Add template agent support to create-agent skill

Allow seeding a new LearningAgent from an existing one by passing an
optional template path. Copies core-knowledge.md, topics, and learnings
from the template as a starting point, which the user can then customize.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: nhorton

learning_agents/scripts/create_agent.sh

@@ -1,7 +1,14 @@
 #!/bin/bash
 # create_agent.sh - Create a new LearningAgent scaffold
 #
-# Usage: create_agent.sh <agent-name>
+# Usage: create_agent.sh <agent-name> [template-agent-path]
+#
+# Arguments:
+#   agent-name           Name for the new agent (use dashes for multi-word)
+#   template-agent-path  Optional path to an existing learning agent directory
+#                        (e.g., .deepwork/learning-agents/my-existing-agent)
+#                        If provided, copies core-knowledge.md, topics/*, and
+#                        learnings/* from the template into the new agent.
 #
 # Creates:
 #   .deepwork/learning-agents/<agent-name>/core-knowledge.md
@@ -13,12 +20,25 @@
 set -euo pipefail
 
 AGENT_NAME="${1:-}"
+TEMPLATE_PATH="${2:-}"
 
 if [ -z "$AGENT_NAME" ]; then
-    echo "Usage: create_agent.sh <agent-name>" >&2
+    echo "Usage: create_agent.sh <agent-name> [template-agent-path]" >&2
     exit 1
 fi
 
+# Validate template path if provided
+if [ -n "$TEMPLATE_PATH" ]; then
+    if [ ! -d "$TEMPLATE_PATH" ]; then
+        echo "Template agent directory not found: ${TEMPLATE_PATH}" >&2
+        exit 1
+    fi
+    if [ ! -f "$TEMPLATE_PATH/core-knowledge.md" ]; then
+        echo "Template directory missing core-knowledge.md: ${TEMPLATE_PATH}" >&2
+        exit 1
+    fi
+fi
+
 AGENT_DIR=".deepwork/learning-agents/${AGENT_NAME}"
 CLAUDE_AGENT_FILE=".claude/agents/${AGENT_NAME}.md"
 
@@ -55,8 +75,39 @@ These files let you customize how the learning cycle works for this agent. Each
 - **learning_from_issues.md** — Included during the `incorporate-learnings` step. Use this to guide how learnings are integrated — e.g., preferences for topics vs learnings, naming conventions, or areas of core-knowledge that should stay concise.
 ALG_README
 
-    # Create core-knowledge.md with TODO placeholder
-    cat > "${AGENT_DIR}/core-knowledge.md" << 'CORE_KNOWLEDGE'
+    # ========================================================================
+    # SEED FROM TEMPLATE OR CREATE EMPTY
+    # ========================================================================
+
+    if [ -n "$TEMPLATE_PATH" ]; then
+        # Copy core-knowledge.md from template
+        cp "$TEMPLATE_PATH/core-knowledge.md" "${AGENT_DIR}/core-knowledge.md"
+        echo "Copied core-knowledge.md from template"
+
+        # Copy topics (if any exist beyond .gitkeep)
+        TOPIC_COUNT=0
+        for f in "$TEMPLATE_PATH/topics/"*.md; do
+            [ -f "$f" ] || continue
+            cp "$f" "${AGENT_DIR}/topics/"
+            TOPIC_COUNT=$((TOPIC_COUNT + 1))
+        done
+        if [ "$TOPIC_COUNT" -gt 0 ]; then
+            echo "Copied ${TOPIC_COUNT} topic(s) from template"
+        fi
+
+        # Copy learnings (if any exist beyond .gitkeep)
+        LEARNING_COUNT=0
+        for f in "$TEMPLATE_PATH/learnings/"*.md; do
+            [ -f "$f" ] || continue
+            cp "$f" "${AGENT_DIR}/learnings/"
+            LEARNING_COUNT=$((LEARNING_COUNT + 1))
+        done
+        if [ "$LEARNING_COUNT" -gt 0 ]; then
+            echo "Copied ${LEARNING_COUNT} learning(s) from template"
+        fi
+    else
+        # Create core-knowledge.md with TODO placeholder
+        cat > "${AGENT_DIR}/core-knowledge.md" << 'CORE_KNOWLEDGE'
 TODO: Complete current knowledge of this domain.
 Written in second person ("You should...") because this text
 becomes the agent's system instructions. Structure it as:
@@ -66,6 +117,7 @@ becomes the agent's system instructions. Structure it as:
 4. Pitfalls to avoid
 5. Decision frameworks
 CORE_KNOWLEDGE
+    fi
 
     echo "Created agent directory: ${AGENT_DIR}"
 fi

learning_agents/skills/create-agent/SKILL.md

@@ -9,34 +9,49 @@ Create a new LearningAgent and guide the user through initial configuration.
 
 ## Arguments
 
-`$ARGUMENTS` is the agent name. Use dashes for multi-word names (e.g., `rails-activejob`). If not provided, ask the user what to name the agent.
+`$ARGUMENTS` contains the agent name and an optional template path, separated by whitespace.
+
+- **Agent name** (required): Use dashes for multi-word names (e.g., `rails-activejob`). If not provided, ask the user what to name the agent.
+- **Template agent path** (optional): Path to an existing learning agent directory (e.g., `.deepwork/learning-agents/my-existing-agent`). If provided, the new agent is seeded with the template's `core-knowledge.md`, `topics/`, and `learnings/` as a starting point. The user can then customize the copied content during configuration.
 
 ## Procedure
 
 ### Step 1: Validate and Run Scaffold Script
 
+Parse `$ARGUMENTS` to extract the agent name (first word) and optional template path (second word, if present).
+
 If the name contains spaces or uppercase letters, normalize to lowercase dashes (e.g., "Rails ActiveJob" → `rails-activejob`).
 
 Check `.claude/agents/` for an existing file matching `<agent-name>.md`. If found, inform the user of the conflict and ask how to proceed.
 
+If a template path was provided, verify it exists and contains `core-knowledge.md`. If not, inform the user and ask how to proceed.
+
 Run the scaffold script:
 
 ```bash
-${CLAUDE_PLUGIN_ROOT}/scripts/create_agent.sh $ARGUMENTS
+# Without template:
+${CLAUDE_PLUGIN_ROOT}/scripts/create_agent.sh <agent-name>
+
+# With template:
+${CLAUDE_PLUGIN_ROOT}/scripts/create_agent.sh <agent-name> <template-agent-path>
 ```
 
 If the script reports that directories already exist, inform the user and ask whether to proceed with updating the configuration or stop.
 
+If a template was used, inform the user what was copied (the script output will list the counts).
+
 ### Step 2: Configure the Agent
 
 Ask the user about the agent's domain:
 
 - What domain or area of expertise does this agent cover?
 - What kinds of tasks will it be delegated to handle?
 
+If a template was used, read the copied `core-knowledge.md` and present it to the user. Ask if they want to keep it as-is, modify it for the new agent's focus, or replace it entirely.
+
 Based on their answers, update:
 
-1. **`.deepwork/learning-agents/<agent-name>/core-knowledge.md`**: Replace the TODO content with the agent's core expertise in second person ("You should...", "You are an expert on...").
+1. **`.deepwork/learning-agents/<agent-name>/core-knowledge.md`**: If created from scratch, replace the TODO content with the agent's core expertise in second person ("You should...", "You are an expert on..."). If seeded from a template, adapt the content to reflect the new agent's specific focus area.
 
    Example:
    ```
@@ -52,7 +67,9 @@ Based on their answers, update:
 
 ### Step 3: Seed Initial Knowledge (Optional)
 
-Ask the user if they want to seed any initial topics or learnings. If yes, create files using these formats:
+If a template was used and topics/learnings were copied, list what was copied and ask if the user wants to review, remove, or add to them.
+
+Otherwise, ask the user if they want to seed any initial topics or learnings. If yes, create files using these formats:
 
 **Topic file** (`.deepwork/learning-agents/<agent-name>/topics/<topic-name>.md`):
 ```yaml