@slamb2k/mad-skills 2.0.14 → 2.0.16

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "mad-skills",
   "description": "AI-assisted planning, development and governance tools",
-  "version": "2.0.14",
+  "version": "2.0.16",
   "author": {
     "name": "slamb2k",
     "url": "https://github.com/slamb2k"

package/README.md

@@ -2,7 +2,7 @@
 
 ![Mad Skills](assets/mad-skills.png)
 
-A skill framework for Claude Code. Ships 8 skills covering the full development lifecycle — from project initialization to shipping PRs.
+A skill framework for Claude Code. Ships 10 skills covering the full development lifecycle — from project initialization to shipping PRs.
 
 ## Skills
 
@@ -11,19 +11,399 @@ A skill framework for Claude Code. Ships 8 skills covering the full development
 | **build** | `/build` | Context-isolated feature development pipeline. Takes a design/plan and executes explore, question, architect, implement, review, ship inside subagents. |
 | **brace** | `/brace` | Initialize projects with the GOTCHA/BRACE framework. Creates 6-layer structure, BRACE build methodology, and project CLAUDE.md. |
 | **distil** | `/distil` | Generate multiple unique web design variations. Creates a Vite + React + TypeScript + Tailwind project with N designs at /1, /2, /3. |
+| **dock** | `/dock` | Generate container release pipelines. Builds once, promotes immutable images through dev → staging → prod. Supports Azure Container Apps, AWS Fargate, Cloud Run, Kubernetes, Dokku, Coolify, CapRover. |
+| **keel** | `/keel` | Generate IaC pipelines (Terraform, Bicep, Pulumi, CDK) to provision cloud infrastructure. Plans on PR, applies on merge. Provisions what /dock deploys to. |
 | **prime** | `/prime` | Load project context before feature work. Supports domain-specific context (security, routing, dashboard, etc.). |
 | **rig** | `/rig` | Bootstrap repos with lefthook hooks, commit templates, PR templates, and GitHub Actions workflows. Idempotent. |
 | **ship** | `/ship` | Full PR lifecycle — sync with main, create branch, commit, push, create PR, wait for CI, fix issues, squash merge, cleanup. |
 | **speccy** | `/speccy` | Interview-driven specification builder. Reviews code/docs, interviews through targeted questions, produces structured specs. |
 | **sync** | `/sync` | Sync local repo with origin/main. Stashes changes, pulls, restores stash, cleans up stale branches. |
 
+## Lifecycle Overview
+
+The 10 skills form a complete development-to-deployment pipeline. Each skill produces artifacts that downstream skills consume.
+
+```mermaid
+graph LR
+    A["/brace<br/>Project Init"] --> B["/rig<br/>Dev Tooling"]
+    B --> C["/speccy<br/>Spec Builder"]
+    C --> D["/build<br/>Features"]
+    D --> E["/ship<br/>Merge PRs"]
+    E --> F["/keel<br/>Infra (IaC)"]
+    F --> G["/dock<br/>Deploy"]
+
+    style A fill:#4a9eff,color:#fff
+    style B fill:#4a9eff,color:#fff
+    style C fill:#9b59b6,color:#fff
+    style D fill:#2ecc71,color:#fff
+    style E fill:#2ecc71,color:#fff
+    style F fill:#e67e22,color:#fff
+    style G fill:#e67e22,color:#fff
+```
+
+| Phase | Skills | What happens |
+|-------|--------|--------------|
+| **Setup** | `/brace` → `/rig` | Initialize project structure, install hooks, templates, CI workflows |
+| **Develop** | `/speccy` → `/build` → `/ship` | Spec features, implement in isolated subagents, merge via PR lifecycle |
+| **Deploy** | `/keel` → `/dock` | Provision cloud infrastructure, then deploy containers to it |
+
+Supporting skills (`/sync`, `/prime`, `/distil`) are used as needed throughout:
+- `/sync` — Pull latest changes before starting work
+- `/prime` — Load domain context before complex features
+- `/distil` — Generate multiple web design variations
+
+---
+
+## End-to-End Walkthrough
+
+This walkthrough follows a Node.js app from an empty folder to a deployed container running on cloud infrastructure.
+
+### Step 0: Session Guard
+
+When you open Claude Code in any project with the mad-skills plugin installed, the **session guard** runs automatically. It validates your development environment before you write a single line of code.
+
+```
+┌─────────────────────────────────────────────────────┐
+│  Session Guard — automatic on every session start    │
+│                                                      │
+│  ✅ CLAUDE.md found                                  │
+│  ✅ Git repository initialized                       │
+│  ✅ On branch: main                                  │
+│  ⚠️  CLAUDE.md last modified 5 days ago              │
+│  ℹ️  Task list configured: my-project                │
+└─────────────────────────────────────────────────────┘
+```
+
+The session guard checks: git status, CLAUDE.md presence and freshness, task list configuration, and branch state. If issues are found, they're surfaced before your first prompt.
+
+---
+
+### Step 1: `/brace` — Initialize the Project
+
+Start in an empty folder. `/brace` creates the project skeleton using the GOTCHA/BRACE framework.
+
+```
+> /brace my-webapp
+```
+
+**What it generates:**
+
+```
+my-webapp/
+├── CLAUDE.md              # AI-readable project instructions
+├── goals/                 # Project goals and success criteria
+├── orchestration/         # Workflow definitions
+├── tools/                 # Tool configurations
+├── context/               # Domain knowledge
+├── hard_prompts/          # Reusable prompt templates
+└── args/                  # Runtime parameters
+```
+
+The CLAUDE.md it creates becomes the foundation — every subsequent skill reads it for project context.
+
+---
+
+### Step 2: `/rig` — Set Up Dev Tooling
+
+With the skeleton in place, `/rig` bootstraps the development infrastructure.
+
+```
+> /rig
+```
+
+**What it generates:**
+
+```
+my-webapp/
+├── .github/
+│   ├── workflows/ci.yml       # PR validation pipeline
+│   └── pull_request_template.md
+├── .lefthook.yml              # Git hooks (lint, test on commit)
+├── .commitlintrc.yml          # Conventional commit enforcement
+└── .editorconfig              # Consistent formatting
+```
+
+`/rig` is idempotent — run it again later and it updates without overwriting your customizations.
+
+---
+
+### Step 3: `/speccy` — Specify What to Build
+
+Before writing code, `/speccy` interviews you to create a detailed specification.
+
+```
+> /speccy a user authentication system with OAuth2
+```
+
+It asks targeted questions about requirements, edge cases, security concerns, and technical constraints, then produces a structured spec document that `/build` can consume.
+
+---
+
+### Step 4: `/build` — Implement Features
+
+Feed the spec (or any design) to `/build`. It runs the entire development lifecycle inside isolated subagents so your main conversation stays clean.
+
+```
+> /build implement the auth system from specs/auth-spec.md
+```
+
+```mermaid
+graph TD
+    A["Stage 1: Explore<br/>Understand codebase"] --> B["Stage 2: Question<br/>Clarify ambiguities"]
+    B --> C["Stage 3: Architect<br/>Design solution"]
+    C --> D["Stage 4: Implement<br/>Write code"]
+    D --> E["Stage 5: Review<br/>Check quality"]
+    E --> F["Stage 6: Ship<br/>Invoke /ship"]
+
+    style A fill:#3498db,color:#fff
+    style B fill:#3498db,color:#fff
+    style C fill:#9b59b6,color:#fff
+    style D fill:#2ecc71,color:#fff
+    style E fill:#e74c3c,color:#fff
+    style F fill:#f39c12,color:#fff
+```
+
+Each stage runs in a subagent with its own context. The primary conversation only receives structured reports.
+
+---
+
+### Step 5: `/ship` — Merge via PR
+
+When features are ready, `/ship` handles the entire PR lifecycle.
+
+```
+> /ship
+```
+
+```mermaid
+sequenceDiagram
+    participant Dev as Developer
+    participant Ship as /ship
+    participant GH as GitHub
+    participant CI as CI Pipeline
+
+    Dev->>Ship: /ship
+    Ship->>Ship: Stage 1: Sync with main
+    Ship->>Ship: Stage 2: Analyze, commit, push
+    Ship->>GH: Create PR
+    Ship->>CI: Stage 3: Monitor checks
+    CI-->>Ship: All checks passed ✅
+    Ship->>GH: Stage 5: Squash merge
+    Ship->>Ship: Sync local main, cleanup branches
+    Ship-->>Dev: Ship complete ✅
+```
+
+If CI fails, `/ship` automatically reads the failure logs, fixes the code, pushes a fix commit, and re-monitors — up to 2 attempts before asking for help.
+
+---
+
+### Step 6: `/keel` — Provision Infrastructure
+
+Before deploying, you need infrastructure. `/keel` interviews you about your cloud setup and generates IaC files.
+
+```
+> /keel
+```
+
+The interview covers: cloud provider, IaC tool, components needed, environments, state management, naming conventions, and resource sizing.
+
+**Example output for Azure + Terraform:**
+
+```
+my-webapp/
+├── infra/
+│   ├── main.tf                  # Provider, backend, module calls
+│   ├── variables.tf             # Input variables
+│   ├── outputs.tf               # Registry URL, endpoints, connection strings
+│   ├── versions.tf              # Required providers
+│   ├── bootstrap.sh             # One-time state backend setup
+│   ├── sync-outputs.sh          # Sync TF outputs → CI/CD variables
+│   ├── environments/
+│   │   ├── dev.tfvars
+│   │   ├── staging.tfvars
+│   │   └── prod.tfvars
+│   └── modules/
+│       ├── registry/            # Azure Container Registry
+│       ├── compute/             # Azure Container Apps
+│       ├── database/            # PostgreSQL Flexible Server
+│       ├── networking/          # VNet, subnets
+│       └── monitoring/          # Log Analytics, App Insights
+└── .github/workflows/
+    └── infra.yml                # Plan on PR, apply on merge
+```
+
+**Infrastructure pipeline flow:**
+
+```mermaid
+graph LR
+    subgraph "PR Phase"
+        A["Push infra/ changes"] --> B["terraform plan"]
+        B --> C["Post plan as<br/>PR comment"]
+    end
+
+    subgraph "Merge Phase"
+        D["Merge to main"] --> E["terraform apply<br/>(dev)"]
+        E --> F["Sync outputs to<br/>CI/CD variables"]
+    end
+
+    subgraph "Promotion Phase"
+        G["Manual dispatch"] --> H["terraform apply<br/>(staging)"]
+        H --> I["terraform apply<br/>(prod)"]
+    end
+
+    C --> D
+    F --> G
+
+    style B fill:#3498db,color:#fff
+    style E fill:#2ecc71,color:#fff
+    style H fill:#e67e22,color:#fff
+    style I fill:#e74c3c,color:#fff
+```
+
+After `/keel` applies, the infrastructure outputs (registry URL, compute endpoints, database connection strings) are synced as CI/CD variables for `/dock` to consume.
+
+---
+
+### Step 7: `/dock` — Deploy Containers
+
+With infrastructure provisioned, `/dock` creates the release pipeline that builds and deploys your app.
+
+```
+> /dock
+```
+
+The interview covers: container registry, environments, deployment targets per environment, testing gates, secrets, and rollback strategy.
+
+**Example output:**
+
+```
+my-webapp/
+├── Dockerfile                   # Multi-stage: deps → build → test → production
+├── .dockerignore
+├── docker-compose.yml           # Local dev parity
+├── deploy/
+│   └── environments.yml         # Per-environment config matrix
+└── .github/workflows/
+    └── deploy.yml               # Build, push, deploy pipeline
+```
+
+**The build-once-promote-everywhere pipeline:**
+
+```mermaid
+graph TD
+    subgraph "Build Phase (on merge to main)"
+        A["Checkout code"] --> B["Build image<br/>target: test"]
+        B --> C["Run tests<br/>inside container"]
+        C --> D["Build image<br/>target: production"]
+        D --> E["Push to registry<br/>tag: abc1234 + latest"]
+    end
+
+    subgraph "Deploy Dev"
+        E --> F["Deploy abc1234<br/>to dev"]
+        F --> G["Smoke tests ✅"]
+    end
+
+    subgraph "Promote to Staging (on release tag v1.2.3)"
+        G -.-> H["Retag abc1234<br/>as v1.2.3"]
+        H --> I["Deploy v1.2.3<br/>to staging"]
+        I --> J["Integration +<br/>e2e tests ✅"]
+    end
+
+    subgraph "Promote to Production"
+        J --> K["Deploy v1.2.3<br/>to production"]
+        K --> L["Post-deploy<br/>smoke test ✅"]
+    end
+
+    style B fill:#3498db,color:#fff
+    style D fill:#3498db,color:#fff
+    style E fill:#2ecc71,color:#fff
+    style H fill:#e67e22,color:#fff
+    style I fill:#e67e22,color:#fff
+    style K fill:#e74c3c,color:#fff
+
+    linkStyle 6 stroke:#999,stroke-dasharray:5
+```
+
+The critical principle: the release tag step **retags** the existing tested image — it never rebuilds. The exact same bytes that passed tests on `main` are what runs in production.
+
+---
+
+### Full Architecture
+
+Here's how all the pipelines connect in the final system:
+
+```mermaid
+graph TB
+    subgraph "Developer Workflow"
+        DEV["Developer"] -->|"/build"| CODE["Code Changes"]
+        CODE -->|"/ship"| PR["Pull Request"]
+    end
+
+    subgraph "CI Pipeline (/rig)"
+        PR --> LINT["Lint + Validate"]
+        LINT --> TEST["Unit Tests"]
+        TEST --> PASS{"Checks<br/>pass?"}
+        PASS -->|Yes| MERGE["Merge to main"]
+        PASS -->|No| FIX["/ship auto-fix"]
+        FIX --> LINT
+    end
+
+    subgraph "Infrastructure Pipeline (/keel)"
+        INFRA_PR["Infra PR"] --> PLAN["terraform plan"]
+        PLAN --> INFRA_MERGE["Merge"]
+        INFRA_MERGE --> APPLY_DEV["Apply to dev"]
+        APPLY_DEV --> SYNC["Sync outputs →<br/>CI/CD vars"]
+    end
+
+    subgraph "Deployment Pipeline (/dock)"
+        MERGE --> BUILD["Build container<br/>image"]
+        BUILD --> PUSH["Push to registry<br/>:sha + :latest"]
+        PUSH --> DEPLOY_DEV["Deploy to dev"]
+        DEPLOY_DEV --> SMOKE["Smoke tests"]
+
+        TAG["Release tag<br/>v1.2.3"] --> RETAG["Retag image<br/>(no rebuild)"]
+        RETAG --> DEPLOY_STG["Deploy staging"]
+        DEPLOY_STG --> E2E["e2e tests"]
+        E2E --> DEPLOY_PROD["Deploy production"]
+        DEPLOY_PROD --> FINAL["Post-deploy smoke"]
+    end
+
+    SYNC -.->|"Registry URL<br/>Endpoints"| BUILD
+
+    style DEV fill:#4a9eff,color:#fff
+    style MERGE fill:#2ecc71,color:#fff
+    style BUILD fill:#3498db,color:#fff
+    style PUSH fill:#3498db,color:#fff
+    style RETAG fill:#e67e22,color:#fff
+    style DEPLOY_PROD fill:#e74c3c,color:#fff
+```
+
+---
+
+### Quick Reference: What Each Skill Generates
+
+| Skill | Key artifacts | Consumed by |
+|-------|--------------|-------------|
+| `/brace` | `CLAUDE.md`, project skeleton | All other skills |
+| `/rig` | `.github/workflows/ci.yml`, hooks, templates | `/ship` (CI checks) |
+| `/speccy` | Specification document | `/build` (implementation guide) |
+| `/build` | Feature code, tests | `/ship` (files to commit) |
+| `/ship` | Commits, PRs, merged code | CI pipeline, `/dock` triggers |
+| `/keel` | `infra/` (Terraform/Bicep), `infra.yml` workflow | `/dock` (infrastructure outputs) |
+| `/dock` | `Dockerfile`, `deploy.yml`, `deploy/` config | CI/CD system (runtime) |
+| `/sync` | Clean working tree | Any skill (pre-work) |
+| `/prime` | Domain context in memory | `/build` (informed decisions) |
+| `/distil` | Multiple web design variations | `/build` (chosen design) |
+
+---
+
 ## Installation
 
 Three methods are available. The table below shows what each delivers:
 
 | | Plugin | npx skills | npm package |
 |---|---|---|---|
-| Skills (slash commands) | ✅ all 8 | ✅ all 8 | — |
+| Skills (slash commands) | ✅ all 10 | ✅ all 10 | — |
 | Agents (e.g. ship-analyzer) | ✅ | ❌ | — |
 | Session hooks (session-guard) | ✅ | ❌ | — |
 | Cross-agent (Cursor, Cline, etc.) | ❌ Claude Code only | ✅ | — |
@@ -111,10 +491,12 @@ ln -sfn "$DOTFILES_DIR/skills/my-skill" "$HOME/.claude/skills/my-skill"
 
 ```
 mad-skills/
-├── skills/                  # Skill definitions (8 skills)
+├── skills/                  # Skill definitions (10 skills)
 │   ├── build/
 │   ├── brace/
 │   ├── distil/
+│   ├── dock/
+│   ├── keel/
 │   ├── prime/
 │   ├── rig/
 │   ├── ship/
@@ -134,8 +516,7 @@ mad-skills/
 │   ├── marketplace.json
 │   └── plugin.json
 └── .github/workflows/
-    ├── ci.yml               # PR validation + evals
-    └── release.yml          # Tagged release → npm + GitHub
+    └── ci.yml               # Unified CI, evals, and release
 ```
 
 ### Skill Structure
@@ -176,16 +557,10 @@ npm test                         # validate + lint + eval
 
 ## CI/CD
 
-**PR pipeline** (`.github/workflows/ci.yml`):
-- Triggers on all pull requests (required status check)
-- Runs validate and lint
-- Runs evals when API key is available (skipped for external PRs)
-- Detects which skills changed and posts eval results as PR comments
-
-**Release pipeline** (`.github/workflows/release.yml`):
-- Phase 1: Triggers on push to main, validates, bumps patch version, creates auto-merge PR
-- Phase 2: When version bump merges, creates tag, publishes to npm with provenance
-- Builds `.skill` packages and creates a GitHub Release
+**Unified pipeline** (`.github/workflows/ci.yml`):
+- **On pull requests:** validate + lint, evals (when API key available), posts eval results as PR comments
+- **On push to main (non-release):** validates, bumps patch version, creates auto-merge PR
+- **On push to main (release):** creates version tag, publishes to npm with provenance, builds `.skill` packages, creates GitHub Release
 
 ## Archive
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@slamb2k/mad-skills",
-  "version": "2.0.14",
+  "version": "2.0.16",
   "description": "Claude Code skills collection — planning, development and governance tools",
   "type": "module",
   "repository": {

package/skills/brace/SKILL.md

@@ -2,7 +2,7 @@
 name: brace
 description: 'Initialize any project directory with the GOTCHA/BRACE framework for agentic AI systems. Creates the 6-layer structure (Goals, Orchestration, Tools, Context, Hard prompts, Args), BRACE build methodology, and a project CLAUDE.md. Recommends claude-mem for persistent memory. Idempotent — safe to run on existing projects. Triggers: "init gotcha", "setup brace", "brace", "initialize framework", "bootstrap gotcha".'
 argument-hint: "[--no-brace] [--force]"
-allowed-tools: Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion
+allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, AskUserQuestion
 ---
 
 # Brace - GOTCHA/BRACE Framework Bootstrap

package/skills/build/SKILL.md

@@ -2,7 +2,7 @@
 name: build
 description: Context-isolated feature development pipeline. Takes a detailed design/plan as argument and executes the full feature-dev lifecycle (explore, question, architect, implement, review, ship) inside subagents so the primary conversation stays compact. Use when you have a well-defined plan and want autonomous execution with minimal context window consumption.
 argument-hint: <detailed design/plan to implement> [--skip-questions] [--skip-review] [--no-ship] [--parallel-impl]
-allowed-tools: Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion
+allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, AskUserQuestion
 ---
 
 # Build - Context-Isolated Feature Development
@@ -60,6 +60,7 @@ Before starting, check all dependencies in this table:
 | Dependency | Type | Check | Required | Resolution | Detail |
 |-----------|------|-------|----------|------------|--------|
 | ship | skill | `.claude/skills/ship/SKILL.md` | yes | stop | Install with: npx skills add slamb2k/mad-skills --skill ship |
+| prime | skill | `.claude/skills/prime/SKILL.md` | no | fallback | Context loading; falls back to manual CLAUDE.md/goals scan |
 | feature-dev:code-explorer | agent | — | no | fallback | Uses general-purpose agent |
 | feature-dev:code-architect | agent | — | no | fallback | Uses general-purpose agent |
 | feature-dev:code-reviewer | agent | — | no | fallback | Uses general-purpose agent |
@@ -76,7 +77,10 @@ For each row, in order:
 4. After all checks: summarize what's available and what's degraded
 
 1. Capture **PLAN** (the user's argument) and **FLAGS**
-2. Detect project type using `references/project-detection.md` to populate
+2. **Load project context** — invoke `/prime` to load domain-specific context
+   (CLAUDE.md, goals, specs, memory). If /prime is unavailable, fall back to
+   manually scanning CLAUDE.md and goals/ directory.
+3. Detect project type using `references/project-detection.md` to populate
    **PROJECT_CONFIG** (language, test_runner, test_setup)
 3. Check for outstanding questions from previous work:
    - Search CLAUDE.md for a "Known Issues" or "Open Questions" section

package/skills/distil/SKILL.md

@@ -2,7 +2,7 @@
 name: distil
 description: Generate multiple unique web design variations for any website or web application. Accepts site specifications from a file (--spec path) or pasted text block. Creates a Vite + React + TypeScript + Tailwind project with Bun and produces N different creative designs accessible at /1, /2, /3, etc. Use when prototyping or exploring design directions for any web interface.
 argument-hint: <count> --port <port> [--spec <path>] [--favorites <1,2,3>]
-allowed-tools: Bash, Read, Write, Edit, Glob, Grep, WebFetch, AskUserQuestion
+allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, WebFetch, AskUserQuestion
 ---
 
 # Distil - Design Variation Generator