everything-gemini 1.0.0 → 1.0.1

package/.github/workflows/release.yml

@@ -0,0 +1,42 @@
+name: Release & Publish
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+jobs:
+  build-and-publish:
+    name: Build, Test & Publish to NPM
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      id-token: write
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          registry-url: 'https://registry.npmjs.org'
+
+      - name: Make Scripts Executable
+        run: |
+          chmod +x scripts/validate.sh scripts/install.sh bin/everything-gemini
+          find hooks/ -type f -name "*.sh" -exec chmod +x {} +
+          find skills/ -type f -name "*.sh" -exec chmod +x {} +
+
+      - name: Run Test Suite
+        run: npm test
+
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          generate_release_notes: true
+          files: |
+            LICENSE
+            README.md
+            CHANGELOG.md

package/CHANGELOG.md

@@ -0,0 +1,45 @@
+# 📜 Changelog
+
+All notable changes to **Everything Gemini (`everything-gemini`)** will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+---
+
+## [1.0.1] - 2026-10-15
+
+### Added
+- **`gemini-grounding` Skill**: Native Google Search Grounding and dynamic fact-verification playbook.
+- **Automated Release Workflow**: `.github/workflows/release.yml` for automated GitHub releases and npm publishing.
+- **NPM Package Verification**: Published to npm registry as `everything-gemini`.
+
+### Changed
+- Normalized all documentation, plugins, and lifecycle hook manifests to `everything-gemini`.
+- Added instant `npx everything-gemini install` installation instructions to README.
+- Credited Everything Claude Code (ECC) by Affan Mustafa in dedicated `Acknowledgements & Prior Art` section.
+
+---
+
+## [1.0.0] - 2026-10-15
+
+### Initial Public Launch
+- **18 Progressive Disclosure Skills**:
+  - `gemini-multimodal`: Visual mockups, diagram extraction, and automated UI regression testing.
+  - `context-caching`: 1M-2M token context optimization with static prefix caching.
+  - `subagent-handoff`: Multi-agent scoped delegation and synthesis.
+  - `api-craftsman`, `database-architect`, `devops-pipeline`, `root-cause-debugger`, `tdd-workflow`, `browser-qa-tester`, `architecture-designer`, `repo-onboarding`, `git-craftsman`, `performance-profiler`, `fullstack-nextjs`, `security-audit`, `continuous-learning`.
+- **6 Scoped Subagents (`agents/`)**:
+  - `planner.md`, `code-reviewer.md`, `build-repair.md`, `browser-qa.md`, `security-auditor.md`, `architect.md`.
+- **GeminiShield Safety Gate & Lifecycle Hooks**:
+  - `PreToolUse`: Catastrophic command blocker (`rm -rf`, `DROP TABLE`, `git push --force`).
+  - `PostToolUse`: Auto-lint formatter.
+  - `Stop`: Goal-verifier preventing premature agent completion on broken tests.
+  - `PreInvocation`: Ephemeral context injector.
+- **4 Modular Plugins**:
+  - `plugins/core`, `plugins/web-fullstack`, `plugins/python-ai`, `plugins/security-shield`.
+- **Zero-Dependency CLI (`bin/everything-gemini`)**:
+  - `doctor`, `install`, `list`, `new-skill`, `new-agent`, `validate`.
+- **Comprehensive Documentation**:
+  - Architectural comparison breakdown against Everything Claude Code (ECC) (`docs/ecc-vs-everything-gemini.md`).
+  - 4 Antigravity Surfaces guide (Desktop 2.0, IDE, CLI, Python SDK).
+  - Progressive disclosure specifications and Cortex event loop diagrams.

package/CONTRIBUTING.md

@@ -1,6 +1,6 @@
-# Contributing to Everything Antigravity (`eagy`)
+# Contributing to Everything Gemini (`everything-gemini`)
 
-Thank you for your interest in contributing to **Everything Antigravity (`eagy`)**! Our goal is to build the highest-quality, most reliable, and most token-efficient agent harness and customization ecosystem for Google Antigravity.
+Thank you for your interest in contributing to **Everything Gemini (`everything-gemini`)**! Our goal is to build the highest-quality, most reliable, and most token-efficient agent harness and customization ecosystem for Google Antigravity and Gemini.
 
 ---
 

package/README.md

@@ -4,7 +4,7 @@
 
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
 [![Antigravity](https://img.shields.io/badge/Google-Antigravity-4285F4.svg)](https://antigravity.google)
-[![Version](https://img.shields.io/badge/version-1.0.0-emerald.svg)](package.json)
+[![Version](https://img.shields.io/badge/version-1.0.1-emerald.svg)](package.json)
 [![Status](https://img.shields.io/badge/status-active-success.svg)](https://github.com/salmandev/everything-gemini)
 [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)
 
@@ -38,9 +38,15 @@ Out of the box, Antigravity is a formidable pair programmer. But without structu
 
 ## 🚀 Quickstart
 
-### 1. One-Line Interactive Installer
+### 1. Instant Installation via npx (Zero Setup)
 
-Run this in your terminal to install `eagy` globally or into your current project:
+Run this directly in any project directory or terminal:
+
+```bash
+npx everything-gemini install
+```
+
+### 2. One-Line Interactive Installer
 
 ```bash
 # macOS / Linux
@@ -52,18 +58,17 @@ curl -fsSL https://raw.githubusercontent.com/salmandev/everything-gemini/main/sc
 irm https://raw.githubusercontent.com/salmandev/everything-gemini/main/scripts/install.ps1 | iex
 ```
 
-### 2. Via `eagy` CLI (Zero-Dependency)
-
+### 3. Via Repository Clone
 ```bash
 # Clone the repository
 git clone https://github.com/salmandev/everything-gemini.git
 cd everything-gemini
 
-# Run the eagy harness CLI
+# Run the Everything Gemini CLI
 ./bin/everything-gemini install --profile developer
 ```
 
-### 3. Installation Profiles
+### 4. Installation Profiles
 
 | Profile | Target Audience | What Gets Installed |
 | :--- | :--- | :--- |
@@ -75,7 +80,7 @@ cd everything-gemini
 
 ## 🏗️ Architecture & Internals
 
-`eagy` is engineered specifically around Google Antigravity's internal execution engine:
+`everything-gemini` is engineered specifically around Google Antigravity's internal execution engine:
 
 ```mermaid
 flowchart TB
@@ -91,7 +96,7 @@ flowchart TB
         Workspace[".agents/ (Workspace Root)"]
     end
 
-    subgraph EagyHarness["3. eagy Harness & Engine"]
+    subgraph GeminiHarness["3. Everything Gemini Harness & Engine"]
         direction TB
         HookEngine["Lifecycle Hooks Engine\n(PreToolUse | PostToolUse | PreInvocation | Stop)"]
         Progressive["Progressive Disclosure Router\n(Injects only metadata until model decides to view)"]
@@ -105,8 +110,8 @@ flowchart TB
     end
 
     AntigravitySurfaces --> CustomizationRoots
-    CustomizationRoots --> EagyHarness
-    EagyHarness --> Capabilities
+    CustomizationRoots --> GeminiHarness
+    GeminiHarness --> Capabilities
 ```
 
 ### Key Differences: ECC vs. Everything Gemini
@@ -136,7 +141,7 @@ everything-gemini/
 ├── agents/                       # Scoped subagent fleet (Planner, Reviewer, Architect, etc.)
 ├── scripts/                      # Automated installers and harness validators
 ├── plugins/                      # Reusable modular plugins (web-fullstack, python-ai, security)
-├── skills/                       # 16+ Progressive disclosure skills
+├── skills/                       # 21+ Progressive disclosure skills
 ├── rules/                        # Contextual guidelines & standards
 ├── hooks/                        # Event-driven lifecycle hooks (GeminiShield, Auto-lint)
 ├── mcp/                          # Production-ready MCP server blueprints
@@ -178,11 +183,12 @@ Skills in Antigravity are lazy-loaded runbooks. Only their YAML frontmatter (`na
 - **[`git-craftsman`](skills/git-craftsman/SKILL.md)**: Enforces conventional commits, atomic diffs, and clean PR descriptions.
 - **[`security-audit`](skills/security-audit/SKILL.md)**: Scans for credentials in commit history and audits dependency risks.
 - **[`performance-profiler`](skills/performance-profiler/SKILL.md)**: Identifies CPU/memory bottlenecks, analyzes database queries, and critical paths.
-- **[`fullstack-nextjs`](skills/fullstack-nextjs/SKILL.md)**: Best practices for React Server Components, hydration fixes, and Server Actions.
-- **[`git-craftsman`](skills/git-craftsman/SKILL.md)**: Enforces conventional commits, crafts atomic diffs, and writes PR summaries linked with file references.
-- **[`security-audit`](skills/security-audit/SKILL.md)**: Scans for credentials in commit history, tests for injection vulnerabilities, and verifies dependencies.
-- **[`performance-profiler`](skills/performance-profiler/SKILL.md)**: Identifies CPU/memory bottlenecks, analyzes database queries, and optimizes critical paths.
-- **[`fullstack-nextjs`](skills/fullstack-nextjs/SKILL.md)**: Best practices for React Server Components, hydration fixes, and API routes.
+- **[`gemini-grounding`](skills/gemini-grounding/SKILL.md)**: Real-time Google Search grounding, live documentation retrieval, and fact-checking.
+- **[`supabase-architect`](skills/supabase-architect/SKILL.md)**: Row Level Security (RLS) policies, pgvector embeddings, and edge function workflows.
+- **[`cloudflare-workers`](skills/cloudflare-workers/SKILL.md)**: Serverless edge functions, Wrangler v3, D1 SQL, and KV low-latency storage.
+- **[`kubernetes-operator`](skills/kubernetes-operator/SKILL.md)**: Production k8s manifests, HPA autoscaling, zero-downtime rolling updates, and health probes.
+- **[`stripe-integration`](skills/stripe-integration/SKILL.md)**: Webhook signature verification, idempotent payments, and customer portal session flows.
+- **[`continuous-learning`](skills/continuous-learning/SKILL.md)**: Codifies corrections and developer feedback into enduring Knowledge Items.
 
 ### 2. Lifecycle Hooks (`hooks/`)
 Hooks run shell scripts at critical lifecycle events with typed JSON contracts on `stdin`/`stdout`:
@@ -203,7 +209,7 @@ Antigravity automatically discovers rules by walking up from the current file's
 
 ## 🖥️ The 4 Antigravity Surfaces
 
-Antigravity operates across four interconnected surfaces. `eagy` supports all of them seamlessly:
+Antigravity operates across four interconnected surfaces. `everything-gemini` supports all of them seamlessly:
 
 ```
 +-----------------------------------------------------------------------------------+
@@ -232,9 +238,9 @@ Antigravity operates across four interconnected surfaces. `eagy` supports all of
 
 Antigravity provides built-in slash commands in chat that activate specialized cognitive modes:
 
-| Command | Purpose | How `eagy` Enhances It |
+| Command | Purpose | How Everything Gemini Enhances It |
 | :--- | :--- | :--- |
-| **`/goal <task>`** | Long-running autonomous mode | Pairs with `eagy`'s **Goal Verifier Hook** to prevent premature termination until test suites pass. |
+| **`/goal <task>`** | Long-running autonomous mode | Pairs with Everything Gemini's **Goal Verifier Hook** to prevent premature termination until test suites pass. |
 | **`/plan <task>`** | Step-by-step implementation blueprint | Enforces architectural review, risk assessment, and mermaid diagrams before code edits. |
 | **`/grill-me`** | Interactive design interview | Asks hard architectural and trade-off questions to resolve ambiguities before implementing. |
 | **`/learn`** | Persist feedback across sessions | Automatically indexes insights into a permanent Knowledge Item (`<appDataDir>/knowledge`). |
@@ -244,13 +250,13 @@ Antigravity provides built-in slash commands in chat that activate specialized c
 
 ## 📊 Token Efficiency & Benchmark
 
-Traditional agent harnesses dump dozens of prompt files into the system prompt on every single turn. Antigravity's **Progressive Disclosure** paired with `eagy` avoids this:
+Traditional agent harnesses dump dozens of prompt files into the system prompt on every single turn. Antigravity's **Progressive Disclosure** paired with Everything Gemini avoids this:
 
 ```
 [Traditional Setup]
 System Prompt: Base Instructions + All 25 Skills (Full Text) + All Rules = ~45,000 Tokens / turn
 
-[eagy on Antigravity]
+[Everything Gemini on Antigravity]
 System Prompt: Base Instructions + 25 Skill Summaries (YAML) + Directory Rules = ~3,200 Tokens / turn
 Skill Body: Loaded on-demand ONLY when invoked = ~1,500 Tokens (one-time)
 Savings: > 85% Token Reduction & 3x Faster First-Token Latency!
@@ -260,7 +266,7 @@ Savings: > 85% Token Reduction & 3x Faster First-Token Latency!
 
 ## 🛠️ Usage & CLI Reference
 
-The zero-dependency `eagy` CLI manages your configurations effortlessly:
+The zero-dependency `everything-gemini` CLI manages your configurations effortlessly:
 
 ```bash
 # Verify your installation and check for conflicts

package/bin/everything-gemini

@@ -1,8 +1,8 @@
 #!/usr/bin/env node
 
 /**
- * Everything Antigravity (eagy) CLI
- * Zero-dependency harness manager for Google Antigravity
+ * Everything Gemini (everything-gemini) CLI
+ * Zero-dependency harness manager for Google Antigravity & Gemini
  */
 
 const fs = require('fs');
@@ -27,7 +27,7 @@ const GRAY = '\x1b[90m';
 
 function printBanner() {
   console.log(`
-${CYAN}${BOLD}🪐 Everything Gemini (${GREEN}everything-gemini${CYAN}) v1.0.0${RESET}
+${CYAN}${BOLD}🪐 Everything Gemini (${GREEN}everything-gemini${CYAN}) v1.0.1${RESET}
 ${GRAY}The open-source agent harness & multi-agent orchestrator for Google Gemini & Antigravity${RESET}
 `);
 }
@@ -38,7 +38,7 @@ function printHelp() {
   console.log(`  everything-gemini <command> [options]\n`);
   console.log(`${BOLD}COMMANDS:${RESET}`);
   console.log(`  ${GREEN}doctor${RESET}                      Inspect system, AGY surfaces, and configuration health`);
-  console.log(`  ${GREEN}install${RESET} [options]           Install eagy profiles into workspace or globally`);
+  console.log(`  ${GREEN}install${RESET} [options]           Install everything-gemini profiles into workspace or globally`);
   console.log(`  ${GREEN}list${RESET}                        Show all available skills, rules, hooks, and plugins`);
   console.log(`  ${GREEN}new-skill${RESET} <name>            Scaffold a new progressive-disclosure skill`);
   console.log(`  ${GREEN}new-agent${RESET} <name>            Scaffold a new scoped subagent specification`);
@@ -217,7 +217,7 @@ function installProfile(profile = 'developer', isGlobal = false, customTarget =
     ? path.resolve(customTarget)
     : (isGlobal ? GLOBAL_CONFIG_DIR : AGENTS_DIR);
 
-  console.log(`${BOLD}🚀 Installing eagy Profile: [${GREEN}${profile}${RESET}${BOLD}]${RESET}`);
+  console.log(`${BOLD}🚀 Installing everything-gemini Profile: [${GREEN}${profile}${RESET}${BOLD}]${RESET}`);
   console.log(`Target Directory: ${CYAN}${targetDir}${RESET}\n`);
 
   if (!fs.existsSync(targetDir)) {

package/docs/architecture/progressive-disclosure.md

@@ -22,7 +22,7 @@ Instead of injecting entire skill files (`SKILL.md`) into the system prompt:
 | Harness Strategy                   | Baseline Prompt Overhead |
 +------------------------------------+--------------------------+
 | Monolithic Prompts (e.g. naive)    | ~48,000 tokens / turn    |
-| eagy Progressive Disclosure        | ~3,200 tokens / turn     |
+| Everything Gemini Progressive Disc. | ~3,200 tokens / turn     |
 +------------------------------------+--------------------------+
 | Net Token Savings                  | 85% - 93%                |
 +------------------------------------+--------------------------+

package/docs/workflows/slash-commands.md

@@ -8,11 +8,11 @@ Slash commands in Antigravity chat trigger specialized cognitive modes, prompt r
 
 ### `/goal <prompt>`
 - **Behavior**: Enters autonomous goal-seeking mode. The agent continues executing multi-step actions until the objective is fully verified.
-- **eagy Synergy**: Combines with `hooks/goal-verifier/` to prevent premature stops if test suites or linters fail.
+- **everything-gemini Synergy**: Combines with `hooks/goal-verifier/` to prevent premature stops if test suites or linters fail.
 
 ### `/plan <prompt>`
 - **Behavior**: Generates a comprehensive architectural plan and step-by-step implementation blueprint before touching any code.
-- **eagy Synergy**: Activates the `architecture-designer` skill, automatically producing C4 Mermaid diagrams and risk analyses.
+- **everything-gemini Synergy**: Activates the `architecture-designer` skill, automatically producing C4 Mermaid diagrams and risk analyses.
 
 ### `/grill-me`
 - **Behavior**: The agent acts as an architectural interviewer, grilling the developer on edge cases, non-functional constraints, and trade-offs before generating solutions.
@@ -20,7 +20,7 @@ Slash commands in Antigravity chat trigger specialized cognitive modes, prompt r
 
 ### `/learn`
 - **Behavior**: Persists lessons learned from mistakes, corrections, or complex configurations into a permanent Knowledge Item (`<appDataDir>/knowledge`).
-- **eagy Synergy**: Connects with `repo-onboarding` and Knowledge Items schemas to build an enduring project memory.
+- **everything-gemini Synergy**: Connects with `repo-onboarding` and Knowledge Items schemas to build an enduring project memory.
 
 ### `/schedule`
 - **Behavior**: Schedules delayed one-shot timers or recurring cron jobs with reactive wakeup.

package/hooks/auto-lint-formatter/scripts/auto-format.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# eagy Auto-Lint Formatter: PostToolUse Hook
+# Everything Gemini Auto-Lint Formatter: PostToolUse Hook
 # Silently runs language-appropriate formatters on modified files.
 
 set -eo pipefail

package/hooks/ephemeral-context/scripts/inject-context.sh

@@ -1,8 +1,8 @@
 #!/usr/bin/env bash
-# eagy Ephemeral Context Injector: PreInvocation Hook
+# Everything Gemini Ephemeral Context Injector: PreInvocation Hook
 # Sends a transient reminder to the agent prior to model invocation.
 
 set -eo pipefail
 
-echo '{"injectSteps": [{"ephemeralMessage": "[eagy Harness Active]: Verify code with tests, follow progressive disclosure, and ensure all file links use markdown file:// scheme."}]}'
+echo '{"injectSteps": [{"ephemeralMessage": "[Everything Gemini Harness Active]: Verify code with tests, follow progressive disclosure, and ensure all file links use markdown file:// scheme."}]}'
 exit 0

package/hooks/goal-verifier/scripts/verify-goal.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# eagy Goal Verifier: Stop Hook
+# Everything Gemini Goal Verifier: Stop Hook
 # Checks if the workspace has uncommitted broken tests before allowing termination.
 
 set -eo pipefail
@@ -14,7 +14,7 @@ if git rev-parse --is-inside-work-tree >/dev/null 2>&1; then
     # If package.json has a test script, verify tests pass
     if [ -f "package.json" ] && grep -q '"test"' package.json; then
       if ! npm test >/dev/null 2>&1; then
-        echo "{\"decision\": \"continue\", \"reason\": \"[eagy Goal Verifier] Uncommitted changes failed 'npm test'. Please resolve failing tests before stopping.\"}"
+        echo "{\"decision\": \"continue\", \"reason\": \"[Everything Gemini Goal Verifier] Uncommitted changes failed 'npm test'. Please resolve failing tests before stopping.\"}"
         exit 0
       fi
     fi

package/hooks/safety-shield/scripts/safety-gate.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# eagy Safety Shield: PreToolUse Security Gate
+# Everything Gemini Safety Shield: PreToolUse Security Gate
 # Reads protojson hook payload from stdin, evaluates safety, outputs JSON on stdout.
 
 set -eo pipefail
@@ -46,7 +46,7 @@ ASK_PATTERNS=(
 # Check blocked patterns
 for pattern in "${BLOCKED_PATTERNS[@]}"; do
   if [[ "$CMD" == *"$pattern"* ]]; then
-    echo "{\"decision\": \"deny\", \"reason\": \"[eagy Safety Shield] Catastrophic command pattern detected and blocked: '$pattern'\"}"
+    echo "{\"decision\": \"deny\", \"reason\": \"[Everything Gemini Safety Shield] Catastrophic command pattern detected and blocked: '$pattern'\"}"
     exit 0
   fi
 done
@@ -54,7 +54,7 @@ done
 # Check ask patterns
 for pattern in "${ASK_PATTERNS[@]}"; do
   if [[ "$CMD" == *"$pattern"* ]]; then
-    echo "{\"decision\": \"ask\", \"reason\": \"[eagy Safety Shield] Potentially destructive command requires user confirmation: '$pattern'\"}"
+    echo "{\"decision\": \"ask\", \"reason\": \"[Everything Gemini Safety Shield] Potentially destructive command requires user confirmation: '$pattern'\"}"
     exit 0
   fi
 done

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "everything-gemini",
-  "version": "1.0.0",
+  "version": "1.0.1",
   "description": "Everything Gemini (everything-gemini) - The Ultimate Agent Harness, Multi-Agent Orchestrator & Performance Suite for Gemini & Google Antigravity",
   "main": "bin/everything-gemini",
   "bin": {

package/plugins/core/plugin.json

@@ -1,3 +1,3 @@
 {
-  "name": "eagy Core Safety & Engineering"
+  "name": "Everything Gemini Core Safety & Engineering"
 }

package/plugins/python-ai/plugin.json

@@ -1,3 +1,3 @@
 {
-  "name": "eagy Python & AI Systems"
+  "name": "Everything Gemini Python & AI Systems"
 }

package/plugins/security-shield/plugin.json

@@ -1,3 +1,3 @@
 {
-  "name": "eagy Security Shield"
+  "name": "Everything Gemini Security Shield"
 }

package/plugins/web-fullstack/plugin.json

@@ -1,3 +1,3 @@
 {
-  "name": "eagy Web Fullstack Suite"
+  "name": "Everything Gemini Web Fullstack Suite"
 }

package/rules/common/AGENTS.md

@@ -1,4 +1,4 @@
-# Antigravity Core Behavioral Standards (eagy)
+# Antigravity Core Behavioral Standards (everything-gemini)
 
 These standards govern all Antigravity agent interactions within this project.
 

package/rules/common/GEMINI.md

@@ -1,4 +1,4 @@
-# Antigravity Core Behavioral Standards (eagy)
+# Antigravity Core Behavioral Standards (everything-gemini)
 
 These standards govern all Antigravity agent interactions within this project.
 

package/skills/cloudflare-workers/SKILL.md

@@ -0,0 +1,72 @@
+---
+name: cloudflare-workers
+description: >-
+  Use this skill when developing Cloudflare Workers, configuring Wrangler v3, integrating Cloudflare D1 SQL or KV storage, or deploying global edge APIs.
+---
+
+# Cloudflare Workers & Edge Infrastructure
+
+## Overview
+Cloudflare Workers execute on V8 isolates across 300+ edge locations worldwide. This skill provides architectural patterns for ultra-low latency serverless APIs, D1 relational databases, KV storage, and Wrangler configuration.
+
+## Procedural Workflow
+
+### 1. Project Scaffolding & Wrangler Config
+Structure `wrangler.jsonc` or `wrangler.toml` with strict environment bindings:
+```jsonc
+{
+  "$schema": "node_modules/wrangler/config-schema.json",
+  "name": "edge-api",
+  "main": "src/index.ts",
+  "compatibility_date": "2024-09-23",
+  "compatibility_flags": ["nodejs_compat"],
+  "d1_databases": [
+    {
+      "binding": "DB",
+      "database_name": "prod-db",
+      "database_id": "xxxx-xxxx"
+    }
+  ],
+  "kv_namespaces": [
+    {
+      "binding": "CACHE",
+      "id": "yyyy-yyyy"
+    }
+  ]
+}
+```
+
+### 2. Edge Request Handling
+Use typed `Env` interfaces and native `fetch` handlers:
+```typescript
+export interface Env {
+  DB: D1Database;
+  CACHE: KVNamespace;
+  API_SECRET: string;
+}
+
+export default {
+  async fetch(request: Request, env: Env, ctx: ExecutionContext): Promise<Response> {
+    const url = new URL(request.url);
+    if (request.method === "OPTIONS") {
+      return handleCors(request);
+    }
+    // Execution context for background tasks that shouldn't block response
+    ctx.waitUntil(logAnalytics(request, env));
+    return new Response(JSON.stringify({ status: "ok" }), {
+      headers: { "Content-Type": "application/json" }
+    });
+  }
+};
+```
+
+### 3. Edge Storage Patterns
+- **Cloudflare KV**: High-read, low-write caching (eventually consistent). Ideal for session tokens, feature flags, and redirect maps.
+- **Cloudflare D1**: Serverless SQLite at the edge. Always use parameterized queries (`env.DB.prepare("SELECT * FROM users WHERE id = ?").bind(id).first()`).
+- **Cloudflare R2**: Zero-egress S3-compatible object storage.
+
+## Verification Checklist
+- [ ] `compatibility_date` pinned to a modern version
+- [ ] Secrets managed via `wrangler secret put`, never hardcoded
+- [ ] Background telemetry wrapped in `ctx.waitUntil`
+- [ ] D1 queries use parameterized bindings to prevent SQL injection

package/skills/gemini-grounding/SKILL.md

@@ -0,0 +1,37 @@
+---
+name: gemini-grounding
+description: >-
+  Use this skill when verifying dynamic facts, researching live documentation, fact-checking technical claims, or integrating Google Search grounding into Gemini agent reasoning workflows.
+---
+
+# Gemini Search Grounding & Dynamic Fact Verification
+
+## Overview
+Gemini frontier models feature native **Google Search Grounding**, enabling agents to supplement static training weights with real-time web citations, current API documentation, and package release notes. This skill outlines best practices for search grounding, citation verification, and hallucination elimination.
+
+## Procedural Workflow
+
+### 1. Identify Grounding Triggers
+Activate search grounding when:
+- Querying rapidly evolving SDKs, library APIs, or breaking versions released after model cutoffs.
+- Verifying deployment status, cloud service outages, or public CVE advisories.
+- Researching latest framework releases (e.g., Next.js canary features, Tailwind v4, React 19).
+
+### 2. Search Query Formulation
+Formulate targeted search queries:
+- **Exact Syntax Match**: Use quotes for exact error strings or function signatures.
+- **Official Domain Prioritization**: Target authoritative documentation:
+  - `site:github.com` for issue threads and release tags.
+  - `site:npmjs.com` or `site:pypi.org` for version numbers and dependencies.
+  - Official vendor docs (`docs.antigravity.google`, `developer.mozilla.org`).
+
+### 3. Verification & Citation Attribution
+When incorporating search findings into code:
+1. **Cross-Check with Active Code**: Never assume an external snippet works as-is; inspect local types and configurations first.
+2. **Clickable Links**: Link external references using markdown links in documentation and artifacts.
+3. **Zero-Trust Validation**: Verify any third-party code against local linters (`npm test` or typecheckers).
+
+## Verification Checklist
+- [ ] Claims backed by verifiable, recent documentation
+- [ ] No hallucinated imports or deprecated APIs
+- [ ] External references properly attributed

package/skills/kubernetes-operator/SKILL.md

@@ -0,0 +1,82 @@
+---
+name: kubernetes-operator
+description: >-
+  Use this skill when authoring Kubernetes manifests, configuring Helm charts, setting up Horizontal Pod Autoscalers (HPA), or troubleshooting container cluster deployments.
+---
+
+# Kubernetes Cluster & Workload Operations
+
+## Overview
+This skill guides the agent in writing declarative, production-ready Kubernetes manifests, configuring health probes, resource constraints, ingress controllers, and rolling update strategies.
+
+## Procedural Workflow
+
+### 1. Hardened Deployment Manifest Pattern
+Always configure resource limits, security contexts, and liveness/readiness probes:
+```yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: api-service
+  labels:
+    app.kubernetes.io/name: api-service
+spec:
+  replicas: 3
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxSurge: 1
+      maxUnavailable: 0
+  selector:
+    matchLabels:
+      app: api-service
+  template:
+    metadata:
+      labels:
+        app: api-service
+    spec:
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 10001
+      containers:
+        - name: app
+          image: myregistry.azurecr.io/api-service:v1.0.0
+          securityContext:
+            readOnlyRootFilesystem: true
+            allowPrivilegeEscalation: false
+          resources:
+            requests:
+              cpu: "100m"
+              memory: "128Mi"
+            limits:
+              cpu: "500m"
+              memory: "512Mi"
+          ports:
+            - containerPort: 8080
+          readinessProbe:
+            httpGet:
+              path: /health/ready
+              port: 8080
+            initialDelaySeconds: 5
+            periodSeconds: 10
+          livenessProbe:
+            httpGet:
+              path: /health/live
+              port: 8080
+            initialDelaySeconds: 15
+            periodSeconds: 20
+```
+
+### 2. Auto-scaling & Ingress
+- **HorizontalPodAutoscaler (HPA)**: Target CPU (e.g. 70%) and Memory utilization before traffic spikes.
+- **Ingress with TLS**: Annotate with cert-manager (`cert-manager.io/cluster-issuer: letsencrypt-prod`) for automated SSL lifecycle.
+
+### 3. Triage & Debugging Commands
+- Inspect crash loops: `kubectl logs -l app=api-service --tail=100 -p` (previous container logs).
+- Inspect pod events: `kubectl describe pod <pod-name>`.
+
+## Verification Checklist
+- [ ] Non-root security context configured (`runAsNonRoot: true`)
+- [ ] Both readiness and liveness probes defined
+- [ ] Memory limits defined to prevent cluster OOM killer cascades
+- [ ] Rolling update configured with zero downtime (`maxUnavailable: 0`)

package/skills/stripe-integration/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: stripe-integration
+description: >-
+  Use this skill when implementing Stripe checkout sessions, managing subscription billing lifecycles, verifying webhook signatures, or configuring customer billing portals.
+---
+
+# Stripe Payments & Subscription Architecture
+
+## Overview
+This skill guides the implementation of PCI-compliant payment flows, webhook signature verification, idempotent charge processing, and customer portal session generation using the official Stripe SDK.
+
+## Procedural Workflow
+
+### 1. Robust Webhook Signature Verification
+Never process webhooks without verifying the cryptographic signature against your endpoint secret:
+```typescript
+import Stripe from "stripe";
+
+const stripe = new Stripe(process.env.STRIPE_SECRET_KEY!, {
+  apiVersion: "2024-06-20",
+});
+
+export async function handleStripeWebhook(rawBody: string | Buffer, signature: string) {
+  let event: Stripe.Event;
+  try {
+    event = stripe.webhooks.constructEvent(
+      rawBody,
+      signature,
+      process.env.STRIPE_WEBHOOK_SECRET!
+    );
+  } catch (err: any) {
+    throw new Error(`Webhook signature verification failed: ${err.message}`);
+  }
+
+  // Handle idempotent events using database transaction
+  switch (event.type) {
+    case "checkout.session.completed":
+      await handleCheckoutCompleted(event.data.object as Stripe.Checkout.Session);
+      break;
+    case "customer.subscription.updated":
+    case "customer.subscription.deleted":
+      await syncSubscriptionStatus(event.data.object as Stripe.Subscription);
+      break;
+  }
+}
+```
+
+### 2. Idempotency & Concurrency Safety
+- Always store `event.id` in an `idempotency_keys` table or set a unique constraint. If Stripe retries a webhook, discard duplicates immediately.
+- Use `client_reference_id` or `metadata` to link Stripe customers with your internal user IDs.
+
+### 3. Customer Billing Portal
+Generate pre-authenticated portal sessions so users can update payment methods and invoices self-service without custom frontend form logic:
+```typescript
+const portalSession = await stripe.billingPortal.sessions.create({
+  customer: stripeCustomerId,
+  return_url: `${process.env.NEXT_PUBLIC_APP_URL}/dashboard/billing`,
+});
+```
+
+## Verification Checklist
+- [ ] Raw body buffer preserved for webhook cryptographic verification
+- [ ] Idempotency key checked before applying database mutations
+- [ ] Webhook handler returns HTTP 200 promptly before long-running async tasks
+- [ ] Stripe secret keys read strictly from environment variables

package/skills/supabase-architect/SKILL.md

@@ -0,0 +1,53 @@
+---
+name: supabase-architect
+description: >-
+  Use this skill when designing Supabase database schemas, writing Row Level Security (RLS) policies, setting up pgvector AI embeddings, or configuring Supabase Edge Functions.
+---
+
+# Supabase Architecture & Security Playbook
+
+## Overview
+Supabase provides a powerful managed backend powered by PostgreSQL. This skill guides the agent in crafting bulletproof Row Level Security (RLS) policies, configuring pgvector for semantic search and AI embeddings, and deploying performant Supabase Edge Functions.
+
+## Procedural Workflow
+
+### 1. Row Level Security (RLS) Defense-in-Depth
+Never leave a table with RLS disabled in production:
+```sql
+-- 1. Always enable RLS on newly created tables
+ALTER TABLE documents ENABLE ROW LEVEL SECURITY;
+
+-- 2. Enforce strict tenant isolation or user ownership
+CREATE POLICY "Users can only read their own documents"
+ON documents
+FOR SELECT
+USING (auth.uid() = user_id);
+
+CREATE POLICY "Users can only insert their own documents"
+ON documents
+FOR INSERT
+WITH CHECK (auth.uid() = user_id);
+```
+
+### 2. Semantic Search & Vector Embeddings (`pgvector`)
+When storing AI embeddings in PostgreSQL:
+1. Enable extension: `CREATE EXTENSION IF NOT EXISTS vector;`
+2. Create vector column matching model dimensions (e.g., 768 or 1536):
+   ```sql
+   ALTER TABLE documents ADD COLUMN embedding vector(768);
+   ```
+3. Create an HNSW index for fast similarity lookups:
+   ```sql
+   CREATE INDEX ON documents USING hnsw (embedding vector_cosine_ops);
+   ```
+4. Define match RPC functions with inner product or cosine distance queries.
+
+### 3. Realtime Channels & Subscriptions
+- Filter broadcasts server-side using Postgres row-level filters (`eq`, `in`) to prevent client-side data leaks.
+- Ensure sensitive columns are omitted or masked in realtime publication sets.
+
+## Verification Checklist
+- [ ] RLS explicitly enabled on every table
+- [ ] RLS policies tested against unauthenticated and cross-tenant tokens
+- [ ] Vector index created with appropriate similarity operator (`vector_cosine_ops`)
+- [ ] Edge functions handle CORS headers and verify JWT signatures