locate their
|
|
100
130
|
> own bundled packs outside the monorepo — now fixed, so `dz registry`/`dz init`/`dz setup` work
|
|
@@ -117,9 +147,9 @@ dz help # see all commands
|
|
|
117
147
|
dz pretrain # analyze project files → recommend by tech stack
|
|
118
148
|
dz recommend "build API and deploy to K8s" # keyword match → skills + toolkits
|
|
119
149
|
dz recommend "work on this project" # generic? → auto-runs pretrain → recommends by stack
|
|
120
|
-
dz stats #
|
|
150
|
+
dz stats # 42 packages, 167 skills, 6 targets, 13 presets
|
|
121
151
|
dz dashboard # visual panel — packages, adapters, skill packs
|
|
122
|
-
dz registry # browse all
|
|
152
|
+
dz registry # browse all 167 skills by category
|
|
123
153
|
dz registry search kubernetes # find specific skills
|
|
124
154
|
dz registry --category devops # filter by domain
|
|
125
155
|
dz downloads # npm weekly download stats
|
|
@@ -250,7 +280,7 @@ npx @dzhechkov/keysarium init # 7-phase research + comman
|
|
|
250
280
|
- Need a **themed set** that works together → `--preset`
|
|
251
281
|
- Need a **full pipeline** with commands and governance → `npx`
|
|
252
282
|
|
|
253
|
-
### Skill Packs (
|
|
283
|
+
### Skill Packs (16 packs · 167 skills)
|
|
254
284
|
|
|
255
285
|
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`.
|
|
256
286
|
|
|
@@ -271,6 +301,7 @@ Each pack is an npm package — click through for the **full per-skill documenta
|
|
|
271
301
|
| [@dzhechkov/skills-pm](https://www.npmjs.com/package/@dzhechkov/skills-pm) | 18 | *imported (MIT)* — product-management toolkit: OST, RICE/ICE prioritization, product-strategy, pricing, OKRs, NSM/metrics/A-B/cohort, outcome-roadmap, stakeholder-map, sprint-plan, strategy-red-team, GTM/growth/beachhead, market-sizing; curated from phuryn/pm-skills (`dz init --preset pm`) ([ADR-0002](https://github.com/djd1m/dz-harness-hub/blob/main/docs/adr/0002-product-and-design-expansion.md)) |
|
|
272
302
|
| [@dzhechkov/skills-taste](https://www.npmjs.com/package/@dzhechkov/skills-taste) | 1 | *imported (MIT)* — `design-taste-frontend`: anti-slop landing/portfolio/redesign framework (dials + pre-flight + GSAP skeletons); complements frontend-design (`dz init --select design-taste-frontend`) ([ADR-0002](https://github.com/djd1m/dz-harness-hub/blob/main/docs/adr/0002-product-and-design-expansion.md)) |
|
|
273
303
|
| [@dzhechkov/skills-book-digitizer](https://www.npmjs.com/package/@dzhechkov/skills-book-digitizer) | 8 | *dz-original* — book → installable methodology pack: `digitize-book` (orchestrator) + ingest/extract/distill/pack/kb-index + `book-brain-register` (CP6 promote → cross-project brain) + `source-brain-ingest` (repo sibling). Verified provenance, IP-safe, resumable (`dz init --select digitize-book`) ([ADR-001](https://github.com/djd1m/dz-harness-hub/blob/main/features/book-knowledge-digitizer/03_adr/001-book-to-skillpack-pipeline.md)) |
|
|
304
|
+
| [@dzhechkov/skills-12factor](https://www.npmjs.com/package/@dzhechkov/skills-12factor) | 12 | *generated by the digitizer, CC BY 4.0* — The Twelve-Factor App distilled into 12 decision-moment skills (one per factor). The first PUBLIC digitized-book pack; paraphrased (shingling-gated), routing-gated 100%/0%, attributed (`NOTICE`) (`dz init --select 12factor-config-in-environment,…`) |
|
|
274
305
|
|
|
275
306
|
### Available Presets (13)
|
|
276
307
|
|
|
@@ -419,7 +450,7 @@ dz scout --since 2026-05-01 # only recent repos
|
|
|
419
450
|
**Radar mode** (`dz scout`) scans **11 sources** in parallel (GitHub + npm + HN + MCP Registry + Glama + OSSInsight + Smithery + Semantic Scholar + arXiv + ECC + AgentBox):
|
|
420
451
|
1. **Detects skill format** — SKILL.md, plugin.json, .claude/skills/, .claude-plugin/, MCP manifests
|
|
421
452
|
2. **Scores relevance** — format (40%) + stars (30%) + recency (20%) + novelty (10%)
|
|
422
|
-
3. **Compares against our
|
|
453
|
+
3. **Compares against our 42 packages** — finds skills we don't have
|
|
423
454
|
4. **Recommends** — integrate (score ≥70) / monitor (40-69 + ≥50 stars) / skip
|
|
424
455
|
|
|
425
456
|
**Deep analyst mode** (`dz scout --deep`) goes further for top-scored repos:
|
|
@@ -510,7 +541,7 @@ Compares installed skills with canonical source, reports which need `dz init --f
|
|
|
510
541
|
### dz downloads — npm weekly download stats
|
|
511
542
|
|
|
512
543
|
```bash
|
|
513
|
-
dz downloads # fetch weekly downloads for all
|
|
544
|
+
dz downloads # fetch weekly downloads for all 42 packages
|
|
514
545
|
```
|
|
515
546
|
|
|
516
547
|
### dz benchmark — L0 quality gate
|
|
@@ -560,7 +591,7 @@ Scans a GitHub repo for SKILL.md files, generates `dz create-skill` commands.
|
|
|
560
591
|
### dz registry — searchable skill index
|
|
561
592
|
|
|
562
593
|
```bash
|
|
563
|
-
dz registry # visual panel:
|
|
594
|
+
dz registry # visual panel: 167 skills in 11 categories
|
|
564
595
|
dz registry search security # fuzzy search
|
|
565
596
|
dz registry --category mcp # filter by category
|
|
566
597
|
```
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@dzhechkov/harness-cli",
|
|
3
|
-
"version": "0.3.
|
|
3
|
+
"version": "0.3.158",
|
|
4
4
|
"description": "The dz CLI — install AI skills for Claude Code, Codex, OpenCode, Hermes, OpenClaude, GitHub Copilot. 35 commands, 13 presets, 6 platform targets.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|