Stats
Actions
Tags
From learning-agents
Scaffolds LearningAgent directories with core-knowledge.md and Claude Code agent files. Runs bash script, handles templates, and guides interactive domain configuration. Invoke with /create-agent <name> [template].
How this skill is triggered — by the user, by Claude, or both
Slash command
/learning-agents:create-agentThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Create a new LearningAgent and guide the user through initial configuration.
Create a new LearningAgent and guide the user through initial configuration.
$ARGUMENTS contains the agent name and an optional template path, separated by whitespace.
rails-activejob). If not provided, ask the user what to name the agent..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.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:
# 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).
Ask the user about the agent's domain:
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:
.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:
You are an expert on Rails ActiveJob. You understand the full job lifecycle,
supported adapters (Sidekiq, Resque, DelayedJob), retry configuration with
exponential backoff, and callback patterns. You should always check the adapter
documentation before recommending queue-specific features.
.claude/agents/<agent-name>.md frontmatter: Replace the TODO placeholders:
name: The agent's display name (human-readable, e.g., "Rails ActiveJob Expert")description: A concise description for deciding when to invoke this agent (2-3 sentences max). Example: "Expert on Rails ActiveJob patterns including job creation, queue configuration, and retry logic. Invoke when delegating background job tasks or debugging queue issues."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):
---
name: "Topic Name"
keywords:
- keyword1
- keyword2
last_updated: "YYYY-MM-DD"
---
Detailed documentation about this topic area...
Learning file (.deepwork/learning-agents/<agent-name>/learnings/<learning-name>.md):
---
name: "Learning Name"
last_updated: "YYYY-MM-DD"
summarized_result: |
One sentence summary of the key takeaway.
---
## Context
...
## Key Takeaway
...
Output in this format:
## Agent Created: <agent-name>
**Files created/modified:**
- `.deepwork/learning-agents/<agent-name>/core-knowledge.md` — core expertise
- `.deepwork/learning-agents/<agent-name>/topics/` — topic documentation
- `.deepwork/learning-agents/<agent-name>/learnings/` — experience-based insights
- `.claude/agents/<agent-name>.md` — Claude Code agent file
Then output the following restart warning exactly as written, including the emphasis markers and blank lines. This is critical — the user WILL NOT be able to use the new agent without doing this:
---
## !! IMPORTANT — YOU MUST RESTART CLAUDE CODE !!
Claude Code does NOT hot-reload agent files. The agent you just created
is **invisible** to Claude until you restart.
**Do this now:**
1. Exit this Claude Code session (type `/exit` or Ctrl+C)
2. Restart with: `claude -c` (this continues your conversation)
3. The new agent will then be available via the Task tool
If you skip this step, Claude will not find the agent when you try to use it.
---
After the restart warning, output:
**Usage (after restart):**
Use the Task tool with `name: "<agent-name>"` to invoke this agent.
**Learning cycle:**
The post-Task hook will automatically track sessions. Run `/learning-agents learn`
after sessions to identify and incorporate learnings.
.claude/agents/ filenames.claude/agents/ description field concise (2-3 sentences max)npx claudepluginhub unsupervisedcom/deepwork --plugin learning-agentsGuides creation of autonomous agents for Claude Code plugins, covering Markdown file structure, YAML frontmatter (name, description, model, color, tools), system prompts, triggering examples, and best practices.
Creates Claude Code agents with YAML frontmatter for name, description, tools, model selection, and color. Use when adding specialized agents to plugins.
Create custom agents for Claude Code including YAML frontmatter, system prompts, tool restrictions, and discovery optimization. Use when creating, building, or designing agents, or when asked about agent creation, subagent configuration, Task tool delegation, or agent best practices.