@dzhechkov/harness-cli 0.3.225 → 0.3.226
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 +9 -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 ~179 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.
|
|
@@ -147,9 +147,9 @@ dz help # see all commands
|
|
|
147
147
|
dz pretrain # analyze project files → recommend by tech stack
|
|
148
148
|
dz recommend "build API and deploy to K8s" # keyword match → skills + toolkits
|
|
149
149
|
dz recommend "work on this project" # generic? → auto-runs pretrain → recommends by stack
|
|
150
|
-
dz stats #
|
|
150
|
+
dz stats # 46 packages, 179 skills, 10 targets, 14 presets
|
|
151
151
|
dz dashboard # visual panel — packages, adapters, skill packs
|
|
152
|
-
dz registry # browse all
|
|
152
|
+
dz registry # browse all 179 skills by category
|
|
153
153
|
dz registry search kubernetes # find specific skills
|
|
154
154
|
dz registry --category devops # filter by domain
|
|
155
155
|
dz downloads # npm weekly download stats
|
|
@@ -355,7 +355,7 @@ the release job gets a perfectly attested malicious package.
|
|
|
355
355
|
A ready-to-install workflow is at `features/publish-provenance/07_code_changes/publish.yml`; copy it to
|
|
356
356
|
`.github/workflows/` and add an `NPM_TOKEN` secret.
|
|
357
357
|
|
|
358
|
-
### Skill Packs (
|
|
358
|
+
### Skill Packs (23 packs · 179 skills)
|
|
359
359
|
|
|
360
360
|
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`.
|
|
361
361
|
|
|
@@ -365,6 +365,7 @@ Each pack is an npm package — click through for the **full per-skill documenta
|
|
|
365
365
|
| [@dzhechkov/skills-mcp](https://www.npmjs.com/package/@dzhechkov/skills-mcp) | 16 | MCP-server integrations — search, git/GitLab, Google Workspace, Notion, AgentDB memory |
|
|
366
366
|
| [@dzhechkov/skills-web3](https://www.npmjs.com/package/@dzhechkov/skills-web3) | 12 | On-chain / DeFi — wallets, swaps, bridges, ENS, agent identity (ERC-8004) |
|
|
367
367
|
| [@dzhechkov/skills-qe](https://www.npmjs.com/package/@dzhechkov/skills-qe) | 20 | Quality engineering — test-gen, coverage, chaos, defect intelligence, QCSD swarms |
|
|
368
|
+
| [@dzhechkov/skills-reasoning](https://www.npmjs.com/package/@dzhechkov/skills-reasoning) | 4 | Generic reasoning & code-quality — investigate (root-cause), solid (SOLID/TDD), karpathy-guidelines, agents-md-creator |
|
|
368
369
|
| [@dzhechkov/skills-ecc](https://www.npmjs.com/package/@dzhechkov/skills-ecc) | 20 | Claude-Code engineering craft — agent architecture, autonomous loops, framework patterns |
|
|
369
370
|
| [@dzhechkov/skills-meta](https://www.npmjs.com/package/@dzhechkov/skills-meta) | 18 | Dev-process meta skills — explore, feature-adr, design-thinking, audit, skill-advisor |
|
|
370
371
|
| [@dzhechkov/skills-academic](https://www.npmjs.com/package/@dzhechkov/skills-academic) | 5 | Thesis-defense toolkit — dissertation review, questions, doc-check, defense eval |
|
|
@@ -389,6 +390,7 @@ Each pack is an npm package — click through for the **full per-skill documenta
|
|
|
389
390
|
| `keysarium` | 9 | Full research toolkit (feature-adr, presentation, reverse-eng) |
|
|
390
391
|
| `p-replicator` | 10 | AI product development (/replicate, SPARC PRD, pipeline-forge) |
|
|
391
392
|
| `feature-adr` | 5 | Feature pipeline (feature-adr, explore, frontend-design) |
|
|
393
|
+
| `reasoning` | 4 | Generic reasoning & code-quality (investigate, solid, karpathy-guidelines, agents-md-creator) — stack-neutral, zero coupling |
|
|
392
394
|
| `devops` | 30 | DevOps skills (terraform, kubernetes, c4-architecture, incident-response, problem-management, risk-assessment, ...) |
|
|
393
395
|
| `web3` | 12 | Web3/DeFi (quicknode, zerion, symbiosis, bankr, veil, neynar, ...) |
|
|
394
396
|
| `mcp` | 16 | MCP servers (agentdb, brave-search, gmail, gitlab, comfyui, notion, ...) |
|
|
@@ -810,7 +812,7 @@ dz scout --since 2026-05-01 # only recent repos
|
|
|
810
812
|
**Radar mode** (`dz scout`) scans **11 sources** in parallel (GitHub + npm + HN + MCP Registry + Glama + OSSInsight + Smithery + Semantic Scholar + arXiv + ECC + AgentBox):
|
|
811
813
|
1. **Detects skill format** — SKILL.md, plugin.json, .claude/skills/, .claude-plugin/, MCP manifests
|
|
812
814
|
2. **Scores relevance** — format (40%) + stars (30%) + recency (20%) + novelty (10%)
|
|
813
|
-
3. **Compares against our
|
|
815
|
+
3. **Compares against our 46 packages** — finds skills we don't have
|
|
814
816
|
4. **Recommends** — integrate (score ≥70) / monitor (40-69 + ≥50 stars) / skip
|
|
815
817
|
|
|
816
818
|
**Deep analyst mode** (`dz scout --deep`) goes further for top-scored repos:
|
|
@@ -932,7 +934,7 @@ Compares installed skills with canonical source, reports which need `dz init --f
|
|
|
932
934
|
### dz downloads — npm weekly download stats
|
|
933
935
|
|
|
934
936
|
```bash
|
|
935
|
-
dz downloads # fetch weekly downloads for all
|
|
937
|
+
dz downloads # fetch weekly downloads for all 46 packages
|
|
936
938
|
```
|
|
937
939
|
|
|
938
940
|
### dz benchmark — L0 quality gate
|
|
@@ -982,7 +984,7 @@ Scans a GitHub repo for SKILL.md files, generates `dz create-skill` commands.
|
|
|
982
984
|
### dz registry — searchable skill index
|
|
983
985
|
|
|
984
986
|
```bash
|
|
985
|
-
dz registry # visual panel:
|
|
987
|
+
dz registry # visual panel: 179 skills in 11 categories
|
|
986
988
|
dz registry search security # fuzzy search
|
|
987
989
|
dz registry --category mcp # filter by category
|
|
988
990
|
```
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@dzhechkov/harness-cli",
|
|
3
|
-
"version": "0.3.
|
|
3
|
+
"version": "0.3.226",
|
|
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",
|