@fluentcommerce/ai-skills 0.14.0 → 0.15.0

package/docs/fluent-ai-skills-reference.md

@@ -92,7 +92,7 @@ npx @fluentcommerce/ai-skills install --profile YOUR_PROFILE
 | **fluent-mcp** (official) | Official Fluent CLI MCP server — workflows and GraphQL |
 | **chrome-devtools** | Browser automation for UI testing (optional) |
 
-**Installable skill groups:** CLI (~10) · Dev (~50) · RFL (1) · MCP (2)
+**Installable skill groups:** CLI (8) · Dev (52) · RFL (1) · MCP (2)
 
 **Supported IDE:** Claude Code (primary) and Codex (experimental skills-first flow)
 
@@ -232,7 +232,7 @@ Mention workflows/rules/Java → backend agent. Mention manifests/pages/UI → f
 | Group | Skills | What it provides |
 |-------|:------:|------------------|
 | `cli` | 8 | Fluent CLI command-family coverage: connect, profile, retailer, modules, workflows, MCP/CI-CD, bootstrap |
-| `dev` | 52 | **Backend:** workflow builder/analyzer, connection analysis, custom code, transition API, rule scaffold, rule test generation/repair, module scaffold/validate/build, source onboarding, trace, entity-flow diagnose, event API, system monitoring, batch, settings, deploy, workflow deploy, rollback. **Frontend:** mystique assess (validate + analyze), manifest builder, SDK scaffold/component/reference, manifest diff, frontend build (8 gates)/review (9 phases)/readme, UI test, UI record. **Cross-cutting:** feature planning, use-case discover, feature status/explain, implementation map, scope plan, E2E test, test data, session, sourcing, knowledge init, workspace tree, skill observability, account snapshot, goal |
+| `dev` | 52 | **Backend:** workflow builder/analyzer, connection analysis, custom code, transition API, rule scaffold, rule test generation/repair, module scaffold/validate/build, source onboarding, trace, entity-flow diagnose, event API, system monitoring, batch, settings, deploy, workflow deploy, rollback. **Frontend:** mystique assess (validate + analyze), manifest builder, SDK scaffold/component/reference, manifest diff, frontend build (7 gates)/review (9 phases)/readme, UI test, UI record. **Cross-cutting:** feature planning, use-case discover, feature status/explain, implementation map, scope plan, E2E test, test data, session, sourcing, knowledge init, workspace tree, skill observability, account snapshot, goal |
 | `rfl` | 1 | Production readiness assessment — scored report across workflows, rules, settings, integrations |
 | `mcp-extn` | 2 | MCP extension tools reference (55+ tools in 15 categories) + official CLI MCP server reference |
 
@@ -556,7 +556,7 @@ Each feature lives in `accounts/<PROFILE>/features/<slug>/` with four canonical
 | 5. Create rules | "Create rules from the plan" | Java classes + tests | `*.java` + `*Test.java` |
 | 6. Build workflow | "Build the workflow" | Workflow JSON + validation | `<WORKFLOW>.json` |
 | 7. Build module | "Build the module" | Maven build + packaging | `dist/<module>.zip` |
-| 8. Pre-deploy checks | "Run pre-deploy checks" | 35+ quality gates | `reports/pre-deploy/*.json` |
+| 8. Pre-deploy checks | "Run pre-deploy checks" | 37 quality gates | `reports/pre-deploy/*.json` |
 | 9. Deploy | "Deploy to MY_RETAILER" | Module + workflow deployment | Live environment changes |
 | 10. E2E test | "Run E2E test" | Create entities, fire events, assert | Test report |
 
@@ -588,10 +588,10 @@ graph LR
 
 A live HTML dashboard auto-starts at `http://localhost:3456` when feature work begins. It shows all features with status, spec/plan content rendered as HTML with Mermaid diagrams, file metadata, and session history. Features being actively updated show a pulsing indicator in the sidebar.
 
-Generated by `fluent-ai-skills/tools/generate-feature-dashboard.mjs` — zero dependencies, vendor libs bundled inline. Updates automatically via SSE when any feature file changes.
+Generated by `fluent-ai-skills/tools/feature-dashboard.mjs` — zero dependencies, vendor libs bundled inline. Updates automatically via SSE when any feature file changes.
 
 **Prerequisites:**
-1. **Vendor libs** — run `node fluent-ai-skills/tools/generate-feature-dashboard.mjs --setup` once. Downloads `marked.min.js` and `mermaid.min.js` to `fluent-ai-skills/tools/vendor/`.
+1. **Vendor libs** — run `node fluent-ai-skills/tools/feature-dashboard.mjs --setup` once. Downloads `marked.min.js` and `mermaid.min.js` to `fluent-ai-skills/tools/vendor/`.
 2. **Features directory** — at least one feature must exist under `accounts/<PROFILE>/features/` (created by `/fluent-use-case-discover`).
 3. **Node.js 18+** (20+ recommended).
 
@@ -612,16 +612,16 @@ Generated by `fluent-ai-skills/tools/generate-feature-dashboard.mjs` — zero de
 
 ```bash
 # One-time setup (download vendor libs)
-node fluent-ai-skills/tools/generate-feature-dashboard.mjs --setup
+node fluent-ai-skills/tools/feature-dashboard.mjs --setup
 
 # Start live server (auto-refreshes on file changes)
-node fluent-ai-skills/tools/generate-feature-dashboard.mjs --profile ACME --serve --port 3456
+node fluent-ai-skills/tools/feature-dashboard.mjs --profile ACME --serve --port 3456
 
 # Generate static HTML only (no server)
-node fluent-ai-skills/tools/generate-feature-dashboard.mjs --profile ACME
+node fluent-ai-skills/tools/feature-dashboard.mjs --profile ACME
 
 # All profiles at once (static only)
-node fluent-ai-skills/tools/generate-feature-dashboard.mjs --all
+node fluent-ai-skills/tools/feature-dashboard.mjs --all
 ```
 
 **Dashboard tabs per feature:** Status (lifecycle progress bar + gates + sessions), Spec (rendered markdown + Mermaid), Plan (rendered markdown + Mermaid), Architecture (diagrams), Feedback (skill success/failure metrics), Reports (embedded markdown + base64 screenshots), Files (file metadata).
@@ -1092,7 +1092,7 @@ Credentials must be set as **shell environment variables** — never in `.mcp.js
 | Manifest building & editing | `/fluent-mystique-builder` |
 | Manifest validation & analysis | `/fluent-mystique-assess` |
 | SDK component scaffolding | `/fluent-mystique-scaffold` |
-| SDK build pipeline (8 gates) | `/fluent-frontend-build` |
+| SDK build pipeline (7 gates) | `/fluent-frontend-build` |
 | SDK code quality audit (9 phases) | `/fluent-frontend-review` |
 | SDK README generation | `/fluent-frontend-readme` |
 | Manifest CDN vs custom diff | `/fluent-mystique-diff` |

package/metadata.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.13.0",
+  "version": "0.14.0",
   "organization": "Fluent Commerce",
   "date": "March 2026",
   "package": "@fluentcommerce/ai-skills",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@fluentcommerce/ai-skills",
-  "version": "0.14.0",
+  "version": "0.15.0",
   "description": "[Experimental] Fluent Commerce domain knowledge for Claude Code. Skills, agents, and MCP server configs for workflows, events, rules, and APIs.",
   "keywords": [
     "fluent-commerce",
@@ -56,6 +56,9 @@
     "eval:run:sandbox": "node evals/scripts/run-live-evals.mjs --suite runtime-live-sandbox --executor evals/executors/codex-live.mjs",
     "eval:run:tools": "FLUENT_EVAL_ENABLE_MCP=1 node evals/scripts/run-live-evals.mjs --suite tool-behavior --executor evals/executors/claude-live.mjs",
     "eval:report": "node evals/scripts/eval-report.mjs",
+    "eval:promptfoo:generate": "node evals/promptfoo/generate.mjs",
+    "eval:promptfoo": "node evals/promptfoo/generate.mjs && npx promptfoo eval -c evals/promptfoo/promptfooconfig.yaml",
+    "eval:promptfoo:view": "npx promptfoo view",
     "eval:playground": "node evals/playground.mjs",
     "eval:playground:dev": "node --watch evals/playground.mjs",
     "playground": "node evals/playground.mjs",
@@ -63,6 +66,7 @@
     "test:parallel": "node scripts/test-parallel.mjs",
     "test:parallel:quick": "node scripts/test-parallel.mjs --quick",
     "test": "npm run test:smoke && npm run test:pack && npm run test:unit && npm run test:evals:core",
+    "postinstall": "node scripts/postinstall.mjs || true",
     "prepublishOnly": "npm test"
   },
   "type": "module",
@@ -78,6 +82,7 @@
     "!content/**/.claude-plugin",
     "docs/",
     "lib/",
+    "scripts/postinstall.mjs",
     "tools/",
     "!tools/vendor/",
     "metadata.json",

package/scripts/postinstall.mjs

@@ -0,0 +1,38 @@
+#!/usr/bin/env node
+
+/**
+ * Post-install nudge — prints a one-time message after `npm install`.
+ * Does NOT auto-execute the install command (that writes to ~/.claude/ and
+ * should always be an explicit user action).
+ *
+ * Safe for CI: exits 0 unconditionally, prints to stderr so it doesn't
+ * pollute piped stdout, and skips entirely when CI env vars are set.
+ */
+
+// Skip in CI — no human to read it
+if (process.env.CI || process.env.CONTINUOUS_INTEGRATION || process.env.BUILD_NUMBER) {
+  process.exit(0);
+}
+
+const YELLOW = "\x1b[33m";
+const CYAN = "\x1b[36m";
+const BOLD = "\x1b[1m";
+const RESET = "\x1b[0m";
+
+console.error(`
+${YELLOW}┌──────────────────────────────────────────────────────────────┐
+│                                                              │
+│  ${BOLD}@fluentcommerce/ai-skills${RESET}${YELLOW} installed.                       │
+│                                                              │
+│  To activate skills in your coding assistant, run:           │
+│                                                              │
+│    ${CYAN}npx @fluentcommerce/ai-skills install${YELLOW}                     │
+│                                                              │
+│  First time? Add a Fluent profile for full API access:       │
+│                                                              │
+│    ${CYAN}npx @fluentcommerce/ai-skills install --profile MYPROFILE${YELLOW} │
+│                                                              │
+│  See all options:  ${CYAN}npx @fluentcommerce/ai-skills --help${YELLOW}      │
+│                                                              │
+└──────────────────────────────────────────────────────────────┘${RESET}
+`);

package/{content/dev/skills/fluent-trace/scripts/analyze-event-capture.mjs → tools/event-capture-analyzer.mjs}

@@ -5,7 +5,7 @@ import path from "node:path";
 
 const USAGE = `
 Usage:
-  node scripts/analyze-event-capture.mjs <capture.json> [more.json ...] [options]
+  node fluent-ai-skills/tools/event-capture-analyzer.mjs <capture.json> [more.json ...] [options]
 
 Options:
   --root-ref <ref>      Filter to events in this root entity lineage
@@ -17,8 +17,8 @@ Options:
   --help                Show this help
 
 Examples:
-  node scripts/analyze-event-capture.mjs ORD-1.window.json --root-ref ORD-1
-  node scripts/analyze-event-capture.mjs evt-123.event.json evt-123.window.json --root-ref ORD-1 --from 2026-03-25T10:00:00Z --to 2026-03-25T10:05:00Z --output ORD-1.metrics.json
+  node fluent-ai-skills/tools/event-capture-analyzer.mjs ORD-1.window.json --root-ref ORD-1
+  node fluent-ai-skills/tools/event-capture-analyzer.mjs evt-123.event.json evt-123.window.json --root-ref ORD-1 --from 2026-03-25T10:00:00Z --to 2026-03-25T10:05:00Z --output ORD-1.metrics.json
 `.trim();
 
 function fail(message) {

package/tools/{generate-feature-dashboard.mjs → feature-dashboard.mjs}

@@ -1,5 +1,5 @@
 #!/usr/bin/env node
-// fluent-ai-skills/tools/generate-feature-dashboard.mjs
+// fluent-ai-skills/tools/feature-dashboard.mjs
 // Feature Lifecycle HTML Dashboard Generator
 // Zero npm dependencies — uses only Node.js built-ins
 // Reads feature data from accounts/<PROFILE>/features/ and produces a self-contained HTML dashboard
@@ -116,7 +116,7 @@ function checkVendor() {
   const marked = join(VENDOR_DIR, 'marked.min.js');
   const mermaid = join(VENDOR_DIR, 'mermaid.min.js');
   if (!existsSync(marked) || !existsSync(mermaid)) {
-    console.error('Error: Vendor libs missing. Run: node fluent-ai-skills/tools/generate-feature-dashboard.mjs --setup');
+    console.error('Error: Vendor libs missing. Run: node fluent-ai-skills/tools/feature-dashboard.mjs --setup');
     process.exit(1);
   }
   return {

package/tools/manifest-diff.mjs

@@ -33,7 +33,7 @@ const ACCOUNTS_DIR = join(WORKSPACE_ROOT, 'accounts');
 
 const CDN_BASE = 'https://fluent.apps.fluentcommerce.com/_plugins';
 
-// ─── OOTB Component Registry (from fluent-mystique-validate/validator.mjs) ──
+// ─── OOTB Component Registry (from tools/manifest-validator.mjs) ──
 const OOTB_COMPONENTS = new Set([
   // Layout & Container
   'fc.page','fc.page.wizard','fc.page.wizard.summary','fc.page.section',

package/{content/dev/skills/fluent-mystique-assess/validator.mjs → tools/manifest-validator.mjs}

@@ -5,7 +5,7 @@
  * Implements all 66 validation rules from SKILL.md across 6 phases.
  *
  * Usage:
- *   node validator.mjs <manifest.json> [--strict] [--fix-suggestions] [--component <alias>] [--json]
+ *   node fluent-ai-skills/tools/manifest-validator.mjs <manifest.json> [--strict] [--fix-suggestions] [--component <alias>] [--json]
  */
 
 import { readFileSync, readdirSync, statSync, writeFileSync } from 'fs';
@@ -1113,7 +1113,7 @@ const args = process.argv.slice(2);
 if (args.length === 0 || args.includes('--help')) {
   console.log(`Mystique Manifest Validator v1.0
 
-Usage: node validator.mjs <manifest.json|directory> [options]
+Usage: node fluent-ai-skills/tools/manifest-validator.mjs <manifest.json|directory> [options]
 
 Options:
   --strict            Treat MEDIUM/LOW as errors