fix: init skill avoids brainstorming interception, detects existing specs

skills/init/SKILL.md

@@ -1,19 +1,21 @@
 ---
 name: init
-description: Initialize the agent loop harness in the current project. Scaffolds .loop/ directory, detects tech stack, picks mode, generates config, and flows into planning.
+description: "Setup task: scaffold .loop/ directory and generate config for the agent loop harness. Not a creative task — do not brainstorm or generate ideas. Reads existing specs if present."
 ---
 
 # /init — Initialize Agent Loop for a Project
 
-Set up the agent loop harness in the current project. This is the entry point for first-time use.
+Set up the agent loop harness in the current project. This is infrastructure setup, not creative work.
+
+**IMPORTANT:** Do NOT invoke brainstorming, planning, or idea-generation skills. This skill handles its own flow. If the user wants to brainstorm first, they should do that separately before running this skill.
 
 ## What This Skill Does
 
-1. Scaffolds the `.loop/` directory with prompts, templates, and lib scripts from the plugin
+1. Checks for existing specs/plans in the project (uses them if found)
-2. Analyzes the project to understand its tech stack, structure, and conventions
+2. Scaffolds the `.loop/` directory
-3. Asks the user what they want to accomplish (explore, implement, or fix)
+3. Detects tech stack
-4. Creates project-specific configuration (`config.json`, `init.sh`)
+4. Picks mode and generates config
-5. Flows into planning to generate the PRD and sprint contracts
+5. Flows into `/agent-loop:plan` to decompose the spec into stories
 
 ## Instructions
 
@@ -56,17 +58,23 @@ archive/
 
 **If `.loop/` already exists**, ask the user if they want to re-initialize (which resets config but preserves prd.json/progress.md if they exist).
 
-### Step 1: Project Discovery
+### Step 1: Check for Existing Specs
 
-Read the project to understand what we're working with:
+Search for existing design documents or specs in the project:
-- Check for `CLAUDE.md`, `AGENTS.md`, `README.md` at the project root
+- `docs/superpowers/specs/*.md`
-- Check for `package.json`, `Cargo.toml`, `pyproject.toml`, `go.mod`, `Package.swift`, `composer.json` to identify the tech stack
+- `docs/specs/*.md`
-- Run `ls` on the project root to see the top-level structure
+- `docs/*.md` (that look like feature specs)
+- `SPEC.md`, `PRD.md`, `DESIGN.md` at root
+- Any markdown file that contains design/architecture/requirements content
 
-Present a brief summary:
+**If a spec is found:**
-> "I see this is a [language/framework] project with [key characteristics]. The main source is in [dir/]."
+> "I found an existing spec at `{path}`. I'll use this as the basis for generating stories."
 
-### Step 2: Mode Selection
+Read the spec and use it as input for planning. Do NOT ask the user to re-describe what they want — the spec already has it. Skip to Step 3 (mode is almost certainly **implement**).
+
+**If no spec is found**, proceed to Step 2.
+
+### Step 2: Mode Selection and Description
 
 Ask the user:
 
@@ -76,28 +84,25 @@ Ask the user:
 > b) **Implement** — Build a new feature from a PRD. Code changes, commits, and tests.
 > c) **Fix** — Work through a list of bugs or tech debt items. Targeted code changes.
 
-### Step 3: Clarifying Questions
+Based on the mode, ask 2-3 brief clarifying questions. Do NOT over-interview — keep it focused:
 
-Based on the mode, ask 3-5 questions:
+**For Implement:** "Describe the feature in 1-3 sentences."
+**For Explore:** "What areas should I focus on?"
+**For Fix:** "Do you have a list of issues, or should I find them?"
 
-**For Explore:**
+### Step 3: Project Discovery
-- "What areas are you most interested in? (e.g., auth, database, API, frontend, everything)"
-- "Are there known problem areas you want me to focus on?"
-- "How many exploration sessions should I budget? (default: 20)"
 
-**For Implement:**
+Read the project to understand what we're working with:
-- "Describe the feature you want to build (1-3 sentences is fine)"
+- Check for `CLAUDE.md`, `AGENTS.md`, `README.md` at the project root
-- "Are there any architectural constraints I should know about?"
+- Check for `package.json`, `Cargo.toml`, `pyproject.toml`, `go.mod`, `Package.swift`, `composer.json` to identify the tech stack
-- "Should I follow any specific patterns from the existing codebase?"
+- Run `ls` on the project root to see the top-level structure
 
-**For Fix:**
+Present a brief summary:
-- "Do you have a list of issues, or should I find them?"
+> "I see this is a [language/framework] project with [key characteristics]."
-- "Any areas that are off-limits for changes?"
-- "What's the priority: security, stability, or code quality?"
 
 ### Step 4: Generate Configuration
 
-Create `.loop/config.json` based on the project and user's answers:
+Create `.loop/config.json` based on the project:
 
 ```json
 {
@@ -114,28 +119,11 @@ Create `.loop/config.json` based on the project and user's answers:
 }
 ```
 
-Create `.loop/init.sh` with project-specific setup commands:
+Create `.loop/init.sh` with project-specific setup commands (dev server, test runner, linter, etc.). Make it executable.
-- Dev server startup (if applicable)
-- Test runner command
-- Type checker command
-- Linter command
-- Any environment setup needed
-
-Make `init.sh` executable.
 
 ### Step 5: Flow into Planning
 
 Tell the user:
-> "Project configured. Now let's plan the work."
+> "Project configured. Generating stories from {spec name / user description}..."
 
-Then invoke the `/agent-loop:plan` skill to generate the PRD and sprint contracts.
+Then invoke `/agent-loop:plan` to generate the PRD and sprint contracts. If a spec was found in Step 1, pass it as context so the plan skill uses it directly.
-
-### Step 6: Ready to Run
-
-Once planning is complete, tell the user:
-> "Everything is set up. To start the loop:"
-> ```
-> /agent-loop:run            # Interactive (recommended) — visible, can intervene
-> .loop/loop.sh              # Headless — fully autonomous
-> ```
-> You can monitor progress in `.loop/progress.md` and check story status in `.loop/prd.json`.