@dzhechkov/harness-cli 0.3.74 → 0.3.76

package/README.md

@@ -442,6 +442,24 @@ dz setup --target claude-code --preset academic --memory agentdb
 
 Skills contain **only evaluation criteria and methodology** — no student data.
 
+### Batch mode: S3 archive → agent swarm
+
+```bash
+# Download and extract: each student = subfolder with .zip
+curl -o students.zip "https://s3.example.com/bucket/students.zip"
+mkdir students && cd students && 7z x ../students.zip
+for f in *.zip; do mkdir -p "${f%.zip}" && cd "${f%.zip}" && 7z x "../$f" && cd ..; done
+```
+
+Then in Claude Code:
+```
+"For each student folder: run document-checker → dissertation-review → question-generator.
+ Save справка.md per student with clickable inline links to pages (стр. 45, разд. 2.3)
+ and external sources ([JTBD](https://hbr.org/...)). Run all students in parallel."
+```
+
+With AgentDB, patterns persist across students — grading calibration improves with each analysis.
+
 ---
 
 ## Example: Product Discovery with Design Thinking
@@ -561,10 +579,16 @@ dz init --target codex --preset meta --enrich
 dz pretrain                                     # detects stack, recommends presets
 dz recommend "work on this Node.js API"         # suggests skills + toolkits
 
-# 2. Install skills with AgentDB (recommended — semantic search + self-learning)
-dz setup --target claude-code --preset meta --memory agentdb  # 8 skills + AgentDB (.rvf + 41 MCP tools)
-dz setup --target claude-code --preset qe-engineer             # 20 QE skills (AgentDB already configured)
-# Without AgentDB: dz setup --preset meta (lightweight JSONL backend)
+# 2. Install skills (choose your level)
+dz setup --target claude-code --preset meta --memory agentdb  # 8 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?
+npx @dzhechkov/skills-feature-adr init                         # adds slash command + rules + shards
+# See: https://www.npmjs.com/package/@dzhechkov/skills-feature-adr
+
+# preset = SKILL.md only (auto-activates on matching tasks)
+# npx = full toolkit (slash command + governance + rules)
 ```
 
 Install [Understand-Anything](https://github.com/Lum1104/Understand-Anything) plugin, then in Claude Code:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dzhechkov/harness-cli",
-  "version": "0.3.74",
+  "version": "0.3.76",
   "description": "The dz CLI — install AI skills for Claude Code, Codex, OpenCode, Hermes. 11 commands, 7 presets, 4 platform adapters.",
   "type": "module",
   "license": "MIT",