/arn-code-help

name: arn-code-help
description: >-
  This skill should be used when the user says "arness code help", "where am I",
  "what's next", "show pipeline", "pipeline status", "what step am I on",
  "arness code status", "arn-code-help", "show workflow",
  or wants to see their current position in the Arness workflow pipeline
  and get guidance on the next step.
version: 1.2.0

Arness Help

Detect the user's current position in the Arness workflow pipeline, render an ASCII diagram with the active stage marked, and suggest the next command to run. Supports cross-plugin awareness — detects activity in Arness Spark 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 and Grep. When Glob or Grep is not available in the session, use read-only shell commands instead (`ls`, `find`, `test -e`, `grep -r`, `git status`, `git log`). This skill MUST NOT use Write or Edit, MUST NOT run a shell command that changes a file, and MUST NOT invoke any agents.

Workflow

Step 0: Multi-Plugin Awareness

1. From the `## Arness` section (loaded in Step 1), detect other plugin field groups:

• **spark_fields_present**: true if `Vision directory` OR `Use cases directory` OR `Prototypes directory` present
• **infra_fields_present**: true if `Infra plans directory` OR `Infra specs directory` present

2. For each detected plugin, do a quick existence check (max 2 files):

• **Spark**: Check if `<Vision directory>/product-concept.md` exists
• **Infra**: Check if `<Infra plans directory>` has any subdirectories, OR if `Dockerfile` or `docker-compose.yml` exists in the project root

3. Record `{ plugin_name, has_activity: bool }` for each detected plugin. 4. Proceed to Step 1. Cross-plugin hints are appended AFTER own status is rendered in Step 3.

---

Step 1: Load Configuration

1. Read the project's `CLAUDE.md` file. 2. Extract the `## Arness` section. 3. From the `## Arness` section, extract **core fields**:

• **Plans directory** (e.g., `.arness/plans/`)
• **Specs directory** (e.g., `.arness/specs/`)
• **Docs directory** (e.g., `.arness/docs/`)

**If `## Arness` is missing:** Skip to Step 3 and render the core pipeline diagram with all stages unmarked. Suggest the user run `/arn-planning` to get started for an existing project, or `/arn-brainstorming` for a brand-new project (requires arn-spark). Do not attempt detection.

---

Step 2: Detect Pipeline Position

Read the pipeline reference file at `${CLAUDE_PLUGIN_ROOT}/skills/arn-code-help/references/pipeline-map.md` to load detection rules, context-aware rendering rules, and next-step tables.

Core Detection

Per-Project Detection

For each subdirectory in the plans directory, check artifacts to determine the most advanced stage. Check from most advanced to least advanced -- first match wins:

1. **Documented** (`docs`): A file matching the project name exists in the configured docs directory (`<docs-dir>/<project>.md` or `<docs-dir>/<project>/` directory) 2. **Execution complete** (`execute-done`): The subdirectory has `PROGRESS_TRACKER.json` with `overallStatus` = `"completed"`. Note: `arn-code-review-implementation` does not write a durable artifact, so both "execution complete" and "review complete" map to this detection. The next-step suggestion covers both cases. 3. **Executing** (`execute`): The subdirectory has any `reports/IMPLEMENTATION_REPORT_*.json` or `reports/TESTING_REPORT_*.json` 4. **Tasks created** (`taskify`): The subdirectory has `TASKS.md` with parseable task entries 5. **Plan saved** (`save`): The subdirectory has `INTRODUCTION.md` 6. Otherwise: skip this subdirectory (incomplete project setup)

Global Core Detection

If no per-project stages were detected:

• Check the plans directory for subdirectories matching `SWIFT_*` containing `SWIFT_REPORT.json` -- if found, stage is **Swift complete** (`swift-complete`)
• Check the plans directory for subdirectories matching `SWIFT_*` containing `SWIFT_*.md` but no `SWIFT_REPORT.json` -- if found, stage is **Swift in progress** (`swift-in-progress`)
• Check the plans directory for subdirectories matching `STANDARD_*` containing `STANDARD_REPORT.json` -- if found, stage is **Standard complete** (`standard-complete`)
• Check the plans directory for subdirectories matching `STANDARD_*` containing `STANDARD_*.md` but no `STANDARD_REPORT.json` -- if found, stage is **Standard in progress** (`standard-in-progress`)
• Check the plans directory for files matching `PLAN_PREVIEW_*.md` -- if found, stage is **Plan generated** (`plan`)
• Check the specs directory for files matching `FEATURE_*.md` or `BUGFIX_*.md` -- if found, stage is **Spec written** (`spec`)
• Check the specs directory for files matching `DRAFT_FEATURE_*.md` -- if found and no finalized `FEATURE_*.md` or `BUGFIX_*.md` exists, stage is **Spec in progress** (`spec-draft`)
• If `## Arness` exists with core fields but specs and plans directories are empty, stage is **Initialized** (`init`). Suggest `/arn-code-feature-spec`, `/arn-code-bug-spec`, for quick changes (1-8 files) `/arn-code-swift`, or for medium complexity `/arn-code-standard`

Fallback

• If `## Arness` exists but no artifacts are found, stage is `init`.

---

Step 3: Render Pipeline Diagram

Read the pipeline templates and rendering rules from `${CLAUDE_PLUGIN_ROOT}/skills/arn-code-help/references/pipeline-map.md`.

Show the core pipeline diagram with the position marker. Follow the existing rendering:

• Single-project or multi-project diagrams
• Next-step suggestion from the core next-step table

After rendering the core pipeline status and next-step suggestion, append cross-plugin hints from Step 0:

• If Spark has activity: append "Spark exploration: active — run `/arn-spark-help` for details."
• If Infra has activity: append "Infrastructure pipeline: active — run `/arn-infra-help` for details."
• If