cc-dev-template 0.1.50 → 0.1.52

package/src/skills/spec-to-tasks/references/step-3-generate.md

@@ -0,0 +1,31 @@
+# Step 3: Generate Task Manifest
+
+Create the task manifest based on the spec and codebase exploration.
+
+## Task Principles
+
+**Atomic**: Each task is a single, focused change — one model, one endpoint, one component, or one test file. A task should take an AI agent one focused session to complete.
+
+**Ordered**: Sequence tasks so each can be completed without blocking. Tasks with no dependencies can share the same `depends_on` value to signal parallel execution.
+
+**Concrete file paths**: Use the file paths discovered in Step 2. Every task specifies which files it touches.
+
+**Declarative**: Tasks describe WHAT to implement, not HOW. Implementation details live in the spec.
+
+## Generate the Manifest
+
+Write to `docs/specs/<name>/tasks.yaml` using the template in `templates/tasks.yaml`.
+
+Derive tasks from the spec:
+- Break each requirement or feature section into atomic units
+- Sequence by dependency (data layer, then business logic, then API, then integration)
+- Reference specific spec sections in task descriptions where helpful
+
+## Review with User
+
+Present:
+1. Number of tasks and estimated scope
+2. Task titles in dependency order
+3. Offer to show full YAML or proceed to implementation
+
+Save the manifest to `docs/specs/<name>/tasks.yaml`.

package/src/skills/spec-to-tasks/templates/tasks.yaml

@@ -0,0 +1,25 @@
+spec: <name>
+spec_path: docs/specs/<name>/spec.md
+generated: <ISO timestamp>
+
+tasks:
+  - id: T001
+    title: <Short descriptive title>
+    description: |
+      <What to implement>
+      <Reference to spec section if applicable>
+    files:
+      - <path/to/file.ts>
+    depends_on: []
+    acceptance: |
+      <How to verify this task is complete>
+
+  - id: T002
+    title: <Next task>
+    description: |
+      <What to implement>
+    files:
+      - <path/to/file.ts>
+    depends_on: [T001]
+    acceptance: |
+      <Verification criteria>

package/src/mcp-servers/qa-server/README.md

@@ -1,122 +0,0 @@
-# QA Server
-
-MCP server that spawns a Claude sub-agent for frontend visual inspection.
-
-## Problem
-
-Playwright MCP adds ~20k tokens to context just from tool definitions, even when browser inspection isn't needed. This wastes context in long sessions.
-
-## Solution
-
-This server exposes a single `inspect_frontend` tool (~500 tokens) that spawns a sub-agent with full browser capabilities on-demand.
-
-```
-Main Conversation (~500 tokens)
-    │
-    └── mcp__qa__inspect_frontend
-            │
-            └── Sub-agent with @playwright/mcp (full browser control)
-                    │
-                    └── Returns QA report
-```
-
-**Note:** No system Chrome installation is required. Playwright automatically downloads and manages its own Chromium browser.
-
-## Installation
-
-```bash
-cd src/mcp-servers/qa-server
-npm install
-npm run build
-```
-
-Then add to Claude Code:
-
-```bash
-claude mcp add qa node /path/to/qa-server/dist/index.js
-```
-
-Or in `~/.claude.json`:
-
-```json
-{
-  "mcpServers": {
-    "qa": {
-      "type": "stdio",
-      "command": "node",
-      "args": ["/path/to/qa-server/dist/index.js"]
-    }
-  }
-}
-```
-
-## After Setup
-
-Remove Playwright MCP from your main config to save tokens (if previously added):
-
-```bash
-claude mcp remove playwright
-```
-
-## Usage
-
-From Claude Code conversation:
-
-```
-Inspect http://localhost:3000 and verify the login form works
-```
-
-Claude will call `mcp__qa__inspect_frontend` with:
-- url: "http://localhost:3000"
-- task: "verify the login form works"
-
-The sub-agent will:
-1. Navigate to the URL
-2. Take screenshots
-3. Check console errors
-4. Perform the task (click, fill forms, etc.)
-5. Return a structured QA report
-
-## Tool Definition
-
-```typescript
-{
-  name: "inspect_frontend",
-  description: "Spawn a QA sub-agent to visually inspect a frontend...",
-  inputSchema: {
-    type: "object",
-    properties: {
-      url: { type: "string", description: "URL to inspect" },
-      task: { type: "string", description: "What to inspect or test" }
-    },
-    required: ["url", "task"]
-  }
-}
-```
-
-## Sub-agent Capabilities
-
-The spawned sub-agent uses Opus (best visual understanding) and has access to Playwright MCP tools:
-
-- **Navigation**: browser_navigate, browser_tab_new, browser_tab_list, browser_tab_select, browser_wait_for
-- **Inspection**: browser_screenshot, browser_snapshot, browser_console_messages
-- **Interaction**: browser_click, browser_type, browser_hover, browser_press_key, browser_handle_dialog
-
-## Token Savings
-
-| Before | After |
-|--------|-------|
-| ~20k tokens (26 browser tools always loaded) | ~500 tokens (1 tool) |
-
-## Development
-
-```bash
-# Run in development mode
-npm run dev
-
-# Build for production
-npm run build
-
-# Run production build
-npm start
-```