gkt-node 3.3.0

package/README.md

@@ -0,0 +1,89 @@
+# gkt-node — GravityKit CLI (npx)
+
+> The AI-Native Software House in a Box — install via `npx`, no Python required.
+
+## Quick Start
+
+```bash
+# Install all skills for all supported IDEs
+npx gkt-node init
+
+# Install for a specific IDE
+npx gkt-node init antigravity
+npx gkt-node init cursor
+npx gkt-node init windsurf
+npx gkt-node init cline
+npx gkt-node init kilocode
+npx gkt-node init copilot
+npx gkt-node init kiro
+```
+
+> **Tip:** After global install (`npm i -g gkt-node`), you can use either `gkt` or `gkt-node` as the command.
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `npx gkt-node init [target]` | Install GravityKit skills & workflows into current directory |
+| `npx gkt-node init [target] --group <name>` | Install a specific skill group |
+| `npx gkt-node groups` | List available skill groups |
+| `npx gkt-node list` | List installed AI Agents (requires `gkt-node init` first) |
+| `npx gkt-node doctor` | Check environment health (Python, Node, Git, npm) |
+| `npx gkt-node version` | Show current version |
+| `npx gkt-node help` | Show help message |
+
+## Init Targets
+
+### By IDE
+
+| Target | Output Directory | IDE |
+|--------|-----------------|-----|
+| `all` (default) | All below | All supported IDEs |
+| `antigravity` | `.agent/` | Antigravity (Gemini) |
+| `cursor` | `.cursor/rules/` | Cursor |
+| `windsurf` | `.windsurf/rules/` | Windsurf |
+| `cline` | `.clinerules/` | Cline |
+| `kilocode` | `.kilocode/rules/` | Kilo Code |
+| `copilot` | `.github/instructions/` | GitHub Copilot |
+| `kiro` | `.kiro/` | Kiro (skills, hooks, steering, specs) |
+
+### By Skill Group
+
+Instead of installing all 500+ skills, pick a focused group:
+
+```bash
+npx gkt-node init general-dev           # General development
+npx gkt-node init n8n-dev               # n8n workflow development
+npx gkt-node init nocobase-dev          # NocoBase plugin development
+npx gkt-node init security-audit        # Security & pentesting
+npx gkt-node init seo-marketing         # SEO & content marketing
+
+# Combine IDE + group
+npx gkt-node init antigravity --group n8n-dev
+npx gkt-node init all --group general-dev
+```
+
+Run `npx gkt-node groups` to see all available groups with skill/workflow counts.
+
+## How It Works
+
+1. **Bundled assets** — skills, workflows, and IDE configs are included in the package (offline-capable)
+2. **Fallback download** — if bundled assets are missing, downloads from GitHub automatically
+3. **Copies** them into the appropriate directories in your project
+
+No external npm dependencies — uses only Node.js built-ins.
+
+## Requirements
+
+- **Node.js** ≥ 16
+
+## Also Available via pip
+
+```bash
+pip install gkt
+gkt init
+```
+
+## License
+
+MIT

package/assets/.agent/brain/agent_index.json

@@ -0,0 +1,208 @@
+{
+    "agents": {
+        "leader": {
+            "role": "Team Lead — Orchestrates the entire team with per-phase reporting",
+            "when_to_call": "Complex tasks that need multiple agents. User approves each phase before proceeding.",
+            "output": "Delegates tasks to specialized agents, reports per phase, manages QA loop (max 3 retries)",
+            "skills": [
+                "progress-tracker",
+                "codebase-navigator"
+            ],
+            "orchestration": {
+                "phases": [
+                    "Planning",
+                    "Architecture",
+                    "Design",
+                    "Development",
+                    "QA & Bug Fix",
+                    "Launch"
+                ],
+                "qa_loop": {
+                    "max_retries": 3,
+                    "on_failure": "Call meta-thinker + planner to rethink approach",
+                    "on_max_retries": "Stop and report to Manager with detailed failure analysis"
+                }
+            }
+        },
+        "quickstart": {
+            "role": "Autopilot — Fully automated project build from idea to production",
+            "when_to_call": "Quick MVPs, prototypes, or when user wants zero-approval fast build",
+            "output": "Complete project with QA, security audit, docs. Final report with all results.",
+            "skills": [],
+            "orchestration": {
+                "phases": [
+                    "Auto-Plan",
+                    "Architecture",
+                    "Design",
+                    "Development",
+                    "QA & Auto-Fix",
+                    "Polish"
+                ],
+                "qa_loop": {
+                    "max_retries": 5,
+                    "on_failure": "Call meta-thinker + planner to rethink approach",
+                    "on_max_retries": "Log unresolved bug, continue with remaining work"
+                }
+            }
+        },
+        "planner": {
+            "role": "Analyzes requirements, writes PRD, breaks down tasks",
+            "when_to_call": "New features, project kickoff, requirement analysis",
+            "output": "PRD.md, task breakdown, user stories, estimation",
+            "skills": [
+                "task-estimator",
+                "user-story-generator",
+                "project-management-assistant",
+                "project-scaffolder"
+            ]
+        },
+        "architect": {
+            "role": "Systems Design — Database, API, Architecture",
+            "when_to_call": "Database schema, API design, system diagrams, tech decisions",
+            "output": "schema.sql, api_spec.yaml, architecture diagrams",
+            "skills": [
+                "db-designer",
+                "api-designer",
+                "system-diagrammer",
+                "system-strategist",
+                "strategic-planning-advisor"
+            ]
+        },
+        "designer": {
+            "role": "UI/UX Design System and Assets",
+            "when_to_call": "UI components, color palette, typography, wireframes, responsive design",
+            "output": "Design system, component specs, color palette, wireframes",
+            "skills": [
+                "ui-ux-pro-max",
+                "color-palette-generator",
+                "product-designer"
+            ]
+        },
+        "frontend-dev": {
+            "role": "Frontend Developer — Component, Layout, State Management",
+            "when_to_call": "React/Vue/Tailwind components, pages, state logic, responsive layout",
+            "output": "Components, pages, hooks, styles, state management code",
+            "skills": []
+        },
+        "backend-dev": {
+            "role": "Backend Developer — API, DB Queries, Business Logic",
+            "when_to_call": "API endpoints, database queries, authentication, server logic",
+            "output": "API routes, controllers, models, middleware, services",
+            "skills": [
+                "test-generator"
+            ]
+        },
+        "mobile-dev": {
+            "role": "Mobile Developer — iOS/Android (React Native/Expo)",
+            "when_to_call": "Mobile screens, native features, navigation, app store deployment",
+            "output": "React Native/Expo screens, navigation config, native module setup",
+            "skills": [
+                "mobile-wizard"
+            ]
+        },
+        "devops": {
+            "role": "DevOps — Docker, CI/CD, Cloud Deployment",
+            "when_to_call": "Docker setup, CI/CD pipelines, deployment, cloud config",
+            "output": "Dockerfile, docker-compose.yml, GitHub Actions, deploy scripts",
+            "skills": [
+                "docker-wizard",
+                "ci-cd-setup",
+                "reliability-engineer"
+            ]
+        },
+        "qa-engineer": {
+            "role": "QA — Test Cases, Automation, Performance, Bug Reporting",
+            "when_to_call": "Test writing, test automation, performance testing, bug triage",
+            "output": "Test suites, test reports, bug reports",
+            "skills": [
+                "test-generator"
+            ]
+        },
+        "security-engineer": {
+            "role": "Security — Audit, Pen-Test, Vulnerability Scanning",
+            "when_to_call": "Security audit, vulnerability scan, OWASP check, secret detection",
+            "output": "Security report, vulnerability list, fix recommendations",
+            "skills": [
+                "security-scanner"
+            ]
+        },
+        "tech-writer": {
+            "role": "Documentation & API Refs",
+            "when_to_call": "README, API docs, user guides, changelog",
+            "output": "README.md, API documentation, user guides",
+            "skills": [
+                "doc-generator",
+                "readme-generator"
+            ]
+        },
+        "seo-specialist": {
+            "role": "SEO — Search Engine Optimization",
+            "when_to_call": "Meta tags, Schema.org, sitemap, performance, Core Web Vitals",
+            "output": "SEO audit report, meta tag fixes, schema markup",
+            "skills": [
+                "seo-analyzer"
+            ]
+        },
+        "meta-thinker": {
+            "role": "Creative Advisor — Ideas, Brainstorming, Vision",
+            "when_to_call": "Brainstorming, product vision, monetization, competitive analysis",
+            "output": "Idea reports, strategy docs, competitor analysis",
+            "skills": [
+                "meta-thinker",
+                "competitor-analyzer",
+                "market-trend-analyst"
+            ]
+        },
+        "knowledge-guide": {
+            "role": "Code Explainer, Note Taker, Handoff Specialist",
+            "when_to_call": "Explain codebase to new team members, capture notes, handoff docs",
+            "output": "Code explanations, handoff documents, context summaries",
+            "skills": [
+                "knowledge-guide",
+                "brain-manager",
+                "journal-manager"
+            ]
+        },
+        "code-reviewer": {
+            "role": "Code Reviewer — Automated code quality review",
+            "when_to_call": "Code quality check, naming review, security scan, performance audit",
+            "output": "Review report with issues (critical/warning/info) and quality score (A-F)",
+            "skills": [
+                "code-reviewer"
+            ]
+        },
+        "release-manager": {
+            "role": "Release Manager — Changelog, versioning, release notes",
+            "when_to_call": "Version bump, changelog generation, release preparation, tagging",
+            "output": "CHANGELOG.md, version bump, release notes, git tags",
+            "skills": [
+                "release-manager"
+            ]
+        },
+        "researcher": {
+            "role": "Researcher — Market analysis, web search, trend discovery",
+            "when_to_call": "Research competitors, validate ideas, discover trends, find best practices, gather information",
+            "output": "research_report.md, market-analysis.md, competitor data, web search results",
+            "skills": [
+                "market-trend-analyst",
+                "competitor-analyzer"
+            ],
+            "capabilities": {
+                "web_search": "DuckDuckGo API (zero dependencies, stdlib only)",
+                "modes": [
+                    "--compact (token-efficient)",
+                    "--json",
+                    "--output (markdown)",
+                    "--instant-only"
+                ]
+            }
+        }
+    },
+    "infrastructure": {
+        "context-router": "Universal data query router — use before reading raw data files. Saves tokens by returning only matching entries.",
+        "template-marketplace": "Pre-built project templates (SaaS, E-commerce, Blog, API, Landing, Dashboard, Mobile). Used by quickstart and leader."
+    },
+    "handoff_template": {
+        "format": "## Handoff to {agent}\nContext: {one_line_summary}\nTask: {specific_task}\nFiles: {relevant_files_from_codebase_index}\nConstraints: {tech_stack_and_rules}\nExpected Output: {what_to_produce}"
+    }
+}

package/assets/.agent/brain/project_context.json

@@ -0,0 +1,31 @@
+{
+    "project": {
+        "name": "",
+        "description": "",
+        "tech_stack": [],
+        "repo_url": "",
+        "created_at": ""
+    },
+    "architecture": {
+        "pattern": "",
+        "database": "",
+        "api_style": "",
+        "auth_method": "",
+        "hosting": "",
+        "notes": []
+    },
+    "decisions": [],
+    "conventions": {
+        "naming": "",
+        "file_structure": "",
+        "git_branch_strategy": "",
+        "commit_format": "",
+        "code_style": ""
+    },
+    "known_issues": [],
+    "current_sprint": {
+        "goal": "",
+        "status": "",
+        "tasks": []
+    }
+}

package/assets/.agent/skills/ab-test-setup/SKILL.md

@@ -0,0 +1,232 @@
+---
+name: ab-test-setup
+description: Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.
+---
+
+# A/B Test Setup
+
+## 1️⃣ Purpose & Scope
+
+Ensure every A/B test is **valid, rigorous, and safe** before a single line of code is written.
+
+- Prevents "peeking"
+- Enforces statistical power
+- Blocks invalid hypotheses
+
+---
+
+## 2️⃣ Pre-Requisites
+
+You must have:
+
+- A clear user problem
+- Access to an analytics source
+- Roughly estimated traffic volume
+
+### Hypothesis Quality Checklist
+
+A valid hypothesis includes:
+
+- Observation or evidence
+- Single, specific change
+- Directional expectation
+- Defined audience
+- Measurable success criteria
+
+---
+
+### 3️⃣ Hypothesis Lock (Hard Gate)
+
+Before designing variants or metrics, you MUST:
+
+- Present the **final hypothesis**
+- Specify:
+  - Target audience
+  - Primary metric
+  - Expected direction of effect
+  - Minimum Detectable Effect (MDE)
+
+Ask explicitly:
+
+> “Is this the final hypothesis we are committing to for this test?”
+
+**Do NOT proceed until confirmed.**
+
+---
+
+### 4️⃣ Assumptions & Validity Check (Mandatory)
+
+Explicitly list assumptions about:
+
+- Traffic stability
+- User independence
+- Metric reliability
+- Randomization quality
+- External factors (seasonality, campaigns, releases)
+
+If assumptions are weak or violated:
+
+- Warn the user
+- Recommend delaying or redesigning the test
+
+---
+
+### 5️⃣ Test Type Selection
+
+Choose the simplest valid test:
+
+- **A/B Test** – single change, two variants
+- **A/B/n Test** – multiple variants, higher traffic required
+- **Multivariate Test (MVT)** – interaction effects, very high traffic
+- **Split URL Test** – major structural changes
+
+Default to **A/B** unless there is a clear reason otherwise.
+
+---
+
+### 6️⃣ Metrics Definition
+
+#### Primary Metric (Mandatory)
+
+- Single metric used to evaluate success
+- Directly tied to the hypothesis
+- Pre-defined and frozen before launch
+
+#### Secondary Metrics
+
+- Provide context
+- Explain _why_ results occurred
+- Must not override the primary metric
+
+#### Guardrail Metrics
+
+- Metrics that must not degrade
+- Used to prevent harmful wins
+- Trigger test stop if significantly negative
+
+---
+
+### 7️⃣ Sample Size & Duration
+
+Define upfront:
+
+- Baseline rate
+- MDE
+- Significance level (typically 95%)
+- Statistical power (typically 80%)
+
+Estimate:
+
+- Required sample size per variant
+- Expected test duration
+
+**Do NOT proceed without a realistic sample size estimate.**
+
+---
+
+### 8️⃣ Execution Readiness Gate (Hard Stop)
+
+You may proceed to implementation **only if all are true**:
+
+- Hypothesis is locked
+- Primary metric is frozen
+- Sample size is calculated
+- Test duration is defined
+- Guardrails are set
+- Tracking is verified
+
+If any item is missing, stop and resolve it.
+
+---
+
+## Running the Test
+
+### During the Test
+
+**DO:**
+
+- Monitor technical health
+- Document external factors
+
+**DO NOT:**
+
+- Stop early due to “good-looking” results
+- Change variants mid-test
+- Add new traffic sources
+- Redefine success criteria
+
+---
+
+## Analyzing Results
+
+### Analysis Discipline
+
+When interpreting results:
+
+- Do NOT generalize beyond the tested population
+- Do NOT claim causality beyond the tested change
+- Do NOT override guardrail failures
+- Separate statistical significance from business judgment
+
+### Interpretation Outcomes
+
+| Result               | Action                                 |
+| -------------------- | -------------------------------------- |
+| Significant positive | Consider rollout                       |
+| Significant negative | Reject variant, document learning      |
+| Inconclusive         | Consider more traffic or bolder change |
+| Guardrail failure    | Do not ship, even if primary wins      |
+
+---
+
+## Documentation & Learning
+
+### Test Record (Mandatory)
+
+Document:
+
+- Hypothesis
+- Variants
+- Metrics
+- Sample size vs achieved
+- Results
+- Decision
+- Learnings
+- Follow-up ideas
+
+Store records in a shared, searchable location to avoid repeated failures.
+
+---
+
+## Refusal Conditions (Safety)
+
+Refuse to proceed if:
+
+- Baseline rate is unknown and cannot be estimated
+- Traffic is insufficient to detect the MDE
+- Primary metric is undefined
+- Multiple variables are changed without proper design
+- Hypothesis cannot be clearly stated
+
+Explain why and recommend next steps.
+
+---
+
+## Key Principles (Non-Negotiable)
+
+- One hypothesis per test
+- One primary metric
+- Commit before launch
+- No peeking
+- Learning over winning
+- Statistical rigor first
+
+---
+
+## Final Reminder
+
+A/B testing is not about proving ideas right.
+It is about **learning the truth with confidence**.
+
+If you feel tempted to rush, simplify, or “just try it” —
+that is the signal to **slow down and re-check the design**.

package/assets/.agent/skills/agent-evaluation/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: agent-evaluation
+description: "Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent."
+source: vibeship-spawner-skills (Apache 2.0)
+---
+
+# Agent Evaluation
+
+You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in
+production. You've learned that evaluating LLM agents is fundamentally different from
+testing traditional software—the same input can produce different outputs, and "correct"
+often has no single answer.
+
+You've built evaluation frameworks that catch issues before production: behavioral regression
+tests, capability assessments, and reliability metrics. You understand that the goal isn't
+100% test pass rate—it
+
+## Capabilities
+
+- agent-testing
+- benchmark-design
+- capability-assessment
+- reliability-metrics
+- regression-testing
+
+## Requirements
+
+- testing-fundamentals
+- llm-fundamentals
+
+## Patterns
+
+### Statistical Test Evaluation
+
+Run tests multiple times and analyze result distributions
+
+### Behavioral Contract Testing
+
+Define and test agent behavioral invariants
+
+### Adversarial Testing
+
+Actively try to break agent behavior
+
+## Anti-Patterns
+
+### ❌ Single-Run Testing
+
+### ❌ Only Happy Path Tests
+
+### ❌ Output String Matching
+
+## ⚠️ Sharp Edges
+
+| Issue | Severity | Solution |
+|-------|----------|----------|
+| Agent scores well on benchmarks but fails in production | high | // Bridge benchmark and production evaluation |
+| Same test passes sometimes, fails other times | high | // Handle flaky tests in LLM agent evaluation |
+| Agent optimized for metric, not actual task | medium | // Multi-dimensional evaluation to prevent gaming |
+| Test data accidentally used in training or prompts | critical | // Prevent data leakage in agent evaluation |
+
+## Related Skills
+
+Works well with: `multi-agent-orchestration`, `agent-communication`, `autonomous-agents`