@dzhechkov/harness-cli 0.3.94 → 0.3.96

package/README.md

@@ -175,7 +175,7 @@ dz publish                                      # publish all changed packages
 dz init --target claude-code --select design-thinking
 
 # Curated set by topic (recommended):
-dz setup --target claude-code --preset meta          # 16 development skills + self-learning
+dz setup --target claude-code --preset meta          # 17 development skills + self-learning
 
 # Full toolkit with orchestrated pipeline:
 npx @dzhechkov/keysarium init                        # 7-phase research + commands + memory
@@ -190,7 +190,7 @@ npx @dzhechkov/keysarium init                        # 7-phase research + comman
 
 | Preset | Skills | Description |
 |--------|--------|-------------|
-| `meta` | 16 | Development process (explore, goap-research, problem-solver, design-thinking, feature-adr, knowledge-extractor, understand-anything-bridge, agentshield-scan, adversarial-verifier, skill-advisor) |
+| `meta` | 17 | Development process (explore, goap-research, problem-solver, design-thinking, feature-adr, knowledge-extractor, understand-anything-bridge, agentshield-scan, adversarial-verifier, skill-advisor, audit) |
 | `qe-engineer` | 20 | Quality engineering (test-gen, coverage, chaos, defect, ...) |
 | `bto` | 1 | Build-Benchmark-Test-Optimize pipeline |
 | `health` | 8 | Medical AI (diagnostics, drugs, labs, clinical decisions) |
@@ -221,7 +221,7 @@ npx @dzhechkov/keysarium init                        # 7-phase research + comman
 
 > **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.
 
-## All Commands (32)
+## All Commands (34)
 
 ```
 dz setup             --target <name> [--preset <name>] [--memory agentdb] [--no-hooks] [--install-driver] [--force]
@@ -260,9 +260,9 @@ dz import-ecc       [--local-path <dir>] [--select id,id,...] [--limit N] [--out
 dz help
 ```
 
-### Targets (5 platforms)
+### Targets (6 platforms — 5 lossless + GitHub Copilot)
 
-All 5 platforms natively support the [agentskills.io](https://agentskills.io) `SKILL.md` format:
+Five platforms natively support the [agentskills.io](https://agentskills.io) `SKILL.md` format:
 
 | Target | Skills directory | Native SKILL.md? |
 |--------|-----------------|:---:|
@@ -274,6 +274,8 @@ All 5 platforms natively support the [agentskills.io](https://agentskills.io) `S
 
 Same SKILL.md file, different directory — no format conversion needed.
 
+The **6th target — `copilot`** (GitHub Copilot) — is an intentionally *lossy* adapter that emits `.github/instructions/<id>.instructions.md` instead of a skills tree.
+
 **Optional platform enrichment** (skills work without these):
 
 | Platform | Optional extra | What it adds |
@@ -303,7 +305,7 @@ dz scout --since 2026-05-01           # only recent repos
 **Radar mode** (`dz scout`) scans **11 sources** in parallel (GitHub + npm + HN + MCP Registry + Glama + OSSInsight + Smithery + Semantic Scholar + arXiv + ECC + AgentBox):
 1. **Detects skill format** — SKILL.md, plugin.json, .claude/skills/, .claude-plugin/, MCP manifests
 2. **Scores relevance** — format (40%) + stars (30%) + recency (20%) + novelty (10%)
-3. **Compares against our 32 packages** — finds skills we don't have
+3. **Compares against our 33 packages** — finds skills we don't have
 4. **Recommends** — integrate (score ≥70) / monitor (40-69 + ≥50 stars) / skip
 
 **Deep analyst mode** (`dz scout --deep`) goes further for top-scored repos:
@@ -566,13 +568,13 @@ Phase 6: VALIDATE   → Pilot with variance analysis: projected vs actual → Sc
 
 ### What's included vs what's optional
 
-**Core DT** — the `meta` preset includes all required dependencies (16 skills):
+**Core DT** — the `meta` preset includes all required dependencies (17 skills):
 
 ```bash
 dz setup --target claude-code --preset meta
 # → explore, goap-research-ed25519, problem-solver-enhanced,
 #   design-thinking, feature-adr, knowledge-extractor,
-#   understand-anything-bridge, ... (15 total)
+#   understand-anything-bridge, ... (17 total)
 ```
 
 **Full DT** — for ALL optional integrations, install [agentic-qe](https://github.com/proffesor-for-testing/agentic-qe):
@@ -633,7 +635,7 @@ dz pretrain                                     # detects stack, recommends pres
 dz recommend "work on this Node.js API"         # suggests skills + toolkits
 
 # 2. Install skills (choose your level)
-dz setup --target claude-code --preset meta --memory agentdb  # 16 skills (includes feature-adr)
+dz setup --target claude-code --preset meta --memory agentdb  # 17 skills (includes feature-adr)
 dz setup --target claude-code --preset qe-engineer             # + 20 QE skills
 
 # Want the full feature-adr toolkit with /feature-adr command + governance?
@@ -954,7 +956,7 @@ npx @dzhechkov/p-replicator init
 
 ## Status
 
-`v0.3.93` — published on npm. Also available as [Claude Plugin](#claude-plugin). Part of [DZ Harness Hub](https://github.com/djd1m/dz-harness-hub).
+`v0.3.95` — published on npm. Also available as [Claude Plugin](#claude-plugin). Part of [DZ Harness Hub](https://github.com/djd1m/dz-harness-hub).
 
 ## Claude Plugin
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dzhechkov/harness-cli",
-  "version": "0.3.94",
+  "version": "0.3.96",
   "description": "The dz CLI — install AI skills for Claude Code, Codex, OpenCode, Hermes, OpenClaude, GitHub Copilot. 32 commands, 11 presets, 6 platform targets.",
   "type": "module",
   "license": "MIT",
@@ -47,7 +47,7 @@
     "@dzhechkov/skills-meta": "^0.9.0",
     "@dzhechkov/skills-academic": "^0.3.0",
     "@dzhechkov/skills-ecc": "^0.1.0",
-    "@dzhechkov/harness-core": "0.3.30"
+    "@dzhechkov/harness-core": "0.3.31"
   },
   "devDependencies": {
     "@types/node": "^25.6.0",