Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
188 changes: 188 additions & 0 deletions .agent/scripts/commands/neuronwriter.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,188 @@
---
description: NeuronWriter content optimization - analyze keywords, score content, get NLP recommendations
agent: Build+
mode: subagent
---

Optimize content for SEO using NeuronWriter's NLP analysis API.

Arguments: $ARGUMENTS

## Workflow

### Step 1: Parse Arguments

Parse `$ARGUMENTS` to determine the action:

```text
/neuronwriter analyze <keyword> [options] → Create query + get NLP recommendations
/neuronwriter score <query-id> <url-or-html> → Score content against a query
/neuronwriter import <query-id> <url-or-html> → Import content into NeuronWriter editor
/neuronwriter get <query-id> → Get recommendations for existing query
/neuronwriter content <query-id> → Get saved content from editor
/neuronwriter projects → List all projects
/neuronwriter queries <project-id> [options] → List queries in a project
/neuronwriter status → Check API key configuration
```

If only a keyword is provided (no subcommand), default to `analyze`.

### Step 2: Check API Key

```bash
source ~/.config/aidevops/mcp-env.sh
if [[ -z "$NEURONWRITER_API_KEY" ]]; then
echo "NEURONWRITER_API_KEY not configured." >&2
echo "Set it with: bash ~/.aidevops/agents/scripts/setup-local-api-keys.sh set NEURONWRITER_API_KEY \"your_key\"" >&2
echo "Get your key from: NeuronWriter profile > Neuron API access tab" >&2
echo "Requires Gold plan or higher." >&2
Comment on lines +35 to +38
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For better readability and to avoid repeating >&2 on each line, consider using a single echo command with a multi-line string to output the error message.

Suggested change
echo "NEURONWRITER_API_KEY not configured." >&2
echo "Set it with: bash ~/.aidevops/agents/scripts/setup-local-api-keys.sh set NEURONWRITER_API_KEY \"your_key\"" >&2
echo "Get your key from: NeuronWriter profile > Neuron API access tab" >&2
echo "Requires Gold plan or higher." >&2
echo "NEURONWRITER_API_KEY not configured.
Set it with: bash ~/.aidevops/agents/scripts/setup-local-api-keys.sh set NEURONWRITER_API_KEY \"your_key\"
Get your key from: NeuronWriter profile > Neuron API access tab
Requires Gold plan or higher." >&2

exit 1
fi
```

### Step 3: Read the NeuronWriter Subagent

Read `seo/neuronwriter.md` for full API reference, then execute the appropriate endpoint.

### Step 4: Execute Action

**For `analyze` (default):**

1. List projects to find the right one (or use `--project <id>` if provided)
2. Call `/new-query` with the keyword
3. Poll `/get-query` every 15 seconds until `status == "ready"` (max 5 minutes)
4. Present NLP recommendations in a structured format

**For `score`:**

1. Call `/evaluate-content` with the query ID and URL or HTML
2. Report the content score

**For `import`:**

1. Call `/import-content` with the query ID and URL or HTML
2. Report the content score and editor URL
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The NeuronWriter API reference (seo/neuronwriter.md) shows /import-content returning a status + content_score, but not an editor URL; consider clarifying how to derive/link an editor URL (or avoid promising one here).

Fix This in Augment

🤖 Was this useful? React with 👍 or 👎


**For `get`:**

1. Call `/get-query` with the query ID
2. Present recommendations (terms, ideas, competitors)

**For `content`:**

1. Call `/get-content` with the query ID
2. Return the saved HTML content, title, and description

**For `projects`:**

1. Call `/list-projects`
2. Display project names, IDs, languages, and engines

**For `queries`:**

1. Call `/list-queries` with the project ID
2. Optionally filter by `--status`, `--keyword`, `--tag`

### Step 5: Report Results

**For `analyze`, present recommendations as:**

```text
Keyword: "trail running shoes"
Query ID: 32dee2a89374a722
Query URL: https://app.neuronwriter.com/analysis/view/32dee2a89374a722

NLP Terms (Content):
- trail running shoes (use 8-12 times)
- running shoe (use 3-5 times)
- trail runners (use 2-4 times)
...

Suggested Headings (H2):
- Best Trail Running Shoes for 2025
- How to Choose Trail Running Shoes
...

Content Ideas:
- What makes trail running shoes different from road shoes?
- How often should you replace trail running shoes?
...

Competitors (Top 5):
1. runnersworld.com - Score: 87
2. rei.com - Score: 82
...

Word Count Target: 2,500-3,000
```

**For `score` / `import`:**

```text
Content Score: 72/100
Query: 32dee2a89374a722
```

## Options
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The Options section doesn’t document --status, --keyword, or --tag, even though they’re referenced for /neuronwriter queries and used in the examples; consider adding them to the table to keep the docs consistent.

Fix This in Augment

🤖 Was this useful? React with 👍 or 👎


| Option | Description |
|--------|-------------|
| `--project <id>` | Project ID (skips project selection) |
| `--engine <engine>` | Search engine (default: `google.com`) |
| `--language <lang>` | Content language (default: `English`) |

## Examples

**Analyze a keyword:**

```text
/neuronwriter trail running shoes
```

**Analyze with specific project and engine:**

```text
/neuronwriter analyze "best running gear" --project ed0b47151fb35b02 --engine google.co.uk
```

**Score a URL against an existing query:**

```text
/neuronwriter score 32dee2a89374a722 https://example.com/running-shoes
```

**Import content into the editor:**

```text
/neuronwriter import 32dee2a89374a722 https://example.com/running-shoes
```

**Get recommendations for an existing query:**

```text
/neuronwriter get 32dee2a89374a722
```

**List all projects:**

```text
/neuronwriter projects
```

**List ready queries in a project:**

```text
/neuronwriter queries ed0b47151fb35b02 --status ready
```

**Check API key status:**

```text
/neuronwriter status
```

## Related

- `seo/neuronwriter.md` - Full API reference and authentication details
- NeuronWriter requires Gold plan or higher for API access
- API requests consume the same monthly limits as the NeuronWriter UI
3 changes: 2 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,7 @@ The result: AI agents that work *with* your development process, not around it.
- Primary agents (Build+, SEO, Marketing, etc.) with @plan-plus subagent for planning-only mode
- 539+ subagent markdown files organized by domain
- 148 helper scripts in `.agent/scripts/`
- 15 slash commands for common workflows
- 16 slash commands for common workflows

<!-- AI-CONTEXT-END -->

Expand Down Expand Up @@ -1420,6 +1420,7 @@ Configure time tracking per-repo via `.aidevops.json`.
| `/autocomplete-research` | Google autocomplete long-tail discovery |
| `/keyword-research-extended` | Full SERP analysis with weakness detection |
| `/webmaster-keywords` | Keywords from GSC + Bing for your verified sites |
| `/neuronwriter` | Content optimization with NLP term recommendations and scoring |

**SEO Debugging** (subagents in `seo/`):

Expand Down
Loading