/arn-spark-help

name: arn-spark-help
description: >-
  This skill should be used when the user says "spark help", "arn spark help",
  "greenfield status", "greenfield help", "where am I in spark", "what's next for spark",
  "spark pipeline", "spark status", "arn-spark-help", "show spark pipeline",
  "what step am I on for spark", "spark workflow", "exploration status",
  "show exploration pipeline", "how does spark work", "explain spark pipeline",
  or wants to see their current position in the
  Arness Spark exploration pipeline and get guidance on the next step.
version: 1.0.0

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.

---

Step 2: Detect Pipeline Position

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

Check from most advanced to least advanced — first match wins:

1. **Feature backlog ready** (`gf-feature-extract`): `<vision-dir>/features/feature-backlog.md` exists 2. **Prototype locked** (`gf-prototype-lock`): `<prototypes-dir>/locked/LOCKED.md` exists 3. **Clickable prototype done** (`gf-clickable-proto`): `<prototypes-dir>/clickable/final-report.md` exists 4. **Static prototype done** (`gf-static-proto`): `<prototypes-dir>/static/final-report.md` exists 5. **Style defined** (`gf-style-explore`): `<vision-dir>/style-brief.md` exists 6. **Visual direction chosen** (`gf-visual-sketch`): `<vision-dir>/visual-direction.md` exists 7. **Spike complete** (`gf-spike`): `<vision-dir>/spike-results.md` exists 8. **Scaffold built** (`gf-scaffold`): `<vision-dir>/scaffold-summary.md` exists 9. **Use cases written** (`gf-use-cases`): At least one `UC-*.md` file exists in `<use-cases-dir>/` 10. **Architecture defined** (`gf-arch-vision`): `<vision-dir>/architecture-vision.md` exists 11. **Naming complete** (`gf-naming`): `<vision-dir>/naming-brief.md` exists OR `<reports-dir>/naming-report.md` exists 12. **Concept reviewed** (`gf-concept-review`): `<reports-dir>/stress-tests/concept-review-report.md` exists 13. **Stress tests run** (`gf-stress-test`): Any of `interview-report.md`, `competitive-report.md`, `premortem-report.md`, `prfaq-report.md` exists in `<reports-dir>/stress-tests/` 14. **Product discovered** (`gf-discover`): `<vision-dir>/product-concept.md` exists 15. **Spark initialized** (`gf-init`): Spark fields exist in `## Arness` but none of the above artifacts found

**Spark complete:** If the detected stage is `gf-feature-extract`, Spark exploration is considered complete.

---

Step 3: Render Pipeline Diagram

Read the pipeline templates from `${CLAUDE_PLUGIN_ROOT}/skills/arn-spark-help/references/pipeline-map.md`.

1. Place the `YOU ARE HERE` marker below the detected stage. 2. Display the next-step suggestion from the next-step table. 3. Spark is a single-track pipeline (no per-project subdirectories).

**Own-plugin suggestions always come first.** After the pipeline diagram and next-step suggestion, append cross-plugin hints from Step 0:

• If own plugin has activity: show own status first. If other plugins have activity, append 1-2 lines at the bottom:

  Other pipelines: Development (active) — `/arn-code-help` | Infrastructure (not started)

• If own plugin is idle (`gf-init`) but other plugins have activity: show own-plugin "ready to start" suggestions FIRST:

  Ready to start: run `/arn-spark-discover` to shape your product idea, or `/arn-brainstorming` for the guided wizard.

Then mention others:

  You also have active work in Code — run `/arn-code-help` for details.

• When Spark pipeline is complete (`gf-feature-extract`): suggest transition:

  Spark exploration is complete. Next steps:
  - Start developing features: `/arn-planning`
  - Deploy infrastructure: `/arn-infra-wizard`

Keep output concise — the user wants a quick status check, not a wall of text.

---

Step 4: Answer Follow-up Quest