@dzhechkov/harness-cli 0.3.87 → 0.3.88
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 +29 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -2,6 +2,34 @@
|
|
|
2
2
|
|
|
3
3
|
The **`dz`** CLI — the main entry point to the DZ Harness Hub. Install AI skills for **Claude Code, Codex, OpenCode, Hermes, OpenClaude** from a single command.
|
|
4
4
|
|
|
5
|
+
## Why dz?
|
|
6
|
+
|
|
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
|
+
|
|
9
|
+
**The problem.** You accumulate ~117 skills (design-thinking, QE, devops, web3, MCP, academic…). Five pains follow:
|
|
10
|
+
|
|
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
|
+
2. **Skills arrive from many upstream repos** — they must be *canonicalized* (brought to one form) and kept in sync without losing provenance.
|
|
13
|
+
3. **It's hard to know which skill** to reach for out of a hundred.
|
|
14
|
+
4. **Quality drifts** — there's no single bar.
|
|
15
|
+
5. **Experience doesn't accumulate** — the harness doesn't learn from feedback.
|
|
16
|
+
|
|
17
|
+
**The answer — one canon → many platforms.** There is a single source of truth (a `CanonicalSkill`); `dz` compiles it for each target — so the same skill drops into `.claude/skills/`, `.codex/`, etc. without hand-copying.
|
|
18
|
+
|
|
19
|
+
**Every command maps to one of five jobs:**
|
|
20
|
+
|
|
21
|
+
| Job | Commands | What it does |
|
|
22
|
+
|-----|----------|--------------|
|
|
23
|
+
| **Author / canonicalize** | `auto-canonicalize`, `sync-upstream`, `diff`, `create-skill` | pull a skill from any repo into one canonical form + keep it in sync with upstream |
|
|
24
|
+
| **Install / assemble** | `init`, `setup`, `install`, `compose`, presets, `upgrade` | deploy the right set of skills into a chosen agent harness (5 targets) |
|
|
25
|
+
| **Find / recommend** | `registry`, `scout`, `recommend`, `skill-advisor` | for a task, suggest which skill / preset / package to use |
|
|
26
|
+
| **Guarantee quality** | `benchmark` (L0 A–F), `verify`, `doctor` | one bar — 20 deterministic checks per skill |
|
|
27
|
+
| **Learn** | `teach`, `pretrain`, `roam` (reward-learning) | accumulate patterns, improve recommendations over time |
|
|
28
|
+
|
|
29
|
+
(+ ops: `publish`, `stats`, `downloads`, `dashboard`, `plugin`.)
|
|
30
|
+
|
|
31
|
+
**Analogy:** **npm** for distribution, a **compiler / Babel** for one source → many targets (adapters for 5 agents), and a **linter / CI** for a quality bar (`benchmark`) — but for AI agent skills, not ordinary code.
|
|
32
|
+
|
|
5
33
|
## Install
|
|
6
34
|
|
|
7
35
|
```bash
|
|
@@ -924,7 +952,7 @@ npx @dzhechkov/p-replicator init
|
|
|
924
952
|
|
|
925
953
|
## Status
|
|
926
954
|
|
|
927
|
-
`v0.3.
|
|
955
|
+
`v0.3.88` — published on npm. Also available as [Claude Plugin](#claude-plugin). Part of [DZ Harness Hub](https://github.com/djd1m/dz-harness-hub).
|
|
928
956
|
|
|
929
957
|
## Claude Plugin
|
|
930
958
|
|
package/package.json
CHANGED