agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Create a new slash command with AI-guided behavior definition
$ npx -y skills add jmagly/aiwg --skill devkit-create-command --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/devkit-create-commandContext preview
The summary Claude sees to decide when to auto-load this skill.
Create a new slash command with AI-guided behavior definition
namespace: aiwg name: devkit-create-command platforms: [all] description: Create a new slash command with AI-guided behavior definition
<!-- AIWG-SKILL-CALLOUT --> > **Skill access pattern (post-kernel-pivot, 2026.5+)** > > Skill names referenced in this document are AIWG skills, **not slash commands**. Most are not kernel-listed and cannot be invoked as `/skill-name` by the platform. Reach them via: > > ```bash > aiwg discover "<capability>" > aiwg show skill <name> > ``` > > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).
Create a new slash command with AI assistance to define arguments, behavior, and output.
/devkit-create-command <name> --to <target> [options]
| Argument | Required | Description | |----------|----------|-------------| | name | Yes | Command name (kebab-case recommended) |
| Option | Description | |--------|-------------| | --to | Target addon or framework |
| Option | Description | |--------|-------------| | --template | Command template: utility (default), transformation, orchestration | | --interactive | Enable interactive mode with guided questions |
Simple operation, single action command.
Content/code transformation pipeline with input/output handling.
Multi-agent workflow coordination with phases and parallel execution.
When `--interactive` is specified, I will ask:
1. **Purpose**: What does this command do? 2. **Arguments**: What inputs does it need? 3. **Options**: What configuration options should it support? 4. **Steps**: What are the execution steps? 5. **Output**: What should the output look like?
# Simple utility command /devkit-create-command lint-fix --to aiwg-utils # Transformation pipeline /devkit-create-command convert-docs --to sdlc-complete --template transformation # Orchestration workflow /devkit-create-command deploy-all --to sdlc-complete --template orchestration --interactive
1. **Validate inputs**: Check name and target 2. **Verify target exists**: Ensure addon/framework is installed 3. **Select template**: Use specified or default to utility 4. **Gather behavior**: In interactive mode, ask about command behavior 5. **Generate command file**: Create with frontmatter and sections 6. **Update manifest**: Add command to manifest.json 7. **Report success**: Show location and usage instructions
<target>/commands/<name>.md
--- name: command-name description: Command description args: [arg1] [--option value --guidance "text"] --- # Command Title [Description] ## Usage [How to invoke] ## Arguments [Input parameters] ## Options [Configuration flags] ## Execution [Step-by-step behavior] ## Output [What to expect]
aiwg add-command <name> --to <target> --template <type>
Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.
Repo: jmagly/aiwg
Crash-resilient external agent loop with state persistence and CI/CD integration
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Enable agent loops to learn from similar past tasks and share patterns across loops
Query and manage the executable feedback debug memory
Execute tests on generated code and iterate until passing