analyzthis_design 2.0.1 → 2.1.1

package/README.md

@@ -15,23 +15,28 @@ Install once. Run structured UX critiques, multi-phase ideation, and task-ground
 
 Use `npx analyzthis_design run-unchunked` for the legacy single-pass orchestrator.
 
-**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.0.1 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
+**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.1.1 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
 
 ---
 
 ## Quick start
 
 ```bash
-# 1. Install slash commands (Cursor/Claude/Codex/Grok/Windsurf)
-npx analyzthis_design
+# 1. Install the npm package (no auto-install, no obfuscation)
+npm install -g analyzthis_design
+
+# 2. Install slash commands into your IDE (explicit, consent-based)
+npx analyzthis_design --target all
 
-# 2. Run a task in v2.0 chunked mode (free/cheap models)
+# 3. Run a task in v2.0 chunked mode (free/cheap models)
 npx analyzthis_design run --task "Review invoice approval screen"
 
-# 3. Or use legacy single-pass orchestrator
+# 4. Or use legacy single-pass orchestrator
 npx analyzthis_design run-unchunked --task "Review invoice approval screen" --provider host
 ```
 
+> **Security:** This package publishes **plain source** — no obfuscation, no minification, no dynamic require. Every file in `dist/` is readable and auditable. The `postinstall` script only prints a welcome message; it does **not** write to any AI-agent directories. Skill installation requires an explicit `npx analyzthis_design --target <ide>` command.
+
 ### Install by target IDE
 
 ```bash

package/agents/cards/evolve-check.md

@@ -0,0 +1,38 @@
+# Evolve Check
+
+**Devi skill** — After a successful critique run, check if the team has enough data to evolve and offer to run the evolution cycle.
+
+---
+
+## When to invoke
+
+After a completed `run` or `run-unchunked` where:
+- Personas produced outputs
+- User accepted at least some outputs
+- Outcomes were confirmed (shipped/revised/blocked/missed)
+
+---
+
+## What to do
+
+1. Run: `npx analyzthis_design evolve --ready --project <project>`
+2. If ready → summarize pending patches and ask: "The team has enough data to evolve. Apply proposed patches?"
+3. If user says yes → run `npx analyzthis_design evolve --apply <patchId>` for each patch
+4. If not ready → tell user what's needed: "Need X more lessons / Y more outcomes"
+
+---
+
+## Example response
+
+> ��� **Devi here!** The critique run completed successfully. I checked the team's evolution status — we have **2 lessons** and **0 confirmed outcomes**. Need **3 more lessons** or **10 outcomes** to trigger evolution.
+>
+> Want me to run a critique on another screen to build up the data?
+
+---
+
+## Commands reference
+
+- `npx analyzthis_design evolve --ready --project <id>` — check readiness
+- `npx analyzthis_design evolve --metrics --project <id>` — show evolution dashboard
+- `npx analyzthis_design evolve --extract --dry-run` — preview patches
+- `npx analyzthis_design evolve --apply <id>` — apply a patch

package/agents/manifests/evolve-check.json

@@ -0,0 +1,16 @@
+{
+  "id": "evolve-check",
+  "name": "Evolve Check",
+  "type": "utility",
+  "tier": "structured",
+  "system_card": "agents/cards/evolve-check.md",
+  "system_skill": "skills/evolve-check/SKILL.md",
+  "allowed_jobs": ["evolve_check", "metrics_report"],
+  "forbidden_jobs": ["critique", "wireframe", "synthesize"],
+  "knowledge_categories": [],
+  "max_output_tokens": 600,
+  "effort_overrides": {
+    "trivial": { "provider": "host", "model": "devi", "max_output_tokens": 400 },
+    "standard": { "provider": "host", "model": "devi", "max_output_tokens": 600 }
+  }
+}

package/dist/README.md

@@ -15,23 +15,28 @@ Install once. Run structured UX critiques, multi-phase ideation, and task-ground
 
 Use `npx analyzthis_design run-unchunked` for the legacy single-pass orchestrator.
 
-**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.0.1 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
+**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.1.1 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
 
 ---
 
 ## Quick start
 
 ```bash
-# 1. Install slash commands (Cursor/Claude/Codex/Grok/Windsurf)
-npx analyzthis_design
+# 1. Install the npm package (no auto-install, no obfuscation)
+npm install -g analyzthis_design
+
+# 2. Install slash commands into your IDE (explicit, consent-based)
+npx analyzthis_design --target all
 
-# 2. Run a task in v2.0 chunked mode (free/cheap models)
+# 3. Run a task in v2.0 chunked mode (free/cheap models)
 npx analyzthis_design run --task "Review invoice approval screen"
 
-# 3. Or use legacy single-pass orchestrator
+# 4. Or use legacy single-pass orchestrator
 npx analyzthis_design run-unchunked --task "Review invoice approval screen" --provider host
 ```
 
+> **Security:** This package publishes **plain source** — no obfuscation, no minification, no dynamic require. Every file in `dist/` is readable and auditable. The `postinstall` script only prints a welcome message; it does **not** write to any AI-agent directories. Skill installation requires an explicit `npx analyzthis_design --target <ide>` command.
+
 ### Install by target IDE
 
 ```bash

package/dist/agents/cards/evolve-check.md

@@ -0,0 +1,38 @@
+# Evolve Check
+
+**Devi skill** — After a successful critique run, check if the team has enough data to evolve and offer to run the evolution cycle.
+
+---
+
+## When to invoke
+
+After a completed `run` or `run-unchunked` where:
+- Personas produced outputs
+- User accepted at least some outputs
+- Outcomes were confirmed (shipped/revised/blocked/missed)
+
+---
+
+## What to do
+
+1. Run: `npx analyzthis_design evolve --ready --project <project>`
+2. If ready → summarize pending patches and ask: "The team has enough data to evolve. Apply proposed patches?"
+3. If user says yes → run `npx analyzthis_design evolve --apply <patchId>` for each patch
+4. If not ready → tell user what's needed: "Need X more lessons / Y more outcomes"
+
+---
+
+## Example response
+
+> ��� **Devi here!** The critique run completed successfully. I checked the team's evolution status — we have **2 lessons** and **0 confirmed outcomes**. Need **3 more lessons** or **10 outcomes** to trigger evolution.
+>
+> Want me to run a critique on another screen to build up the data?
+
+---
+
+## Commands reference
+
+- `npx analyzthis_design evolve --ready --project <id>` — check readiness
+- `npx analyzthis_design evolve --metrics --project <id>` — show evolution dashboard
+- `npx analyzthis_design evolve --extract --dry-run` — preview patches
+- `npx analyzthis_design evolve --apply <id>` — apply a patch

package/dist/agents/manifests/evolve-check.json

@@ -0,0 +1,16 @@
+{
+  "id": "evolve-check",
+  "name": "Evolve Check",
+  "type": "utility",
+  "tier": "structured",
+  "system_card": "agents/cards/evolve-check.md",
+  "system_skill": "skills/evolve-check/SKILL.md",
+  "allowed_jobs": ["evolve_check", "metrics_report"],
+  "forbidden_jobs": ["critique", "wireframe", "synthesize"],
+  "knowledge_categories": [],
+  "max_output_tokens": 600,
+  "effort_overrides": {
+    "trivial": { "provider": "host", "model": "devi", "max_output_tokens": 400 },
+    "standard": { "provider": "host", "model": "devi", "max_output_tokens": 600 }
+  }
+}