@radenadri/skills-alena 1.1.0 → 1.2.1

package/CLAUDE.md

@@ -97,6 +97,7 @@ Slash commands are available in `commands/`. Key commands:
 | `/deep-audit` | Brutal 5-pass exhaustive audit |
 | `/discuss` | Lock user preferences BEFORE planning — prevents rework |
 | `/lmf` | Run the learning-first tutorial flow before or alongside execution |
+| `/prd` | Create a product requirements document through an interview-first flow |
 | `/plan` | Create executable prompt plans with task anatomy |
 | `/execute` | Execute plans with deviation protocol and checkpoints |
 | `/settings` | View/modify project config (mode, depth, preferences) |
@@ -169,9 +170,10 @@ alena/
 │   ├── investigator.md
 │   └── fixer.md
 ├── cursor-rules/          ← Cursor IDE rules (10 rules)
-└── skills/                ← Composable skill library (31 skills)
+└── skills/                ← Composable skill library (32 skills)
     ├── brainstorming/
     ├── lmf/
+    ├── write-prd/
     ├── writing-plans/
     ├── executing-plans/
     ├── test-driven-development/

package/GEMINI.md

@@ -94,6 +94,7 @@ Slash commands are available in `commands/`. Key commands:
 | `/deep-audit` | Brutal 5-pass exhaustive audit |
 | `/discuss` | Lock user preferences BEFORE planning — prevents rework |
 | `/lmf` | Run the learning-first tutorial flow before or alongside execution |
+| `/prd` | Create a product requirements document through an interview-first flow |
 | `/plan` | Create executable prompt plans with task anatomy |
 | `/execute` | Execute plans with deviation protocol and checkpoints |
 | `/settings` | View/modify project config (mode, depth, preferences) |
@@ -160,9 +161,10 @@ alena/
 │   ├── investigator.md
 │   └── fixer.md
 ├── cursor-rules/          ← Cursor IDE rules (10 rules)
-└── skills/                ← Composable skill library (31 skills)
+└── skills/                ← Composable skill library (32 skills)
     ├── brainstorming/
     ├── lmf/
+    ├── write-prd/
     ├── writing-plans/
     ├── executing-plans/
     ├── test-driven-development/
@@ -199,6 +201,7 @@ alena/
 Workflows are installed in `.agent/workflows/`. Use `/workflow-name` to execute them. Workflows with `// turbo` annotations auto-run safe steps.
 
 Use `/lmf` when you want tutorial-first explanation and planning guidance before switching to direct execution.
+Use `/prd` when you want an interview-first product requirements document before implementation planning.
 
 ## Persistent Memory
 

package/README.md

@@ -1,14 +1,13 @@
 <p align="center">
   <h1 align="center">🧠 ALENA (Autonomous Layer for Executing Networked Agents)</h1>
   <p align="center">
-    <strong>A personal toolkit for autonomous, networked AI agents — 34 skills · 35 commands · 38 workflows · 9 agents · 10 cursor rules · 8 hooks · 13 modules · 11 templates</strong>
+    <strong>A personal toolkit for autonomous, networked AI agents — 35 skills · 36 commands · 39 workflows · 9 agents · 10 cursor rules · 8 hooks · 13 modules · 11 templates</strong>
   </p>
   <p align="center">
     Make your AI coding assistant operate like your own disciplined toolkit.
   </p>
   <p align="center">
     <a href="#-quick-start"><img src="https://img.shields.io/badge/Get_Started-blue?style=for-the-badge" alt="Get Started"></a>
-    <a href="https://alena.radenadri.xyz"><img src="https://img.shields.io/badge/Website-7c3aed?style=for-the-badge&logo=google-chrome&logoColor=white" alt="Website"></a>
     <a href="https://www.npmjs.com/package/@radenadri/skills-alena"><img src="https://img.shields.io/npm/v/%40radenadri%2Fskills-alena?style=for-the-badge&color=red" alt="NPM Version"></a>
     <a href="https://github.com/radenadri/skills-alena/blob/main/LICENSE"><img src="https://img.shields.io/github/license/radenadri/skills-alena?style=for-the-badge" alt="License"></a>
     <a href="https://github.com/radenadri/skills-alena/stargazers"><img src="https://img.shields.io/github/stars/radenadri/skills-alena?style=for-the-badge&color=gold" alt="Stars"></a>
@@ -16,7 +15,6 @@
   <p align="center">
     <a href="https://github.com/radenadri"><img src="https://img.shields.io/badge/GitHub-radenadri-181717?style=flat-square&logo=github" alt="GitHub"></a>
     <a href="https://github.com/radenadri/skills-alena/wiki"><img src="https://img.shields.io/badge/Wiki-Documentation-0969da?style=flat-square&logo=github" alt="Wiki"></a>
-    <a href="https://alena.radenadri.xyz"><img src="https://img.shields.io/badge/Homepage-alena.radenadri.xyz-0f766e?style=flat-square" alt="Homepage"></a>
   </p>
 </p>
 
@@ -28,19 +26,21 @@
 
 ---
 
-### 💎 The Gem: LLM Council v2 + Memory Module
+## 💎 LLM Council v2 — Agent Team Coordination
 
-> The most powerful pattern in AI-assisted development — real subagent spawning with deterministic orchestration.
+### The Problem
+AI coding tasks fail at scale because no single agent can hold all context: database schemas, API routes, service dependencies, frontend components, and business logic — simultaneously. Linear handoffs lose context. Role-switching in a single context window wastes tokens.
 
-**The Memory Module** deeply scans your entire codebase BEFORE any work begins — databases, schemas, API routes, service dependencies, frontend components, tech stack — and creates a structured intelligence layer that persists across sessions.
+### The Solution: Real Subagent Spawning + Deterministic Orchestration
 
-**Council v2** spawns **real subagents** via `Task()` — each specialist gets a fresh 200k context window. The orchestrator stays lean at ~10-15% context, coordinating through 13 deterministic CLI commands with code-enforced quality gates.
+**Council v2** replaces the old role-switching pattern with **real subagent spawning** via `Task()`. Each specialist agent gets a fresh 200k context window — no shared context pollution. The orchestrator stays lean at ~10-15% context usage.
 
 ```
                     ╔═══════════════════════════════╗
-                    ║     🎯 ORCHESTRATOR (lean)     ║
-                    ║  13 CLI commands · Quality gates ║
-                    ║  ~10-15% context · Task() spawn  ║
+                    ║     🎯 ORCHESTRATOR (lean)      ║
+                    ║  ~10-15% context usage           ║
+                    ║  13 deterministic CLI commands    ║
+                    ║  Code-enforced quality gates      ║
                     ╚════════════╦══════════════════╝
                                  ║
                         Task() spawning
@@ -52,6 +52,17 @@
        └──────────┘ └────────┘ └──────┘ └─────────┘
 ```
 
+### Key Capabilities
+
+| Capability | Description |
+|:---|:---|
+| 🧠 **Real subagent spawning** | Each agent gets a fresh 200k context via `Task()` — no shared context pollution |
+| 🎛️ **13 CLI commands** | Deterministic state machine for council orchestration (`council start`, `council next`, `council status`, etc.) |
+| 🚪 **Code-enforced quality gates** | Agents cannot advance phases without passing automated gate checks |
+| 🎯 **6 presets** | Full, Rapid, Debug, Architecture, Refactoring, Audit councils |
+| 📐 **Lean orchestrator** | Orchestrator uses ~10-15% context — delegates deep work to specialists |
+| 🧠 **Memory Module** | Deep intelligence layer: schemas, routes, services, components, tech stack |
+
 **What makes it different:**
 - ✅ **Real subagent spawning** — each agent gets a fresh 200k context via `Task()`, no context pollution
 - ✅ **13 deterministic CLI commands** — `council start`, `council next`, `council status`, etc.
@@ -64,14 +75,23 @@
 
 ## 🔄 Version History
 
-### 1.1.0 — Add `lmf` learning-first flow
+### 1.2.1 — Improve `/lmf` for manual coding
+
+- Update `lmf` so it remains learning-first but also includes copyable code blocks when implementation detail is needed.
+- Position `/lmf` as the manual-coding alternative to `/execute` when the user wants to type the code themselves instead of having the agent apply it automatically.
+
+### 1.2.0 — Add `/prd` command
+
+- Add `write-prd` skill. Add `/prd` command for Claude Code and Antigravity.
+
+### 1.1.0 — Add `/lmf` command
 
 - Add `lmf` skills. Add `/lmf` command for Claude Code and Antigravity. 
 
 ### 1.0.0 — Initial ALENA Release
 
 - 🧠 **ALENA identity and public release reset** — the toolkit starts at `v1.0.0` with ALENA branding, updated install commands, refreshed docs, and release surfaces aligned under the new package and repository.
-- 🤖 **Full asset library included** — ships with **34 skills**, **35 commands**, **38 workflows**, and **9 specialist agents** covering brainstorming, planning, execution, debugging, auditing, review, verification, memory, and team coordination.
+- 🤖 **Full asset library included** — ships with **35 skills**, **36 commands**, **39 workflows**, and **9 specialist agents** covering brainstorming, planning, PRD creation, execution, debugging, auditing, review, verification, memory, and team coordination.
 - ⚙️ **Deterministic planning core** — `planning-tools.cjs` plus **12 supporting CLI modules** handle state, phase, roadmap, verification, frontmatter, config, templates, milestones, model resolution, and council coordination without relying on brittle freeform markdown edits.
 - 🏛️ **Council system built in** — real subagent spawning, structured handoffs, code-enforced quality gates, task boards, and 6 presets (`full`, `rapid`, `debug`, `architecture`, `refactoring`, `audit`) are included in the first release.
 - 🪝 **Hook and session tooling** — includes **8 hooks** for statusline, update checks, context monitoring, memory capture, cost tracking, and related session behavior where the target runtime supports them.
@@ -121,6 +141,22 @@ npx @radenadri/skills-alena list
 
 After installing skills, your workflow depends on whether you're starting fresh or joining an existing codebase.
 
+### First question: do you need a PRD?
+
+If you only have an idea, a product problem, or a rough feature request, start with `/prd` before engineering planning.
+
+- `/prd` clarifies the user, problem, goals, non-goals, constraints, and success metrics.
+- `/discuss` locks implementation preferences and trade-off decisions before planning.
+- `/plan` turns the approved PRD or clarified request into implementation work.
+
+Think of it as:
+
+```text
+/prd = what and why
+/discuss = preference and trade-off lock-in
+/plan = how to build it
+```
+
 ### 🟢 New Project (Greenfield)
 
 > You're building something from scratch. No existing code, no legacy decisions.
@@ -129,6 +165,10 @@ After installing skills, your workflow depends on whether you're starting fresh
 ┌─────────────────────────────────────────────────────────────────┐
 │  GREENFIELD WORKFLOW                                            │
 │                                                                 │
+│  Step 0 ─ /prd (optional)                                       │
+│           Use when the project or feature idea is still fuzzy    │
+│           Produces a product requirements document first         │
+│                          ▼                                      │
 │  Step 1 ─ /init-project                                         │
 │           Creates .planning/ structure, ROADMAP, REQUIREMENTS    │
 │           Bootstraps memory system + config.json                 │
@@ -159,10 +199,13 @@ After installing skills, your workflow depends on whether you're starting fresh
 # 1. Install skills
 npx @radenadri/skills-alena add
 
-# 2. Tell your AI agent:
+# 2. If the product idea is still fuzzy, start here:
+/prd "describe the product or feature idea"
+
+# 3. Then tell your AI agent:
 /init-project
 
-# 3. The agent will walk you through:
+# 4. The agent will walk you through:
 #    → Project context gathering
 #    → Requirements capture
 #    → Roadmap phases
@@ -186,20 +229,24 @@ npx @radenadri/skills-alena add
 │           Writes: MEMORY.md with project brain                   │
 │           Captures: architecture, conventions, known issues      │
 │                          ▼                                      │
-│  Step 3 ─ /discuss                                              │
+│  Step 3 ─ /prd (optional)                                       │
+│           Use for new feature work that needs product clarity    │
+│           Grounds the PRD in the real codebase constraints       │
+│                          ▼                                      │
+│  Step 4 ─ /discuss                                              │
 │           "I want to add [feature] to this existing project"     │
 │           Agent asks MCQ questions considering existing patterns  │
 │           Quick-answer: "1A 2B 3C 4A"                           │
 │                          ▼                                      │
-│  Step 4 ─ /plan                                                 │
+│  Step 5 ─ /plan                                                 │
 │           Creates plan that respects existing architecture       │
 │           References real files, real patterns, real conventions  │
 │                          ▼                                      │
-│  Step 5 ─ /execute                                              │
+│  Step 6 ─ /execute                                              │
 │           Implements following existing patterns                 │
 │           codebase-conformity skill ensures consistency           │
 │                          ▼                                      │
-│  Step 6 ─ /verify                                               │
+│  Step 7 ─ /verify                                               │
 │           Validates against plan + existing test suite            │
 └─────────────────────────────────────────────────────────────────┘
 ```
@@ -212,10 +259,15 @@ npx @radenadri/skills-alena add
 # 2. Tell your AI agent:
 /memory init
 
-# 3. Let the agent scan your codebase, then:
+# 3. Let the agent scan your codebase
+
+# 4. If the feature needs product clarification, do this next:
+/prd "describe the feature or product problem"
+
+# 5. Then lock implementation decisions:
 /discuss add user preferences feature
 
-# 4. Answer the MCQ questions, then:
+# 6. Answer the MCQ questions, then:
 /plan
 /execute
 ```
@@ -297,82 +349,83 @@ ALENA works with **30+ AI coding agents**. **12 platforms have full asset parity
 
 ## 📚 Complete Asset Catalog
 
-### 🧠 Skills (34)
+### 🧠 Skills (35)
 
 Skills are deep instructional documents that teach AI agents HOW to think about specific engineering tasks. Each skill contains principles, protocols, anti-patterns, and quality criteria.
 
-#### 🔷 Core Development (9 skills)
+#### 🔷 Core Development (10 skills)
 
 | # | Skill | Description |
 |:---:|:---|:---|
 | 1 | 💡 **brainstorming** | Creative ideation — mind maps, structured exploration, and divergent thinking before any feature work |
-| 2 | 🧭 **lmf** | Learning-first mode flow — wrapper skill that combines `brainstorming`, `writing-plans`, and `writing-documentation` into a tutorial-first orchestration pattern — ✨ NEW |
-| 3 | 📝 **writing-plans** | Task decomposition — dependency-aware plans with effort estimates, risk assessments, and implementation waves |
-| 4 | ⚙️ **executing-plans** | Plan execution — wave-based implementation with checkpoints, inline verification, and state tracking |
-| 5 | 🧪 **test-driven-development** | TDD methodology — red-green-refactor cycle, test architecture, fixture patterns, and coverage strategies |
-| 6 | 🐛 **systematic-debugging** | Scientific debugging — hypothesis-driven investigation with evidence chains and root cause analysis |
-| 7 | 🔍 **code-review** | Structured code review — security, performance, correctness checks with severity-based feedback |
-| 8 | ✅ **verification-before-completion** | Completion gates — automated checks, compliance verification, and regression testing before marking done |
-| 9 | 📦 **git-workflow** | Git best practices — conventional commits, branching strategies, PR workflows, and conflict resolution |
+| 2 | 📄 **write-prd** | Product requirements writing — interview-first wrapper skill that turns feature ideas into structured PRDs before engineering planning — ✨ NEW |
+| 3 | 🧭 **lmf** | Learning-first mode flow — wrapper skill that combines `brainstorming`, `writing-plans`, and `writing-documentation` into a tutorial-first orchestration pattern with copyable code when manual implementation is needed — ✨ NEW |
+| 4 | 📝 **writing-plans** | Task decomposition — dependency-aware plans with effort estimates, risk assessments, and implementation waves |
+| 5 | ⚙️ **executing-plans** | Plan execution — wave-based implementation with checkpoints, inline verification, and state tracking |
+| 6 | 🧪 **test-driven-development** | TDD methodology — red-green-refactor cycle, test architecture, fixture patterns, and coverage strategies |
+| 7 | 🐛 **systematic-debugging** | Scientific debugging — hypothesis-driven investigation with evidence chains and root cause analysis |
+| 8 | 🔍 **code-review** | Structured code review — security, performance, correctness checks with severity-based feedback |
+| 9 | ✅ **verification-before-completion** | Completion gates — automated checks, compliance verification, and regression testing before marking done |
+| 10 | 📦 **git-workflow** | Git best practices — conventional commits, branching strategies, PR workflows, and conflict resolution |
 
 #### 🔶 Auditing (10 skills)
 
 | # | Skill | Description |
 |:---:|:---|:---|
-| 10 | 🏛️ **architecture-audit** | Architecture review — modularity, coupling, SOLID compliance, dependency direction, and scalability assessment |
-| 11 | 🔒 **security-audit** | Security assessment — OWASP top 10, auth flows, input validation, secrets management, and vulnerability scanning |
-| 12 | ⚡ **performance-audit** | Performance profiling — N+1 queries, bundle sizes, runtime bottlenecks, caching opportunities, and load testing |
-| 13 | 🗄️ **database-audit** | Database health — schema design, indexing strategy, query optimization, migrations, and normalization review |
-| 14 | 🎨 **frontend-audit** | Frontend quality — component architecture, state management, rendering efficiency, and responsive design |
-| 15 | 🌐 **api-design-audit** | API design review — REST/GraphQL conventions, versioning, error handling, pagination, and documentation |
-| 16 | 📦 **dependency-audit** | Dependency health — outdated packages, security vulnerabilities, license compliance, and bundle impact |
-| 17 | 📊 **observability-audit** | Observability review — logging strategy, metrics, tracing, alerting, and production debugging capability |
-| 18 | ♿ **accessibility-audit** | Accessibility compliance — WCAG standards, keyboard navigation, screen reader support, and color contrast |
-| 19 | 🔄 **ci-cd-audit** | CI/CD pipeline review — build times, test reliability, deployment safety, and pipeline optimization |
+| 11 | 🏛️ **architecture-audit** | Architecture review — modularity, coupling, SOLID compliance, dependency direction, and scalability assessment |
+| 12 | 🔒 **security-audit** | Security assessment — OWASP top 10, auth flows, input validation, secrets management, and vulnerability scanning |
+| 13 | ⚡ **performance-audit** | Performance profiling — N+1 queries, bundle sizes, runtime bottlenecks, caching opportunities, and load testing |
+| 14 | 🗄️ **database-audit** | Database health — schema design, indexing strategy, query optimization, migrations, and normalization review |
+| 15 | 🎨 **frontend-audit** | Frontend quality — component architecture, state management, rendering efficiency, and responsive design |
+| 16 | 🌐 **api-design-audit** | API design review — REST/GraphQL conventions, versioning, error handling, pagination, and documentation |
+| 17 | 📦 **dependency-audit** | Dependency health — outdated packages, security vulnerabilities, license compliance, and bundle impact |
+| 18 | 📊 **observability-audit** | Observability review — logging strategy, metrics, tracing, alerting, and production debugging capability |
+| 19 | ♿ **accessibility-audit** | Accessibility compliance — WCAG standards, keyboard navigation, screen reader support, and color contrast |
+| 20 | 🔄 **ci-cd-audit** | CI/CD pipeline review — build times, test reliability, deployment safety, and pipeline optimization |
 
 #### 🔷 Evolution (4 skills)
 
 | # | Skill | Description |
 |:---:|:---|:---|
-| 20 | ♻️ **refactoring-safely** | Safe refactoring — incremental transformation with test coverage, feature flags, and rollback strategies |
-| 21 | 📖 **writing-documentation** | Documentation authoring — API docs, architecture diagrams, README standards, and knowledge transfer |
-| 22 | 🗺️ **codebase-mapping** | Codebase analysis — module boundaries, dependency graphs, entry points, and health metrics |
-| 23 | 🚨 **incident-response** | Incident handling — triage protocols, root cause analysis, post-mortems, and prevention measures |
+| 21 | ♻️ **refactoring-safely** | Safe refactoring — incremental transformation with test coverage, feature flags, and rollback strategies |
+| 22 | 📖 **writing-documentation** | Documentation authoring — API docs, architecture diagrams, README standards, and knowledge transfer |
+| 23 | 🗺️ **codebase-mapping** | Codebase analysis — module boundaries, dependency graphs, entry points, and health metrics |
+| 24 | 🚨 **incident-response** | Incident handling — triage protocols, root cause analysis, post-mortems, and prevention measures |
 
 #### 🟣 Agent Intelligence (2 skills)
 
 | # | Skill | Description |
 |:---:|:---|:---|
-| 24 | 💾 **persistent-memory** | Automated session memory — captures decisions, context, and learnings across sessions via file-based protocols. Zero infrastructure, works in ANY agent. Inspired by [claude-mem](https://github.com/thedotmack/claude-mem). |
-| 25 | 💎 **agent-team-coordination** | **LLM Council** — Manager-orchestrated multi-agent coordination with Memory Module. Manager has full project knowledge (schemas, routes, services), dynamically routes tasks to specialist sub-agents, enables peer communication, handles escalations across 6 council presets. |
+| 25 | 💾 **persistent-memory** | Automated session memory — captures decisions, context, and learnings across sessions via file-based protocols. Zero infrastructure, works in ANY agent. Inspired by [claude-mem](https://github.com/thedotmack/claude-mem). |
+| 26 | 💎 **agent-team-coordination** | **LLM Council** — Manager-orchestrated multi-agent coordination with Memory Module. Manager has full project knowledge (schemas, routes, services), dynamically routes tasks to specialist sub-agents, enables peer communication, handles escalations across 6 council presets. |
 
 #### 🔶 Integration & Completeness (4 skills)
 
 | # | Skill | Description |
 |:---:|:---|:---|
-| 26 | 🔗 **full-stack-api-integration** | End-to-end API integration — spec analysis, surface mapping, SOLID-compliant API layer design, systematic endpoint implementation, and integration testing |
-| 27 | 🏥 **product-completeness-audit** | Functional completeness verification — 5-level completeness spectrum, placeholder detection, broken flow identification, and API connection validation |
-| 28 | 🔬 **brutal-exhaustive-audit** | No-shortcuts 5-pass audit — build verification, route checking, data flow tracing, user flow testing, and edge case validation with anti-shortcut rules |
-| 29 | 🔄 **codebase-conformity** | Pattern uniformity enforcement — read existing patterns before writing, match them exactly, and double-verify conformity before claiming done |
+| 27 | 🔗 **full-stack-api-integration** | End-to-end API integration — spec analysis, surface mapping, SOLID-compliant API layer design, systematic endpoint implementation, and integration testing |
+| 28 | 🏥 **product-completeness-audit** | Functional completeness verification — 5-level completeness spectrum, placeholder detection, broken flow identification, and API connection validation |
+| 29 | 🔬 **brutal-exhaustive-audit** | No-shortcuts 5-pass audit — build verification, route checking, data flow tracing, user flow testing, and edge case validation with anti-shortcut rules |
+| 30 | 🔄 **codebase-conformity** | Pattern uniformity enforcement — read existing patterns before writing, match them exactly, and double-verify conformity before claiming done |
 
 #### 🔀 Migration (1 skill)
 
 | # | Skill | Description |
 |:---:|:---|:---|
-| 30 | 🔀 **nextjs-to-nuxt-migration** | Next.js → Nuxt 4 migration — submodule analysis, backend verification, multi-pass execution (backend wiring → feature completeness → CSS polish → verification), sidebar registration, theme/dark-mode rules, URL encoding, Agent Team File Protocol, and Playwright visual QA |
+| 31 | 🔀 **nextjs-to-nuxt-migration** | Next.js → Nuxt 4 migration — submodule analysis, backend verification, multi-pass execution (backend wiring → feature completeness → CSS polish → verification), sidebar registration, theme/dark-mode rules, URL encoding, Agent Team File Protocol, and Playwright visual QA |
 
 #### 🔸 Meta (5 skills)
 
 | # | Skill | Description |
 |:---:|:---|:---|
-| 31 | 📘 **using-skills** | How to use and combine skills effectively in your workflow |
-| 32 | ✍️ **writing-skills** | How to create new skills — format, quality standards, and testing requirements |
-| 33 | 🎨 **ui-ux-redesign** | Full-stack visual audit — inventories backend APIs, audits every component and design token, analyzes user flows, and produces layered redesign recommendations |
-| 34 | 📏 **_rules** | Master rules skill — consolidates core principles, anti-hallucination protocol, severity framework, and skill activation table |
+| 32 | 📘 **using-skills** | How to use and combine skills effectively in your workflow |
+| 33 | ✍️ **writing-skills** | How to create new skills — format, quality standards, and testing requirements |
+| 34 | 🎨 **ui-ux-redesign** | Full-stack visual audit — inventories backend APIs, audits every component and design token, analyzes user flows, and produces layered redesign recommendations |
+| 35 | 📏 **_rules** | Master rules skill — consolidates core principles, anti-hallucination protocol, severity framework, and skill activation table |
 
 ---
 
-### ⚡ Commands (35)
+### ⚡ Commands (36)
 
 Commands are Claude Code slash commands (`.md` files installed to `.claude/commands/`). They provide structured workflows for common project tasks.
 
@@ -382,7 +435,8 @@ Commands are Claude Code slash commands (`.md` files installed to `.claude/comma
 |:---|:---|
 | `/init-project` | 🏗️ Initialize a new project with `.planning/` directory — `PROJECT.md`, `REQUIREMENTS.md`, `ROADMAP.md`, `STATE.md`, `config.json`. Uses `planning-tools.cjs` for deterministic bootstrapping. |
 | `/discuss` | 💬 Pre-planning MCQ decision capture — presents multiple-choice questions with recommendations, quick-answer format (`1A 2B 3C`), locks decisions in CONTEXT.md |
-| `/lmf` | 🧭 Learning-first tutorial flow — uses the local `lmf` wrapper skill to combine explanation, planning, and documentation-style guidance before execution — ✨ NEW |
+| `/prd` | 📄 Product requirements drafting — interview-first flow that uses the local `write-prd` wrapper skill to produce a reusable PRD before implementation planning — ✨ NEW |
+| `/lmf` | 🧭 Learning-first tutorial flow — uses the local `lmf` wrapper skill to combine explanation, planning, and copyable code guidance before execution — ✨ NEW |
 | `/plan` | 📋 Create a 2-3 task implementation plan with task anatomy (`<files>` `<action>` `<verify>` `<done>`), context budgets, and locked decision enforcement |
 | `/execute` | ⚙️ Execute an implementation plan with deviation protocol (4 categories), checkpoint system, and `planning-tools.cjs` state management |
 | `/verify` | ✅ Validate implementations against plans — automated checks, compliance verification, regression testing, conversational UAT |
@@ -453,7 +507,7 @@ Commands are Claude Code slash commands (`.md` files installed to `.claude/comma
 
 ---
 
-### 🔄 Workflows (38)
+### 🔄 Workflows (39)
 
 Workflows are Antigravity step-by-step execution scripts (`.md` files installed to `.agent/workflows/`). Many include `// turbo` annotations for auto-execution.
 
@@ -461,7 +515,8 @@ Workflows are Antigravity step-by-step execution scripts (`.md` files installed
 |:---|:---|
 | `/init-project` | 🏗️ Initialize project with `.planning/` structure |
 | `/discuss` | 💬 Pre-planning MCQ discussion with quick-answer |
-| `/lmf` | 🧭 Learning-first tutorial workflow that mirrors the local `lmf` wrapper skill in Antigravity — ✨ NEW |
+| `/prd` | 📄 Product requirements workflow that mirrors the local `write-prd` wrapper skill in Antigravity — ✨ NEW |
+| `/lmf` | 🧭 Learning-first tutorial workflow that mirrors the local `lmf` wrapper skill in Antigravity, including copyable code when implementation is needed — ✨ NEW |
 | `/plan-feature` | 📋 Plan a feature with research, design, and task decomposition |
 | `/execute` | ⚙️ Execute plans with wave-based steps and verification |
 | `/verify` | ✅ Validate implementation against plans |
@@ -635,64 +690,25 @@ Use `/memory init` to initialize, `/memory write` to save.
 
 ---
 
-## 💎 LLM Council v2 — Agent Team Coordination
-
-### The Problem
-AI coding tasks fail at scale because no single agent can hold all context: database schemas, API routes, service dependencies, frontend components, and business logic — simultaneously. Linear handoffs lose context. Role-switching in a single context window wastes tokens.
-
-### The Solution: Real Subagent Spawning + Deterministic Orchestration
-
-**Council v2** replaces the old role-switching pattern with **real subagent spawning** via `Task()`. Each specialist agent gets a fresh 200k context window — no shared context pollution. The orchestrator stays lean at ~10-15% context usage.
-
-```
-                    ╔═══════════════════════════════╗
-                    ║     🎯 ORCHESTRATOR (lean)      ║
-                    ║  ~10-15% context usage           ║
-                    ║  13 deterministic CLI commands    ║
-                    ║  Code-enforced quality gates      ║
-                    ╚════════════╦══════════════════╝
-                                 ║
-                        Task() spawning
-              ┌──────────────────┼──────────────────┐
-       ┌──────▼──┐ ┌──────▼──┐ ┌──▼────┐ ┌──▼──────┐
-       │🔬Research│ │📐Planner│ │⚙️Exec │ │🔍Review │
-       │ Fresh    │ │ Fresh   │ │ Fresh │ │ Fresh   │
-       │ 200k ctx │ │ 200k   │ │ 200k  │ │ 200k   │
-       └──────────┘ └────────┘ └──────┘ └─────────┘
-```
-
-### Key Capabilities
-
-| Capability | Description |
-|:---|:---|
-| 🧠 **Real subagent spawning** | Each agent gets a fresh 200k context via `Task()` — no shared context pollution |
-| 🎛️ **13 CLI commands** | Deterministic state machine for council orchestration (`council start`, `council next`, `council status`, etc.) |
-| 🚪 **Code-enforced quality gates** | Agents cannot advance phases without passing automated gate checks |
-| 🎯 **6 presets** | Full, Rapid, Debug, Architecture, Refactoring, Audit councils |
-| 📐 **Lean orchestrator** | Orchestrator uses ~10-15% context — delegates deep work to specialists |
-| 🧠 **Memory Module** | Deep intelligence layer: schemas, routes, services, components, tech stack |
-
----
-
 ## 📁 Project Structure
 
 ```
 alena/
-├── 📂 skills/                   # 32 deep instructional skills
+├── 📂 skills/                   # 35 deep instructional skills
 │   ├── brainstorming/SKILL.md
 │   ├── writing-plans/SKILL.md          # Plans-as-prompts with task anatomy
 │   ├── executing-plans/SKILL.md        # Deviation protocol + checkpoints
 │   ├── persistent-memory/SKILL.md
 │   ├── agent-team-coordination/SKILL.md
 │   └── ... (26 more)
-├── 📂 commands/                 # 34 Claude Code slash commands
+├── 📂 commands/                 # 36 Claude Code slash commands
 │   ├── init-project.md
 │   ├── discuss.md                       ✨ MCQ decision capture
 │   ├── settings.md                      ✨ Config management
 │   ├── memory.md
 │   ├── team.md
 │   └── ... (23 more)
-├── 📂 workflows/                # 37 Antigravity workflows
+├── 📂 workflows/                # 39 Antigravity workflows
 │   ├── init-project.md
 │   ├── discuss.md                       ✨ MCQ discussion workflow
 │   ├── gap-closure.md                   ✨ Execution gap closure
@@ -745,6 +761,7 @@ npx @radenadri/skills-alena add --global
 # Install specific skills
 npx @radenadri/skills-alena add persistent-memory code-review
 npx @radenadri/skills-alena add lmf brainstorming writing-plans writing-documentation
+npx @radenadri/skills-alena add write-prd brainstorming writing-documentation
 
 # Update all skills to latest version
 npx @radenadri/skills-alena update
@@ -788,7 +805,7 @@ npx @radenadri/skills-alena help
 | **GEMINI.md** | Appends activation section (preserves your content). Updates on re-install. | ❌ Skipped |
 | **Memory** | Never installed (created at runtime per-project). | ❌ Never installed |
 
-If you want the full local `lmf` experience, install locally so the `lmf` wrapper skill can be paired with the Claude Code `/lmf` command and the Antigravity `/lmf` workflow. Global install still includes the `lmf` skill itself, but not the local command/workflow surfaces.
+If you want the full local experience, install locally so wrapper skills can be paired with their agent-specific surfaces. That applies to both `lmf` and PRD drafting: global install includes the `lmf` and `write-prd` skills, but the Claude Code `/lmf` and `/prd` commands plus the Antigravity `/lmf` and `/prd` workflows are local-only surfaces.
 
 ### What Gets Installed Where
 
@@ -808,12 +825,15 @@ If you want the full local `lmf` experience, install locally so the `lmf` wrappe
 |:---|:---|
 | [🌐 Website](https://alena.radenadri.xyz) | Product homepage and primary landing page |
 | [📖 Wiki](https://github.com/radenadri/skills-alena/wiki) | Comprehensive GitHub Wiki with guides and reference |
+| [`skills/write-prd/SKILL.md`](skills/write-prd/SKILL.md) | Local wrapper skill for interview-first PRD creation |
+| [`commands/prd.md`](commands/prd.md) | Claude Code `/prd` product requirements command |
+| [`workflows/prd.md`](workflows/prd.md) | Antigravity `/prd` product requirements workflow |
 | [`skills/lmf/SKILL.md`](skills/lmf/SKILL.md) | Local wrapper skill for the `lmf` orchestrator pattern |
 | [`commands/lmf.md`](commands/lmf.md) | Claude Code `/lmf` learning-first command |
 | [`workflows/lmf.md`](workflows/lmf.md) | Antigravity `/lmf` learning-first workflow |
 | [Agent Teams & Memory](docs/AGENT-TEAMS-AND-MEMORY.md) | Comprehensive guide to the team coordination and persistent memory systems |
 | [Competitive Analysis](docs/COMPETITIVE_ANALYSIS.md) | Analysis of GSD, Claude Code, Cursor, and Antigravity frameworks |
-| [Audit Report](docs/AUDIT-REPORT.md) | Comprehensive 10/10 quality audit of all 29 skills |
+| [Audit Report](docs/AUDIT-REPORT.md) | Comprehensive quality audit report for the ALENA skill library |
 | [Contributing](CONTRIBUTING.md) | How to contribute to this project |
 | [Changelog](CHANGELOG.md) | Version history and release notes |
 
@@ -823,9 +843,9 @@ If you want the full local `lmf` experience, install locally so the `lmf` wrappe
 
 | Metric | Count |
 |:---:|:---:|
-| 🧠 Skills | **34** |
-| ⚡ Commands | **35** |
-| 🔄 Workflows | **38** |
+| 🧠 Skills | **35** |
+| ⚡ Commands | **36** |
+| 🔄 Workflows | **39** |
 | 🤖 Agents | **9** |
 | 🎯 Cursor Rules | **10** |
 | 📏 Rules | **5** |

package/commands/lmf.md

@@ -1,6 +1,6 @@
 ---
 name: lmf
-description: "Run the learning-first /lmf flow for tutorial-style planning and explanation before execution."
+description: "Run the learning-first /lmf flow for tutorial-style planning, explanation, and copyable code before execution."
 disable-model-invocation: true
 argument-hint: "[topic-or-task]"
 ---
@@ -18,6 +18,7 @@ Guide the user through the request in a tutorial-first way using the local `lmf`
    - Mental model
    - Recommended path
    - Step-by-step actions
+   - Copyable code
    - Next move
 4. Compose the existing ALENA skills inside the response:
    - `brainstorming` for intent and trade-offs
@@ -26,11 +27,13 @@ Guide the user through the request in a tutorial-first way using the local `lmf`
 5. Keep the output local-first and tutorial-first:
    - Explain before optimizing
    - Be specific to the current request and codebase
-   - Use small examples only when they reduce ambiguity
+   - Include copyable code blocks when the user needs to implement manually or when code would teach faster than prose
+   - Prefer complete file-level snippets over pseudo-code and placeholders
    - Do not turn `/lmf` into a shell-script or helper-script instruction
 
 ## Success Criteria
 
 - The user understands the problem shape before seeing the steps
 - The response contains a clear recommendation with trade-offs
+- The response includes copyable code when implementation detail is needed
 - The next action is explicit enough to execute immediately

package/commands/prd.md

@@ -0,0 +1,35 @@
+---
+name: prd
+description: "Create a product requirements document through an interview-first PRD workflow."
+disable-model-invocation: true
+argument-hint: "[feature-or-product-problem]"
+---
+
+# /prd - Product Requirements Document
+
+Create a structured PRD using the local `write-prd` wrapper skill.
+
+## Instructions
+
+1. Read `skills/write-prd/SKILL.md` and follow it exactly.
+2. Use `$ARGUMENTS` as the starting feature idea, product problem, or PRD topic.
+3. Interview before drafting:
+   - clarify the user
+   - clarify the problem
+   - clarify goals and non-goals
+   - clarify constraints, risks, and success definition
+4. Compose ALENA's underlying logic:
+   - `brainstorming` for discovery and trade-offs
+   - `writing-documentation` for the final PRD structure and clarity
+   - `writing-plans` only as a handoff suggestion after the PRD is accepted
+5. Keep the output product-first:
+   - write requirements as outcomes, not code tasks
+   - call out assumptions and open questions
+   - include explicit non-goals
+   - end with the next recommended step
+
+## Success Criteria
+
+- The PRD is grounded in an interview, not guesswork
+- The document is understandable without the full chat history
+- The output is a real product artifact, not an implementation checklist

package/dist/cli.js

@@ -288,6 +288,7 @@ var SKILL_CATEGORIES = {
   "Core Development": [
     "brainstorming",
     "lmf",
+    "write-prd",
     "writing-plans",
     "executing-plans",
     "test-driven-development",
@@ -481,13 +482,14 @@ Skills activate automatically when their conditions are met. You MUST use the re
 ### Workflows
 
 Workflows are installed in \`${agent.workflowsDir}/\`. Use \`/workflow-name\` to execute them. Workflows with \`// turbo\` annotations auto-run safe steps. Use \`/lmf\` for learning-first tutorial and explanation flow.
+Workflows are installed in \`${agent.workflowsDir}/\`. Use \`/workflow-name\` to execute them. Workflows with \`// turbo\` annotations auto-run safe steps. Use \`/lmf\` for learning-first tutorial and explanation flow, and \`/prd\` for interview-first product requirements drafting.
 `;
   }
   if (hasCommands) {
     content += `
 ### Commands
 
-Slash commands are available in \`${agent.commandsDir}/\`. Key commands include: \`/audit\`, \`/debug\`, \`/lmf\`, \`/plan\`, \`/execute\`, \`/verify\`, \`/commit\`, \`/team\`, \`/memory\`.
+Slash commands are available in \`${agent.commandsDir}/\`. Key commands include: \`/audit\`, \`/debug\`, \`/lmf\`, \`/prd\`, \`/plan\`, \`/execute\`, \`/verify\`, \`/commit\`, \`/team\`, \`/memory\`.
 `;
   }
   if (hasAgentDefs) {