arn-spark-help

Arness Spark Help

Detect the user's current position in the Arness Spark exploration pipeline, render a diagram with the active stage marked, and suggest the next command to run. Supports cross-plugin awareness — detects activity in Arness Code and Arness Infra and provides hints at the bottom of the output. This skill is strictly read-only — it never modifies files or project state.

Allowed tools: Read, Glob, Grep only. This skill MUST NOT use Write, Edit, Bash, or Task tools. This skill MUST NOT invoke any agents.

Workflow

Step 0: Multi-Plugin Awareness

1. Read the project's CLAUDE.md file.
2. Extract the ## Arness section.
3. Detect other plugin field groups:
   • code_fields_present: true if Plans directory OR Specs directory present in ## Arness
   • infra_fields_present: true if Infra plans directory OR Infra specs directory present in ## Arness
4. For each detected plugin, do a quick existence check (max 2 files):
   • Code: Check if <Specs directory> contains any FEATURE_*.md or BUGFIX_*.md, OR <Plans directory> has any subdirectories
   • Infra: Check if <Infra plans directory> has any subdirectories, OR if Dockerfile or docker-compose.yml exists in the project root
5. Record { plugin_name, has_activity: bool } for each detected plugin.
6. Proceed to Step 1. The cross-plugin hints are appended AFTER own status is rendered in Step 3.

Step 1: Load Configuration

1. From the ## Arness section, extract Spark fields:
   • Vision directory (e.g., .arness/vision/)
   • Use cases directory (e.g., .arness/use-cases/)
   • Prototypes directory (e.g., .arness/prototypes/)
   • Spikes directory (e.g., .arness/spikes/)
   • Visual grounding directory (e.g., .arness/visual-grounding/)
   • Reports directory (e.g., .arness/reports/)

If ## Arness is missing or no Spark fields present: Show the Spark pipeline diagram with all stages unmarked. Suggest /arn-brainstorming to start a new greenfield project. Do not attempt detection.