@amrhas82/agentic-kit 1.2.0 → 1.5.0

package/packages/{opencode/skills/verification-before-completion/SKILL.md → ampcode/commands/verification-before-completion.md}

@@ -136,4 +136,4 @@ From 24 failure memories:
 
 Run the command. Read the output. THEN claim the result.
 
-This is non-negotiable.
+This is non-negotiable.

package/{tests/tmp/test-cli-install-1762170060156/claude-standard-test/skills/xlsx/SKILL.md → packages/ampcode/commands/xlsx.md}

@@ -68,7 +68,7 @@ A user may ask you to create, edit, or analyze the contents of an .xlsx file. Yo
 
 ## Important Requirements
 
-**LibreOffice Required for Formula Recalculation**: You can assume LibreOffice is installed for recalculating formula values using the `recalc.py` script. The script automatically configures LibreOffice on first run
+**LibreOffice Required for Formula Recalculation**: You can assume LibreOffice is installed for recalculating formula values using the `xlsx/recalc.py` script. The script automatically configures LibreOffice on first run
 
 ## Reading and analyzing data
 
@@ -131,7 +131,7 @@ This applies to ALL calculations - totals, percentages, ratios, differences, etc
 2. **Create/Load**: Create new workbook or load existing file
 3. **Modify**: Add/edit data, formulas, and formatting
 4. **Save**: Write to file
-5. **Recalculate formulas (MANDATORY IF USING FORMULAS)**: Use the recalc.py script
+5. **Recalculate formulas (MANDATORY IF USING FORMULAS)**: Use the xlsx/recalc.py script
    ```bash
    python recalc.py output.xlsx
    ```
@@ -203,7 +203,7 @@ wb.save('modified.xlsx')
 
 ## Recalculating formulas
 
-Excel files created or modified by openpyxl contain formulas as strings but not calculated values. Use the provided `recalc.py` script to recalculate formulas:
+Excel files created or modified by openpyxl contain formulas as strings but not calculated values. Use the provided `xlsx/recalc.py` script to recalculate formulas:
 
 ```bash
 python recalc.py <excel_file> [timeout_seconds]
@@ -243,7 +243,7 @@ Quick checks to ensure formulas work correctly:
 - [ ] **Verify dependencies**: Check all cells referenced in formulas exist
 - [ ] **Test edge cases**: Include zero, negative, and very large values
 
-### Interpreting recalc.py Output
+### Interpreting xlsx/recalc.py Output
 The script returns JSON with error details:
 ```json
 {
@@ -270,7 +270,7 @@ The script returns JSON with error details:
 - Use `data_only=True` to read calculated values: `load_workbook('file.xlsx', data_only=True)`
 - **Warning**: If opened with `data_only=True` and saved, formulas are replaced with values and permanently lost
 - For large files: Use `read_only=True` for reading or `write_only=True` for writing
-- Formulas are preserved but not evaluated - use recalc.py to update values
+- Formulas are preserved but not evaluated - use xlsx/recalc.py to update values
 
 ### Working with pandas
 - Specify data types to avoid inference issues: `pd.read_excel('file.xlsx', dtype={'id': str})`

package/packages/ampcode/subagentic-manual.md

@@ -0,0 +1,155 @@
+# Subagent Kits Manual
+
+Complete ready-to-use package of AI subagents, skills, and task templates for **Claude Code**, **OpenCode**, **Amp**, and **Droid**. Production-tested agent definitions from Simple + BMAD methodologies, zero configuration needed.
+
+---
+
+## 🚀 Quick Start
+
+Clone the toolkit:
+```bash
+git clone https://github.com/amrhas82/agentic-toolkit
+cd agentic-toolkit
+```
+
+Install and invoke for your platform:
+
+| Platform | Installation | Invocation |
+|----------|--------------|-----------|
+| **Claude Code** | `cp -rv ai/subagents/claude/* ~/.claude/` | `@agent-name` or `As agent-name, ...` |
+| **OpenCode** | `cp -rv ai/subagents/opencode/* ~/.config/opencode/` | `@agent-name` or `As agent-name, ...` |
+| **Amp** | `cp -rv ai/subagents/ampcode/* ~/.config/amp/` | `As agent-name, ...` |
+| **Droid** | `cp -rv ai/subagents/droid/* ~/.factory/` + enable in `~/.factory/settings.json` | `invoke droid agent_name` |
+
+---
+
+## 📦 What's Included
+
+**Per-kit contents** (14 subagents + 22 skills + 20+ tasks):
+- **3 Workflow Subagents** – Three-phase development: 1-Create PRD → 2-Generate Tasks → 3-Process Task List
+- **11 Specialist Subagents** – Expert roles (UX, QA, Product, Dev, Architecture, etc.)
+- **22 Reusable Skills** – Code creation, testing, debugging, docs, design, file processing
+- **20+ Task Templates** – Validation, planning, development, documentation, specialized workflows
+- **Zero Configuration** – Ready to use immediately
+---
+
+## 🤖 14 Subagents
+
+### Workflow Phase Agents (3)
+| Agent | Purpose |
+|-------|---------|
+| **1-create-prd** | Create Product Requirement Documents with structured scope and requirements |
+| **2-generate-tasks** | Break PRDs into granular, actionable task lists |
+| **3-process-task-list** | Execute tasks iteratively with built-in review and progress tracking |
+
+**Recommended Workflow:** PRD → Tasks → Process → Complete
+
+### Specialist Agents (11)
+| Agent | Purpose |
+|-------|---------|
+| **ux-expert** | UI/UX design, wireframes, prototypes, front-end specifications |
+| **scrum-master** | User stories, epic management, agile process guidance |
+| **qa-test-architect** | Test architecture, quality gates, code review feedback |
+| **product-owner** | Backlog management, story refinement, acceptance criteria |
+| **product-manager** | PRDs, product strategy, feature prioritization, roadmaps |
+| **full-stack-dev** | Code implementation, debugging, refactoring |
+| **holistic-architect** | System design, architecture docs, API design, scalability |
+| **business-analyst** | Market research, competitive analysis, project discovery |
+| **orchestrator** | Workflow coordination, multi-agent task management |
+| **master** | Comprehensive expertise across all domains, universal executor |
+| **context-initializer** | Project context setup, documentation discovery and organization |
+
+---
+
+## 🛠 22 Reusable Skills
+
+### Development & Testing (7)
+| Skill | Purpose |
+|-------|---------|
+| **test-driven-development** | Write tests first, red-green-refactor cycle ensures tests verify behavior |
+| **testing-anti-patterns** | Avoid mock testing, test-only code, and mindless mocking |
+| **code-review** | Structured code review workflow before merging |
+| **systematic-debugging** | Four-phase debugging: investigate → analyze → hypothesize → implement |
+| **root-cause-tracing** | Trace bugs backward through call stack to find original trigger |
+| **condition-based-waiting** | Replace timeouts with polling to eliminate flaky tests |
+| **verification-before-completion** | Verify claims with evidence before marking tasks complete |
+
+### Design & Creativity (5)
+| Skill | Purpose |
+|-------|---------|
+| **algorithmic-art** | Create generative art using p5.js with seeded randomness |
+| **canvas-design** | Create visual art in PNG/PDF with design philosophy |
+| **artifacts-builder** | Build React/TypeScript/Tailwind/shadcn artifacts with Parcel bundling |
+| **theme-factory** | Apply 10 curated professional themes with color/font pairings |
+| **slack-gif-creator** | Create optimized animated GIFs for Slack |
+
+### Office & Document Processing (4)
+| Skill | Purpose |
+|-------|---------|
+| **pdf** | Extract/create PDFs, merge/split, handle forms and tables |
+| **docx** | Create/edit Word documents with tracked changes and comments |
+| **pptx** | Create/edit PowerPoint with design-first approach and HTML conversion |
+| **xlsx** | Create/edit spreadsheets with formulas, formatting, and data analysis |
+
+### Strategy & Communication (4)
+| Skill | Purpose |
+|-------|---------|
+| **brainstorming** | Collaborative design through questioning and exploration |
+| **internal-comms** | Write internal communications with company-approved formats |
+| **brand-guidelines** | Apply Anthropic's official brand colors and typography |
+| **mcp-builder** | Create MCP servers for LLM-service integration |
+
+### Specialized (2)
+| Skill | Purpose |
+|-------|---------|
+| **webapp-testing** | Test local web apps with Playwright – verify, debug, screenshot |
+| **skill-creator** | Create custom skills extending Claude's capabilities |
+
+---
+
+## 📋 20+ Reusable Task Templates
+
+Pre-built workflows for common development patterns (available in all kits):
+
+### Quality & Validation (5)
+- **validate-next-story** – Validate user story before implementation
+- **review-story** – Comprehensive story review and feedback
+- **trace-requirements** – Map requirements to tests
+- **qa-gate** – Quality gate decision (PASS/CONCERNS/FAIL)
+- **apply-qa-fixes** – Apply QA feedback to code
+
+### Planning & Analysis (4)
+- **risk-profile** – Risk assessment matrix and mitigation
+- **nfr-assess** – Non-functional requirements validation
+- **advanced-elicitation** – Structured requirements discovery
+- **test-design** – Test scenario creation
+
+### Development (4)
+- **create-next-story** – Generate user story from requirements
+- **create-brownfield-story** – Story template for existing codebase
+- **brownfield-create-epic** – Epic breakdown for existing systems
+- **correct-course** – Realign strategy or approach mid-project
+
+### Documentation (4)
+- **create-doc** – Generate documentation from code/context
+- **shard-doc** – Break large documents into focused sections
+- **index-docs** – Create documentation indices
+- **document-project** – Comprehensive project documentation
+
+### Specialized (3+)
+- **generate-ai-frontend-prompt** – v0 and Lovable UI generation prompts
+- **facilitate-brainstorming-session** – Structured brainstorming workflow
+- **create-deep-research-prompt** – Deep research and analysis workflow
+- **execute-checklist** – Universal checklist execution
+
+---
+
+## 🎯 How to Use This Package
+
+1. **Clone and Install** – Copy files to your CLI's config directory
+2. **Start with Workflow** – Use 1-create-prd → 2-generate-tasks → 3-process-task-list
+3. **Add Specialists** – Invoke agents by name for specific domain expertise
+4. **Leverage Skills** – Use skills within agents for specialized capabilities
+5. **Reuse Tasks** – Apply pre-built task templates for common patterns
+
+**Across all four platforms:** Claude Code, OpenCode, Amp, Droid

package/packages/ampcode/variants.json

@@ -1,14 +1,15 @@
 {
   "lite": {
     "name": "Lite",
-    "description": "Essential workflow agents with core document and debugging skills optimized for amplified development",
-    "useCase": "Users wanting comprehensive amplified workflow management with essential document processing and debugging capabilities",
-    "targetUsers": "Beginners, evaluators, developers wanting balanced features with amplified productivity",
+    "description": "Essential workflow agents with core document and debugging skills",
+    "useCase": "Users wanting comprehensive workflow management with essential document processing and debugging capabilities",
+    "targetUsers": "Beginners, evaluators, users wanting balanced features with moderate footprint",
     "agents": [
       "1-create-prd",
       "2-generate-tasks",
       "3-process-task-list",
-      "master"
+      "master",
+      "context-initializer"
     ],
     "skills": [
       "docx",
@@ -24,9 +25,9 @@
   },
   "standard": {
     "name": "Standard",
-    "description": "Complete workflow and development team with enhanced testing and validation skills for amplified development",
-    "useCase": "Professional accelerated development with full team coordination, testing, and comprehensive skill set",
-    "targetUsers": "Professional developers, teams focused on velocity, quality-focused users",
+    "description": "Complete workflow and development team with enhanced testing and validation skills",
+    "useCase": "Professional development with full team coordination, testing, and comprehensive skill set",
+    "targetUsers": "Professional developers, teams, quality-focused users",
     "agents": [
       "1-create-prd",
       "2-generate-tasks",
@@ -36,7 +37,8 @@
       "qa-test-architect",
       "full-stack-dev",
       "business-analyst",
-      "ux-expert"
+      "ux-expert",
+      "context-initializer"
     ],
     "skills": [
       "docx",
@@ -56,9 +58,9 @@
   },
   "pro": {
     "name": "Pro",
-    "description": "Complete installation with all capabilities optimized for maximum amplified development and automation",
-    "useCase": "Full-featured installation for users needing all AI codegen, document processing, testing, and advanced automation capabilities",
-    "targetUsers": "Power users, enterprises, teams requiring maximum velocity, automation-focused developers",
+    "description": "Complete installation with all capabilities including advanced development, testing, and creative skills",
+    "useCase": "Full-featured installation for users needing all AI codegen, document processing, testing, debugging, and creative capabilities",
+    "targetUsers": "Power users, enterprises, teams requiring comprehensive feature set",
     "agents": "*",
     "skills": "*",
     "resources": "*",

package/packages/claude/.claude-plugin/plugin-lite.json

@@ -1,6 +1,6 @@
 {
   "name": "Agentic Toolkit - Lite",
-  "version": "1.1.0",
+  "version": "1.0.0",
   "description": "Lightweight variant with 3 core agents and no skills for minimal dependencies",
   "variant": "lite",
   "agents": [
@@ -21,6 +21,12 @@
       "name": "Scrum Master",
       "description": "Project management and team coordination",
       "path": "agents/scrum-master.md"
+    },
+    {
+      "id": "context-initializer",
+      "name": "Context Initializer",
+      "description": "Initialize Claude Code context through elicitation, organize docs, create CLAUDE.md and KNOWLEDGE_BASE.md",
+      "path": "agents/context-initializer.md"
     }
   ],
   "skills": [],
@@ -29,11 +35,6 @@
       "name": "register-agents",
       "path": "hooks/register-agents.js",
       "event": "plugin-load"
-    },
-    {
-      "name": "session-start",
-      "path": "hooks/session-start.js",
-      "event": "session-start"
     }
   ],
   "resources": {

package/packages/claude/.claude-plugin/plugin-pro.json

@@ -1,6 +1,6 @@
 {
   "name": "Agentic Toolkit - Pro",
-  "version": "1.1.0",
+  "version": "1.0.0",
   "description": "Pro variant with all 13 agents and all 14 skills for maximum capabilities",
   "variant": "pro",
   "agents": [
@@ -34,6 +34,12 @@
       "description": "Business requirements analysis",
       "path": "agents/business-analyst.md"
     },
+    {
+      "id": "context-initializer",
+      "name": "Context Initializer",
+      "description": "Initialize Claude Code context through elicitation, organize docs, create CLAUDE.md and KNOWLEDGE_BASE.md",
+      "path": "agents/context-initializer.md"
+    },
     {
       "id": "full-stack-dev",
       "name": "Full-Stack Developer",
@@ -174,11 +180,6 @@
       "name": "register-agents",
       "path": "hooks/register-agents.js",
       "event": "plugin-load"
-    },
-    {
-      "name": "session-start",
-      "path": "hooks/session-start.js",
-      "event": "session-start"
     }
   ],
   "resources": {

package/packages/claude/.claude-plugin/plugin-standard.json

@@ -1,6 +1,6 @@
 {
   "name": "Agentic Toolkit - Standard",
-  "version": "1.1.0",
+  "version": "1.0.0",
   "description": "Standard variant with all 13 agents and 8 core production skills",
   "variant": "standard",
   "agents": [
@@ -34,6 +34,12 @@
       "description": "Business requirements analysis",
       "path": "agents/business-analyst.md"
     },
+    {
+      "id": "context-initializer",
+      "name": "Context Initializer",
+      "description": "Initialize Claude Code context through elicitation, organize docs, create CLAUDE.md and KNOWLEDGE_BASE.md",
+      "path": "agents/context-initializer.md"
+    },
     {
       "id": "full-stack-dev",
       "name": "Full-Stack Developer",
@@ -138,11 +144,6 @@
       "name": "register-agents",
       "path": "hooks/register-agents.js",
       "event": "plugin-load"
-    },
-    {
-      "name": "session-start",
-      "path": "hooks/session-start.js",
-      "event": "session-start"
     }
   ],
   "resources": {

package/packages/claude/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "Agentic Toolkit",
-  "version": "1.1.0",
+  "version": "1.0.0",
   "description": "Comprehensive toolkit for AI-driven software development with 13 specialized agents and 14 powerful skills",
   "author": "Anthropic",
   "default_variant": "standard",
@@ -34,11 +34,6 @@
       "name": "register-agents",
       "path": "hooks/register-agents.js",
       "event": "plugin-load"
-    },
-    {
-      "name": "session-start",
-      "path": "hooks/session-start.js",
-      "event": "session-start"
     }
   ],
   "resources": {