@haposoft/cafekit 0.11.0 → 0.11.3

package/src/claude/rules/workflow.md

@@ -8,11 +8,11 @@ Use the CafeKit loop: **Understand -> Plan -> Execute -> Verify -> Sync**.
 - Read the active spec/task file when one exists.
 - Read and activate any CafeKit skill that likely applies before taking action.
 - Inspect only the code needed to understand the affected area.
-- Use `hapo:inspect` or focused search when structure is unclear.
+- Use `inspect` or focused search when structure is unclear.
 
 ## 2. Plan
 
-- For non-trivial features, use `/hapo:specs` to create or validate the spec.
+- For non-trivial features, use `/specs` to create or validate the spec.
 - For approved specs, work one task file at a time.
 - Extract from the active task:
   - `Context`

package/src/claude/skills/agent-browser/SKILL.md

@@ -2,12 +2,15 @@
 name: hapo:agent-browser
 description: AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).
 license: Apache-2.0
+user-invocable: true
+when_to_use: "Invoke to drive a real browser for navigation, screenshots, or DOM actions."
+category: dev-tools
+keywords: [browser, automation, screenshot, navigation]
 argument-hint: "[url or task]"
 metadata:
   author: haposoft
   version: "1.0.0"
 ---
-
 # agent-browser Skill
 
 Browser automation CLI designed for AI agents. Uses "snapshot + refs" paradigm for 93% less context than Playwright MCP.

package/src/claude/skills/ai-multimodal/SKILL.md

@@ -2,14 +2,15 @@
 name: hapo:ai-multimodal
 description: Analyze images/audio/video/documentation with Gemini API. Use for vision analysis, transcription, OCR, design extraction, and deep multimodal understanding.
 license: MIT
-allowed-tools:
-  - Bash
-  - Read
-  - Write
-  - Edit
+user-invocable: true
+when_to_use: "Invoke to analyze or generate images, audio, or mixed-media content."
+category: utilities
+keywords: [multimodal, image, audio, vision]
 argument-hint: "[file-path] [prompt]"
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # AI Multimodal
 
 Process audio, images, videos, documents using Gemini. Purely focused on robust analysis, transcription, and contextual extraction.

package/src/claude/skills/backend-development/SKILL.md

@@ -2,10 +2,15 @@
 name: hapo:backend-development
 description: Build backends with Node.js, Python, Go (NestJS, FastAPI, Django). Use for REST/GraphQL/gRPC APIs, auth (OAuth, JWT), databases, microservices, security (OWASP), Docker/K8s.
 license: MIT
+user-invocable: true
+when_to_use: "Invoke to build or modify server APIs, services, and data layers."
+category: backend
+keywords: [backend, api, server, database]
 argument-hint: "[framework] [task]"
-version: "1.0.0"
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Backend Development Skill
 
 Production-ready backend development with modern technologies, best practices, and proven patterns.

package/src/claude/skills/brainstorm/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:brainstorm
 description: "Scout-first brainstorming for unclear ideas, architectural choices, scope gates, and translating raw intent into a spec-ready design."
+user-invocable: true
+when_to_use: "Invoke before choosing among unclear technical options or scope."
+category: utilities
+keywords: [ideation, tradeoffs, decisions, scope]
 argument-hint: "<idea_or_problem>"
-version: 2.1.0
+metadata:
+  author: haposoft
+  version: "2.1.0"
 ---
-
 # Brainstorming Skill
 
 You execute CafeKit's pre-spec design workflow. Your job is to turn a raw idea into a validated, spec-ready design without writing code or starting implementation.

package/src/claude/skills/chrome-devtools/SKILL.md

@@ -2,10 +2,15 @@
 name: hapo:chrome-devtools
 description: Automate browsers with Puppeteer CLI scripts and persistent sessions. Use for screenshots, performance analysis, network monitoring, web scraping, form automation, JavaScript debugging.
 license: Apache-2.0
+user-invocable: true
+when_to_use: "Invoke to inspect, debug, or profile a page via Chrome DevTools."
+category: dev-tools
+keywords: [devtools, chrome, debug, profiling]
 argument-hint: "[url or task]"
-version: "1.1.0"
+metadata:
+  author: haposoft
+  version: "1.1.0"
 ---
-
 # Chrome DevTools Agent Skill
 
 Browser automation via Puppeteer scripts with persistent sessions. All scripts output JSON.

package/src/claude/skills/code-review/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:code-review
 description: "Adversarial code review with technical rigor. Supports 3-Stage Protocol with ai-multimodal injection for multimodal spec compliance. Red-team analysis finds security holes, logic gaps, and architecture violations."
+user-invocable: true
+when_to_use: "Invoke to review a diff for correctness and quality before merge."
+category: dev-tools
+keywords: [review, diff, quality, correctness]
 argument-hint: "[#PR | COMMIT | --pending | scope]"
-version: 1.0.0
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Code Review
 
 Adversarial code review with technical rigor, evidence-based claims, and visual/document intelligence via the `hapo:ai-multimodal` Hub.

package/src/claude/skills/debug/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:debug
 description: "Use before fixing any bug, failing test, CI/CD failure, production incident, performance issue, UI regression, flaky test, or unexpected behavior. Diagnostic-only root-cause workflow with evidence, hypotheses, blast-radius mapping, and verification plan."
+user-invocable: true
+when_to_use: "Invoke for evidence-first root-cause diagnosis before any fix."
+category: dev-tools
+keywords: [debug, diagnosis, root-cause, evidence]
 argument-hint: "[issue] --quick|--ci|--frontend|--perf"
-version: "1.0.0"
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Debug - Evidence-First Root Cause Analysis
 
 Debugging is diagnosis, not repair. Find the source of the failure before changing product code.

package/src/claude/skills/develop/SKILL.md

@@ -1,9 +1,15 @@
 ---
 name: hapo:develop
 description: "Code execution engine: Reads specs and implements code end-to-end with automatic code review, self-healing, and visual implementation notes."
+user-invocable: true
+when_to_use: "Invoke to implement specs and tasks end-to-end after scope is clear."
+category: utilities
+keywords: [implementation, specs, build, orchestration]
 argument-hint: "[feature-name|specs-directory-path] [task-file] [--flash] [--no-notes]"
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Develop — Feature Implementation (Task-Orchestrated Build)
 
 Reads the project specification (`hapo:specs`) and implements code through a disciplined task loop. In specific-task mode it behaves like a surgical executor. In full-spec mode it behaves like a sequential orchestrator, processing one unblocked task at a time and syncing state after every verified task.

package/src/claude/skills/devops/SKILL.md

@@ -2,10 +2,15 @@
 name: hapo:devops
 description: Deploy to Cloudflare (Workers, R2, D1), Docker, GCP (Cloud Run, GKE), Kubernetes (kubectl, Helm). Use for serverless, containers, CI/CD, GitOps, security audit.
 license: MIT
+user-invocable: true
+when_to_use: "Invoke to deploy, containerize, or set up CI/CD and infra."
+category: devops
+keywords: [deploy, docker, ci-cd, kubernetes]
 argument-hint: "[platform] [task]"
-version: "2.0.0"
+metadata:
+  author: haposoft
+  version: "2.0.0"
 ---
-
 # DevOps Skill
 
 Deploy and manage cloud infrastructure across Cloudflare, Docker, Google Cloud, and Kubernetes.

package/src/claude/skills/docs/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:docs
 description: "Create, update, summarize, or reconstruct project/system documentation from source code. Use reconstruct mode for as-is documentation of existing or legacy systems with evidence and uncertainty tracking."
-version: 1.0.0
+user-invocable: true
+when_to_use: "Invoke to create, update, or reconstruct project documentation from source."
+category: document-skills
+keywords: [docs, reconstruct, documentation, evidence]
 argument-hint: "[--init|--update|--summarize|--reconstruct] [scope]"
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Docs
 
 Project documentation workflow for CafeKit.

package/src/claude/skills/docx/SKILL.md

@@ -2,11 +2,14 @@
 name: hapo:docx
 description: Create, edit, analyze .docx Word documents. Use for document creation, tracked changes, comments, formatting preservation, text extraction, template modification.
 license: Proprietary. LICENSE.txt has complete terms
+user-invocable: true
+when_to_use: "Invoke to read, create, or edit Word .docx documents."
+category: document-skills
+keywords: [docx, word, document, office]
 metadata:
   author: haposoft
   version: "1.0.0"
 ---
-
 # DOCX creation, editing, and analysis
 
 ## Overview

package/src/claude/skills/frontend-design/SKILL.md

@@ -2,9 +2,14 @@
 name: hapo:frontend-design
 description: Create polished frontend interfaces from designs/screenshots/videos. Use for web components, 3D experiences, replicating UI designs, quick prototypes, immersive interfaces, avoiding AI slop.
 license: Complete terms in LICENSE.txt
-version: "1.0.0"
+user-invocable: true
+when_to_use: "Invoke to translate mockups or screenshots into UI implementation."
+category: frontend
+keywords: [design, mockup, ui, replication]
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.
 
 **IMPORTANT**: MUST follow Design Thinking, Frontend Aesthetics Guidelines, Asset & Analysis References, and Anti-Patterns (AI Slop) sections below. DO NOT skip these rules.

package/src/claude/skills/frontend-development/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:frontend-development
 description: Build React/TypeScript frontends with modern patterns. Use for components, Suspense, lazy loading, useSuspenseQuery, MUI v7 styling, TanStack Router, performance optimization.
+user-invocable: true
+when_to_use: "Invoke to build React/TS components with best practices."
+category: frontend
+keywords: [frontend, react, typescript, components]
 argument-hint: "[component or feature]"
-version: "1.0.0"
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Frontend Development Guidelines
 
 ## Purpose

package/src/claude/skills/generate-graph/SKILL.md

@@ -1,12 +1,14 @@
 ---
 name: hapo:generate-graph
 description: >-
-  Use when the user wants to create any technical diagram - architecture, data
-  flow, flowchart, sequence, agent/memory, or concept map - and export as
-  SVG+PNG. Trigger on: "generate diagram" "draw diagram" "visualize" or any
-  system/flow description the user wants illustrated.
+user-invocable: true
+when_to_use: "Invoke to build a queryable graph or diagram from code or data."
+category: utilities
+keywords: [graph, visualization, diagram, analysis]
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Generate Graph
 
 Generate production-quality SVG technical diagrams exported as PNG via `rsvg-convert`.

package/src/claude/skills/git/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:git
 description: "Hapo Native Git Operations & Worktree Management. Handles safe commits, conventional split, branch finish choices, secret scanning, and sibling-branch worktrees locally."
+user-invocable: true
+when_to_use: "Invoke for commits, PRs, branch hygiene, or worktree management."
+category: dev-tools
+keywords: [git, commits, pr, worktree]
 argument-hint: "commit | push | pr | finish | worktree <feature-desc>"
-version: "1.0.0"
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Git Operations & Worktree
 
 This skill merges Version Control Systems (VSC) capabilities and parallel Worktree management into a single, clean-room execution engine utilizing pure Bash commands rather than proprietary Node scripts.

package/src/claude/skills/hotfix/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:hotfix
 description: "ALWAYS activate this skill when you are asked to FIX a bug, error, test failure, CI/CD issue, type error, lint error, log error, UI issue, or code problem. Uses hapo:debug for evidence-first diagnosis before any code change."
+user-invocable: true
+when_to_use: "Invoke to fix a bug or failure with scout-first diagnosis before change."
+category: dev-tools
+keywords: [hotfix, fix, bug, diagnosis]
 argument-hint: "[issue] --quick|--parallel|--from-debug"
-version: "1.0.0"
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Hotfix - Structured Bug Elimination
 
 Kill bugs systematically. No guessing. Evidence first, fix second.

package/src/claude/skills/impact-analysis/SKILL.md

@@ -1,10 +1,15 @@
 ---
-name: impact-analysis
+name: hapo:impact-analysis
 description: "Analyze code change impacts and generate test scenarios. Use after code changes, before commit, or when checking for regressions. Automatically detects affected files, dependencies, and edge cases."
+user-invocable: true
+when_to_use: "Invoke after code changes to map regression impact and test scenarios."
+category: dev-tools
+keywords: [impact, regression, dependencies, testing]
 argument-hint: "[files] OR auto"
-version: 1.0.0
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Impact Analysis - Impact Analysis & Test Guidance
 
 Analyze the impact of code changes and provide detailed test guidance to prevent regression bugs.

package/src/claude/skills/inspect/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:inspect
 description: "Fast codebase discovery using parallel agents. Use for file discovery, task context gathering, quick searches across directories. Supports internal (Explore) and external (Gemini) agents."
-version: 2.0.0
+user-invocable: true
+when_to_use: "Invoke for fast parallel codebase discovery and file location."
+category: discovery
+keywords: [discovery, search, explore, context]
 argument-hint: "[search-target] [ext]"
+metadata:
+  author: haposoft
+  version: "2.0.0"
 ---
-
 # Inspect
 
 Fast, token-efficient codebase discovery using parallel agents to find files needed for tasks.

package/src/claude/skills/mobile-development/SKILL.md

@@ -2,10 +2,15 @@
 name: hapo:mobile-development
 description: Build mobile apps with React Native, Flutter, Swift/SwiftUI, Kotlin/Jetpack Compose. Use for iOS/Android, mobile UX, performance optimization, offline-first, app store deployment.
 license: MIT
+user-invocable: true
+when_to_use: "Invoke to build or modify mobile app features and UI."
+category: frontend
+keywords: [mobile, app, ios, android]
 argument-hint: "[platform] [feature]"
-version: "1.0.0"
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Mobile Development Skill
 
 Production-ready mobile development with modern frameworks, best practices, and mobile-first thinking patterns.

package/src/claude/skills/pdf/SKILL.md

@@ -2,11 +2,14 @@
 name: hapo:pdf
 description: Extract text/tables, create, merge, split PDFs. Fill PDF forms programmatically. Use for PDF processing, generation, form filling, document analysis, batch operations.
 license: Proprietary. LICENSE.txt has complete terms
+user-invocable: true
+when_to_use: "Invoke to read, extract, or generate PDF documents."
+category: document-skills
+keywords: [pdf, extract, document, generate]
 metadata:
   author: haposoft
   version: "1.0.0"
 ---
-
 # PDF Processing Guide
 
 ## Overview

package/src/claude/skills/pptx/SKILL.md

@@ -2,11 +2,14 @@
 name: hapo:pptx
 description: Create, edit, analyze .pptx PowerPoint files. Use for presentations, slides, layouts, speaker notes, template modification, content extraction, slide generation.
 license: Proprietary. LICENSE.txt has complete terms
+user-invocable: true
+when_to_use: "Invoke to read, create, or edit PowerPoint .pptx slides."
+category: document-skills
+keywords: [pptx, powerpoint, slides, office]
 metadata:
   author: haposoft
   version: "1.0.0"
 ---
-
 # PPTX creation, editing, and analysis
 
 ## Overview

package/src/claude/skills/question/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:question
 description: "Answer questions with evidence. Use when the user asks about project behavior, source code, specs, docs, configuration, dependencies, or external technical information; inspect the repo first, use internet/current docs when repo evidence is insufficient, and ask back only when the question cannot be answered safely."
+user-invocable: true
+when_to_use: "Invoke to answer project or technical questions with repo-first evidence."
+category: utilities
+keywords: [question, evidence, answer, research]
 argument-hint: "<question> [--repo|--web|--both|--brief|--deep]"
-version: 1.0.0
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Question Skill
 
 `hapo:question` is an evidence-backed question-answering skill. It answers user questions by checking the local project first, then external/current sources when the repository cannot answer the question.

package/src/claude/skills/react-best-practices/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:react-best-practices
 description: React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
+user-invocable: true
+when_to_use: "Invoke to apply React performance and architecture best practices."
+category: frontend
+keywords: [react, performance, patterns, hooks]
 argument-hint: "[component or pattern]"
-version: "1.0.0"
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Vercel React Best Practices
 
 Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 45 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation.

package/src/claude/skills/research/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:research
 description: "Research technical solutions and analyze architectures. Acts as a command facade to trigger the 'researcher' subagent for multi-source verification and deep report synthesis."
+user-invocable: true
+when_to_use: "Invoke for deep technical research and solution evaluation before building."
+category: research
+keywords: [research, evaluation, analysis, solutions]
 argument-hint: "<topic_or_question>"
-version: 2.0.0
+metadata:
+  author: haposoft
+  version: "2.0.0"
 ---
-
 # Research (Delegation Facade)
 
 **Mantra:** YAGNI, KISS, DRY. Be brutal, straight to the point, and strictly authoritative.

package/src/claude/skills/specs/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:specs
 description: "Structured specification workflow — from vague idea to actionable task list. Includes init, requirements, design, task breakdown, review, and archiving."
-version: 2.0.0
+user-invocable: true
+when_to_use: "Invoke to turn a vague idea into an actionable, gated specification."
+category: utilities
+keywords: [specs, requirements, design, tasks]
 argument-hint: "<feature-description> | status | resume | --validate | archive"
+metadata:
+  author: haposoft
+  version: "2.0.0"
 ---
-
 # Specs (SDD — Specification-Driven Development)
 
 > A structured specification system that turns vague ideas into actionable, implementable task lists.

package/src/claude/skills/sync/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:sync
 description: "Dumb-proof status tracker and file synchronizer. Updates spec.json, task_registry, and tasks/*.md without breaking structural schemas. Includes Auto-Audit."
-version: 1.0.0
+user-invocable: true
+when_to_use: "Invoke to synchronize spec state, docs, or task tracking after changes."
+category: utilities
+keywords: [sync, state, tracking, consistency]
 argument-hint: "<feature_name> <task_id|task-file> <status> [blocker] | phase <feature_name> <next_phase> | audit <feature_name>"
+metadata:
+  author: haposoft
+  version: "1.0.0"
 ---
-
 # Sync (State Tracking Protocol)
 
 This skill safely bridges the gap between active development state and physical documentation files (`spec.json` + `task_registry` + `tasks/task-R*.md`). Instead of relying on risky raw AI edits, this skill executes precise contextual replacements.

package/src/claude/skills/test/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: hapo:test
 description: "Run and verify project tests across all scopes: unit, integration, e2e, and UI. Blast-radius scoping for speed, chrome-devtools for UI verification, structured verdicts for downstream automation."
+user-invocable: true
+when_to_use: "Invoke to run and verify unit, integration, e2e, and UI tests."
+category: testing
+keywords: [test, unit, integration, e2e]
 argument-hint: "[scope|--full|--ui <url>|--ui-auth <url>|--ui-flow <url>]"
-version: 2.0.0
+metadata:
+  author: haposoft
+  version: "2.0.0"
 ---
-
 # Test — Verify Implementation Quality
 
 Run the project's test suite, analyze results, and return a structured verdict.

package/src/claude/skills/ui-ux-pro-max/SKILL.md

@@ -1,9 +1,14 @@
 ---
 name: hapo:ui-ux-pro-max
 description: "UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples."
-version: "1.1.0"
+user-invocable: true
+when_to_use: "Invoke to choose colors, fonts, layout, and design systems."
+category: frontend
+keywords: [ui, ux, design-system, layout]
+metadata:
+  author: haposoft
+  version: "1.1.0"
 ---
-
 # UI/UX Pro Max - Design Intelligence
 
 Comprehensive design guide for web and mobile applications. Contains 50+ styles, 161 color palettes, 57 font pairings, 161 product types with reasoning rules, 99 UX guidelines, and 25 chart types across 10 technology stacks. Searchable database with priority-based recommendations.

package/src/claude/skills/web-testing/SKILL.md

@@ -2,10 +2,15 @@
 name: hapo:web-testing
 description: Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.
 license: Apache-2.0
+user-invocable: true
+when_to_use: "Invoke to test web flows in a real browser end-to-end."
+category: testing
+keywords: [web-testing, e2e, browser, validation]
 argument-hint: "[test-type] [target]"
-version: "3.0.0"
+metadata:
+  author: haposoft
+  version: "3.0.0"
 ---
-
 # Web Testing Skill
 
 Comprehensive web testing: unit, integration, E2E, load, security, visual regression, accessibility.

package/src/claude/skills/xlsx/SKILL.md

@@ -2,11 +2,14 @@
 name: hapo:xlsx
 description: Create, edit, analyze spreadsheets (.xlsx, .csv, .tsv). Use for Excel formulas, data analysis, visualization, formatting, pivot tables, charts, formula recalculation.
 license: Proprietary. LICENSE.txt has complete terms
+user-invocable: true
+when_to_use: "Invoke to read, create, or edit Excel .xlsx spreadsheets."
+category: document-skills
+keywords: [xlsx, excel, spreadsheet, office]
 metadata:
   author: haposoft
   version: "1.0.0"
 ---
-
 # Requirements for Outputs
 
 ## All Excel files