0xray 2.0.0 → 2.1.0

package/.opencode/skills/code-review/SKILL.md

@@ -1,52 +0,0 @@
----
-source: framework
-name: code-review
-description: Perform comprehensive code quality assessment and provide improvement suggestions
-author: StrRay Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [review, quality, assessment, improvement]
-capabilities:
-  - assess_quality
-  - review_code
-  - suggest_improvements
-dependencies: []
-
-mcp:
-  code-review:
-    command: node
-    args: [node_modules/strray-ai/dist/mcps/knowledge-skills/code-review.server.js]
-  tools:
-    - analyze_code_quality
-    - review_pull_request
-    - check_best_practices
-
-agent_binding:
-  primary: code-reviewer
-  auto_invoke: true
-  invoke_on:
-    - pre_commit
-    - pr_review
----
-
-# Code Review Skill
-
-Provides automated code review capabilities with quality assessment and improvement suggestions.
-
-## Tools Available
-
-- **analyze_code_quality**: Analyze code quality metrics, identify issues, and provide improvement suggestions
-- **review_pull_request**: Review pull requests by analyzing changed files and providing comprehensive feedback
-- **check_best_practices**: Check adherence to coding best practices and standards
-
-## Usage
-
-This skill performs automated code reviews including:
-- Code quality analysis and metrics
-- Pull request review and feedback
-- Best practices compliance checking
-- Improvement recommendations and suggestions
-
-## Integration
-
-Activated for code review requests, pull request analysis, and quality assessments through the skills system.

package/.opencode/skills/content-creator/SKILL.md

@@ -1,38 +0,0 @@
----
-source: framework
-name: content-creator
-description: "SEO copywriter for content that ranks and converts in both Google and AI search engines"
-category: content
----
-
-# Content Creator Skill
-
-SEO copywriter specializing in content that ranks and converts for humans and AI search engines.
-
-## Brand Archetypes
-
-Adapt tone on command: Magician, Hero, Sage, Ruler, Everyman, Explorer, Innocent, Jester.
-Default: Professional-friendly-innovative.
-
-## SEO Content Rules
-
-- Primary keywords in H1, first 100 words, throughout
-- LSI/semantic keywords naturally integrated
-- H2-H4 structure with keyword-rich headings
-- Bullets, numbered lists, tables for scannability
-- E-E-A-T signals (author, dates, citations)
-- AI-citation friendly: clear lists, stats, examples
-- Meta descriptions: 150-160 chars, actionable
-
-## Content Types
-
-Blog posts (800-2000w), Product pages, Landing pages, Email sequences, Social posts, Meta descriptions & title tags
-
-## Copy Principles
-
-- Lead with benefit
-- Active voice
-- Tight sentences
-- Zero fluff
-- Strong CTAs
-- Social proof

package/.opencode/skills/database-engineer/SKILL.md

@@ -1,46 +0,0 @@
----
-source: framework
-name: database-engineer
-description: "Database engineer for schema design, query optimization, migrations, and SQL/NoSQL architecture"
-category: database
----
-
-# Database Engineer Skill
-
-Database specialist for architecture and optimization. Technical, precise, performance-oriented.
-
-## Database Systems
-
-PostgreSQL, MySQL, SQLite, SQL Server, MongoDB, Cassandra, Redis, DynamoDB, CockroachDB, TiDB, PlanetScale, Elasticsearch, Meilisearch
-
-## Schema Design
-
-- 3NF minimum normalization
-- Denormalize intentionally for read-heavy workloads
-- Use appropriate data types (no string for dates)
-- Soft deletes with deleted_at timestamps
-- Audit columns (created_at, updated_at, created_by)
-- Foreign key constraints for referential integrity
-
-## Query Optimization
-
-- Use EXPLAIN ANALYZE to find bottlenecks
-- Covering indexes for frequent queries
-- Avoid SELECT * — specify columns
-- Parameterized queries only (prevent SQL injection)
-- Cursor-based pagination, not OFFSET
-
-## Migration Strategy
-
-- Wrap in transactions
-- Batch backfills for large data changes
-- Additive columns first (drop later)
-- Concurrent index creation (CREATE INDEX CONCURRENTLY)
-- Deprecation periods before removing columns
-
-## Performance Targets
-
-- < 100ms OLTP queries
-- < 1s OLAP queries
-- 10-50 connection pool size
-- Zero-downtime migrations

package/.opencode/skills/devops-engineer/SKILL.md

@@ -1,49 +0,0 @@
----
-source: framework
-name: devops-engineer
-description: "DevOps engineer for CI/CD, infrastructure as code, containers, cloud deployment, and operational reliability"
-category: devops
----
-
-# DevOps Engineer Skill
-
-DevOps specialist for infrastructure, CI/CD, and operational reliability. Reliability-focused, security-conscious, automate everything.
-
-## CI/CD Best Practices
-
-- Conventional commits for trigger control
-- Branch protection rules
-- Matrix builds for multi-platform testing
-- Dependency caching for faster builds
-- Progressive rollout (canary / blue-green)
-- Automated rollback procedures
-
-## Infrastructure as Code
-
-- Modular, reusable components
-- Remote state + locking (Terraform)
-- Drift detection
-- GitOps (ArgoCD/Flux)
-- Secrets separation (Vault/AWS Secrets Manager)
-
-## Containers
-
-- Helm/Kustomize for Kubernetes
-- Health checks and readiness probes
-- Resource limits and PDBs
-- Service mesh for inter-service communication
-
-## Monitoring
-
-- Logs / Metrics / Traces (three pillars)
-- Structured JSON logging
-- OpenTelemetry for instrumentation
-- SLO-based alerting (not threshold-based)
-- Runbooks for incident response
-
-## Cloud Security
-
-- Least privilege IAM
-- VPC / private subnets
-- Encryption at rest and in transit
-- CI/CD pipeline scanning

package/.opencode/skills/enforcer/SKILL.md

@@ -1,37 +0,0 @@
----
-source: framework
-name: enforcer
-description: Codex compliance validation and error prevention
-author: StrRay Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [quality, enforcer]
-capabilities:
-  - validate_compliance
-  - prevent_errors
-  - enforce_codex
-dependencies: []
-
-mcp:
-  enforcer:
-    command: node
-    args: [node_modules/strray-ai/dist/mcps/enforcer-tools.server.js]
----
-
-# Enforcer Skill
-
-Codex compliance validation and error prevention.
-
-## Tools Available
-
-- **code_compliance**: Code compliance
-- **error_prevention**: Error prevention
-- **quality_validation**: Quality validation
-
-## Usage
-
-This skill provides quality capabilities for enforcer functionality.
-
-## Integration
-
-Activated when quality capabilities are requested through the skills system.

package/.opencode/skills/framework-compliance-audit/SKILL.md

@@ -1,37 +0,0 @@
----
-source: framework
-name: framework-compliance-audit
-description: Framework compliance auditing and validation
-author: StrRay Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [compliance, framework, compliance, audit]
-capabilities:
-  - audit_compliance
-  - validate_framework
-  - generate_report
-dependencies: []
-
-mcp:
-  framework-compliance-audit:
-    command: node
-    args: [node_modules/strray-ai/dist/mcps/framework-compliance-audit.server.js]
----
-
-# Framework Compliance Audit Skill
-
-Framework compliance auditing and validation.
-
-## Tools Available
-
-- **compliance_auditing**: Compliance auditing
-- **framework_validation**: Framework validation
-- **audit_reporting**: Audit reporting
-
-## Usage
-
-This skill provides compliance capabilities for framework compliance audit functionality.
-
-## Integration
-
-Activated when compliance capabilities are requested through the skills system.

package/.opencode/skills/frontend-engineer/SKILL.md

@@ -1,49 +0,0 @@
----
-source: framework
-name: frontend-engineer
-description: "Frontend engineer for React/Vue/Angular/Svelte, responsive design, accessibility, and performance"
-category: frontend
----
-
-# Frontend Engineer Skill
-
-Modern UI development specialist. User-experience focused, accessible, performant.
-
-## Framework Best Practices
-
-- Functional components + hooks/composition API
-- Component composition over inheritance
-- TypeScript for all new code
-- Small, focused components
-- Memoization for expensive computations
-
-## Accessibility (WCAG 2.1 AA)
-
-- Semantic HTML elements
-- ARIA labels for interactive elements
-- Full keyboard navigation
-- 4.5:1 text contrast ratio
-- Form labels associated with inputs
-- Alt text for all images
-
-## Performance
-
-- LCP < 2.5s, INP < 200ms, CLS < 0.1
-- Code splitting and lazy loading
-- WebP/AVIF images
-- Bundle < 200KB initial load
-- Font preloading
-
-## State Management
-
-- Local state for UI-only concerns
-- Global state for cross-component data
-- Normalized data structures
-- Optimistic updates for perceived performance
-
-## CSS
-
-- CSS-in-JS / Tailwind / CSS Modules
-- Mobile-first responsive design
-- CSS custom properties for theming
-- Dark mode support

package/.opencode/skills/frontend-ui-ux-engineer/SKILL.md

@@ -1,41 +0,0 @@
----
-source: framework
-name: frontend-ui-ux-engineer
-description: "Frontend UI/UX engineer for visual design, typography, accessibility, and user experience"
-category: design
----
-
-# Frontend UI/UX Engineer Skill
-
-UI/UX design specialist. User-experience focused, accessible, visually appealing.
-
-## Design Principles
-
-- Golden ratio for proportions
-- 4px-based spacing system
-- Visual hierarchy through size, weight, and color
-- Contrast ratios: 4.5:1 text, 3:1 graphics
-- Color theory for cohesive palettes
-
-## Typography
-
-- Limit to 2-3 font families
-- Establish type scale (h1-h6 with consistent ratios)
-- Line height 1.4-1.6 for body text
-- Max line width 65-75 characters
-
-## Accessibility (WCAG 2.1 AA)
-
-- Semantic HTML
-- ARIA attributes where semantic HTML isn't enough
-- Full keyboard navigation with visible focus states
-- Screen reader compatibility
-- Respect prefers-reduced-motion
-
-## UX Best Practices
-
-- Clear, action-oriented CTAs
-- Consistent navigation patterns
-- Loading states and skeleton screens
-- Error prevention and recovery
-- Mobile-first responsive design

package/.opencode/skills/git-workflow/SKILL.md

@@ -1,37 +0,0 @@
----
-source: framework
-name: git-workflow
-description: Git workflow management and collaboration tools
-author: StrRay Framework
-version: 1.0.0
-schema_version: "1.0"
-tags: [collaboration, git, workflow]
-capabilities:
-  - manage_branches
-  - create_commits
-  - handle_pull_requests
-dependencies: []
-
-mcp:
-  git-workflow:
-    command: node
-    args: [node_modules/strray-ai/dist/mcps/knowledge-skills/git-workflow.server.js]
----
-
-# Git Workflow Skill
-
-Git workflow management and collaboration tools.
-
-## Tools Available
-
-- **git_workflows**: Git workflows
-- **collaboration_tools**: Collaboration tools
-- **version_control**: Version control
-
-## Usage
-
-This skill provides collaboration capabilities for git workflow functionality.
-
-## Integration
-
-Activated when collaboration capabilities are requested through the skills system.

package/.opencode/skills/growth-strategist/SKILL.md

@@ -1,48 +0,0 @@
----
-source: framework
-name: growth-strategist
-description: "Marketing strategist for campaign strategy, market analysis, brand positioning, and conversion optimization"
-category: content
----
-
-# Growth Strategist Skill
-
-Strategic marketing expert focused on growth and conversion. Professional, strategic, actionable tone. Zero fluff.
-
-## Landing Page Optimization
-
-The "Don't Make Me Think" Principle (Steve Krug):
-- Users scan, don't read. Make it obvious.
-- 3 seconds to understand value proposition above the fold.
-- Each section should answer: "Why should I care?"
-
-Essential Landing Page Sections:
-1. HERO: Headline (hook), Subheadline (explain), CTA button
-2. SOCIAL PROOF: Logos, testimonials, stats
-3. PROBLEM/PAIN: Acknowledge user struggle
-4. SOLUTION: How product solves it
-5. BENEFITS vs FEATURES: Lead with benefits
-6. HOW IT WORKS: Simple 1-2-3 steps
-7. CTA: Strong call-to-action (action verb + urgency)
-8. RISK REVERSAL: Guarantee, trial, testimonials
-9. FAQ: Address objections
-
-## Conversion Triggers
-
-- Action verbs: Get, Start, Try, Download, Join, Book
-- Urgency: "Limited time", "Only X left", "Today only"
-- Scarcity: "Enrollment closes", "spots available"
-- Social proof: "Join 10,000+ users", "4.9/5 rating"
-- Risk reversal: "30-day guarantee", "No credit card required"
-
-## Strategic Framework
-
-1. Market Analysis (target audience, size, competitive landscape, SWOT)
-2. Positioning Strategy (UVP, differentiation, messaging hierarchy, brand voice)
-3. Channel Strategy (organic, paid, email, partnerships)
-4. Campaign Development (objectives, messages, channel mix, KPIs)
-5. Growth Strategy (funnel optimization, retention/LTV, scaling, attribution)
-
-## Output Format
-
-Executive summary, data-backed recommendations, action items with timelines, budget guidance, KPIs.

package/.opencode/skills/hermes-agent/SKILL.md

@@ -1,212 +0,0 @@
----
-name: hermes-agent
-description: Manage xray framework from Hermes Agent via the native strray-hermes plugin. Covers the 4 plugin tools (validate, codex_check, health, hooks), lifecycle hooks, slash commands, bridge architecture, and CLI fallback.
-version: 2.1.0
-author: xray
-metadata:
-  hermes:
-    tags: [xray, Plugin, Validation, Codex, GitHooks, Bridge]
-    related_skills: []
----
-
-# xray Hermes Plugin (strray-hermes)
-
-Native Hermes plugin providing xray framework integration — quality gates, codex enforcement, git hooks, and full pre/post processing pipeline. Runs via a Node.js bridge to compiled framework components.
-
-## When to Use
-
-- User asks about xray health, validation, or codex checks
-- User wants to install/manage git hooks for automated enforcement
-- User asks about the plugin's tools, hooks, or slash commands
-- User asks about bridge errors or framework not loading
-- User wants to validate files before committing or pushing
-
-## Plugin Architecture
-
-```
-~/.hermes/plugins/strray-hermes/
-├── __init__.py         # Plugin registration, hooks, slash commands
-├── tools.py            # 4 tool handlers (validate, codex_check, health, hooks)
-├── schemas.py          # JSON schemas the LLM sees
-├── bridge.mjs          # Node.js bridge to compiled xray framework
-├── plugin.yaml         # Plugin metadata (name, version, tools, hooks)
-├── types.py            # TypeScript-equivalent type definitions
-├── after-install.md    # Post-install instructions
-└── test_plugin.py      # Tests
-```
-
-**Bridge protocol:** JSON over stdin/stdout to `bridge.mjs` (Node.js). The bridge lazy-loads compiled framework modules from `dist/`:
-- `dist/plugin/quality-gate.js` — codex violation detection
-- `dist/processors/processor-manager.js` — pre/post processor pipeline
-- `dist/state/state-manager.js` — persistent state
-- `dist/core/features-config.js` — feature flags
-
-**Fallback:** When bridge is unavailable, tools fall back to `npx xray` CLI commands.
-
-**Config path resolution:** `STRRAY_CONFIG_DIR/` > `.strray/` > `.opencode/strray/` > built-in defaults.
-
-## 4 Tools
-
-### strray_validate
-
-Run pre-commit validation on files. Uses bridge quality gate + processor pipeline, falls back to CLI.
-
-```
-strray_validate(files=["src/my-module.ts"], operation="commit")
-strray_validate(files=["src/auth.ts", "src/auth.test.ts"], operation="modify")
-```
-
-Parameters:
-- `files` (required, array of strings) — file paths to validate
-- `operation` (string) — commit, create, modify, refactor (default: commit)
-
-Returns: pass/fail with per-file results and violations.
-
-### strray_codex_check
-
-Validate code against the 60-term Universal Development Codex. Checks error-handling, type-safety, performance, security, architecture.
-
-```
-strray_codex_check(code="const x: any = foo()", operation="create")
-strray_codex_check(code=snippet, operation="modify", focus_areas=["security", "error-handling"])
-```
-
-Parameters:
-- `code` (string) — code snippet to check. If omitted, returns framework health instead.
-- `operation` (required, string) — create, modify, refactor
-- `focus_areas` (array) — error-handling, type-safety, performance, security, architecture
-
-Returns: violations list with actionable remediation.
-
-### strray_health
-
-Framework health check. Returns version, loaded components, project root.
-
-```
-strray_health()
-```
-
-Returns: framework status, version, component availability, node version.
-
-### strray_hooks
-
-Manage xray git hooks (install, uninstall, list, status).
-
-```
-strray_hooks(action="install")
-strray_hooks(action="status")
-strray_hooks(action="list")
-strray_hooks(action="uninstall", hooks=["pre-commit"])
-```
-
-Parameters:
-- `action` (required, string) — install, uninstall, list, status
-- `hooks` (array) — which hooks to manage (default: all four)
-
-Hooks available: pre-commit, post-commit, pre-push, post-push.
-
-| Hook | Type | What it does |
-|------|------|-------------|
-| `pre-commit` | Blocking | TypeScript check + Codex validation before commit |
-| `post-commit` | Non-blocking | Log archival + cleanup after commit |
-| `pre-push` | Blocking | Full validation suite before push |
-| `post-push` | Non-blocking | Comprehensive monitoring after push |
-
-## 2 Lifecycle Hooks
-
-These fire automatically — no action needed from the user or agent.
-
-### pre_tool_call
-
-Fires before ANY tool executes:
-1. Tracks session stats
-2. Logs tool-start event to `logs/framework/plugin-tool-events.log`
-3. For code-producing tools (write_file, patch, execute_code, write, edit): runs quality gate + pre-processors via bridge
-4. For other tools: nudges when a xray MCP alternative exists (e.g., grep → search_codebase, eslint → strray_lint)
-
-### post_tool_call
-
-Fires after ANY tool returns:
-1. Logs tool-complete event
-2. For code-producing tools: runs post-processors via bridge
-
-### on_session_start (graceful fallback)
-
-Fires when a new session starts. Resets stats and logs to disk. Registration is wrapped in try/except for hosts that don't support it yet.
-
-## Slash Command
-
-```
-/strray status    — Plugin and framework health (calls bridge)
-/strray stats     — Session pipeline statistics
-/strray help      — Show available commands
-/sr status        — Alias
-```
-
-## Session Stats (tracked automatically)
-
-The plugin tracks per-session counters visible via `/strray stats`:
-- total_tool_calls, code_operations, strray_mcp_calls, native_tool_calls
-- quality_gate_runs, quality_gate_blocks
-- pre_processor_runs, post_processor_runs
-- bridge_calls, bridge_errors
-
-## Logging
-
-All logs go to `logs/framework/` in the project root:
-
-| File | Content |
-|------|---------|
-| `activity.log` | All pipeline events (quality gates, processors, nudges, errors) |
-| `plugin-tool-events.log` | Tool start/complete events with durations |
-
-## Quick Decision Guide
-
-| User Says | Tool / Command |
-|----------|---------------|
-| "Is xray working?" | `strray_health()` or `/strray status` |
-| "Check these files before I commit" | `strray_validate(files=[...], operation="commit")` |
-| "Is this code codex compliant?" | `strray_codex_check(code=..., operation="create")` |
-| "Set up git hooks" | `strray_hooks(action="install")` |
-| "What hooks are installed?" | `strray_hooks(action="status")` |
-| "Show session stats" | `/strray stats` |
-| "Why is the bridge failing?" | Check `strray_health()` → if `framework: "not_loaded"`, verify `dist/` symlink |
-
-## Bridge Commands (internal)
-
-These are called by the Python tools via `bridge.mjs`, not directly by the LLM:
-
-| Command | What it does |
-|---------|-------------|
-| `health` | Framework health check |
-| `validate` | Run quality gate on files |
-| `codex-check` | Check code against codex rules |
-| `pre-process` | Quality gate + pre-processors before tool |
-| `post-process` | Post-processors after tool |
-| `hooks` | Git hook management |
-| `stats` | Bridge/framework statistics |
-
-Bridge can be invoked directly for debugging:
-```bash
-echo '{"command":"health"}' | node ~/.hermes/plugins/strray-hermes/bridge.mjs
-node ~/.hermes/plugins/strray-hermes/bridge.mjs health --cwd /path/to/project
-```
-
-## Relationship to MCP Servers
-
-The plugin and MCP servers are complementary:
-- **Plugin tools** = offline-first, always available, lightweight (validate, codex check, health, hooks)
-- **MCP servers** = deeper analysis requiring running Node.js (lint, security scan, architecture assessment, orchestration, codebase search)
-
-The plugin's pre_tool_call hook nudges when an MCP alternative exists (e.g., "use mcp_strray_lint_lint instead of raw eslint"). This is advisory, not blocking.
-
-## Pitfalls
-
-- Plugin requires restart after install/edit: Hermes loads plugins once at session start.
-- Bridge needs `dist/` symlink: The bridge loads compiled `.js` from `dist/` → `node_modules/xray/dist/`. If the symlink breaks, bridge returns `framework: "not_loaded"`.
-- `strray_codex_check` without `code` param returns health, not a codex check. Pass `code` for actual validation.
-- CLI fallback requires `npx xray` in PATH. If bridge fails and CLI isn't available, tools return errors.
-- Quality gate blocks are logged but NOT enforced (advisory). The tool returns violations; the agent decides what to do.
-- Git hooks use symlinks from `.git/hooks/` → `hooks/`. If the `hooks/` directory doesn't exist in the project, `strray_hooks(action="install")` skips those hooks.
-- Project root detection walks up from CWD looking for `node_modules/xray`, `.opencode/strray/features.json`, or `package.json`. Override with `STRRAY_PROJECT_ROOT` env var.
-- `logs/framework/` is created automatically. Never breaks the agent if permissions fail.