agileflow 3.4.3 → 4.0.0-alpha.10

package/src/core/commands/seo/audit.md

@@ -1,444 +0,0 @@
----
-description: Full website SEO audit with 6 parallel analyzers, business type detection, weighted health score 0-100, and prioritized action plan
-argument-hint: "URL [DEPTH=quick|deep|ultradeep|extreme] [MAX_PAGES=50]"
-compact_context:
-  priority: high
-  preserve_rules:
-    - "ACTIVE COMMAND: /agileflow:seo:audit - Full website SEO audit"
-    - "CRITICAL: Deploy 6 analyzers IN PARALLEL in ONE message with multiple Task calls"
-    - "CRITICAL: Wait for all results before running consensus (use TaskOutput with block=true)"
-    - "CRITICAL: Weighted scoring - Technical 20%, Content 20%, Schema 15%, Performance 15%, Images 15%, Sitemap 15%"
-    - "MUST parse arguments: URL (required), DEPTH (quick/deep/ultradeep/extreme), MAX_PAGES (default 50)"
-    - "Fetch homepage FIRST to detect business type before deploying analyzers"
-    - "Pass all analyzer outputs to seo-consensus for final report"
-    - "DEPTH GATE: ultradeep/extreme MUST spawn tmux sessions via spawn-audit-sessions.js — NEVER deploy in-process"
-    - "Use check-sessions.js to monitor spawned tmux sessions — NEVER write custom polling scripts"
-  state_fields:
-    - target_url
-    - depth
-    - max_pages
-    - business_type
-    - analyzers_deployed
-    - health_score
----
-
-# /agileflow:seo:audit
-
-Deploy 6 specialized SEO analyzers in parallel to audit a website, then synthesize results through consensus into a weighted health score (0-100) with prioritized action plan.
-
----
-
-## Quick Reference
-
-```
-/agileflow:seo:audit https://example.com                     # Quick audit (all 6 analyzers)
-/agileflow:seo:audit https://example.com DEPTH=deep           # Deep audit (more thorough per-analyzer)
-/agileflow:seo:audit https://example.com DEPTH=ultradeep      # Each analyzer in its own tmux session
-/agileflow:seo:audit https://example.com DEPTH=extreme        # Multi-page partition audit
-/agileflow:seo:audit https://example.com MAX_PAGES=100        # Audit up to 100 pages
-```
-
----
-
-## How It Works
-
-```
-┌──────────────────────────────────────────────────────────────┐
-│                    /agileflow:seo:audit                       │
-│                                                               │
-│  1. Parse arguments (URL, depth, max_pages)                   │
-│  2. Fetch homepage → detect business type                     │
-│  3. Fetch robots.txt + sitemap.xml                            │
-│  4. Deploy 6 analyzers IN PARALLEL                            │
-│  5. Collect all results                                       │
-│  6. Run consensus → weighted health score                     │
-│  7. Generate SEO Audit Report + action plan                   │
-└──────────────────────────────────────────────────────────────┘
-
-   ┌──────────┐ ┌─────────┐ ┌────────┐
-   │Technical │ │ Content │ │ Schema │
-   └────┬─────┘ └────┬────┘ └───┬────┘
-        │            │          │
-   ┌────┴──────┐ ┌───┴────┐ ┌──┴──────┐
-   │Performance│ │ Images │ │ Sitemap │
-   └────┬──────┘ └───┬────┘ └──┬──────┘
-        │            │          │
-        └────────────┼──────────┘
-                     ▼
-          ┌─────────────────────┐
-          │  SEO Consensus      │
-          │  (weighted scoring, │
-          │   health score,     │
-          │   action plan)      │
-          └─────────────────────┘
-```
-
----
-
-## Arguments
-
-| Argument | Values | Default | Description |
-|----------|--------|---------|-------------|
-| URL | Any valid URL | Required | Homepage URL to audit |
-| DEPTH | quick, deep, ultradeep, extreme | quick | quick = standard, deep = comprehensive, ultradeep = tmux sessions, extreme = page partitions |
-| MAX_PAGES | 1-500 | 50 | Maximum pages to analyze |
-
----
-
-## Step-by-Step Process
-
-### STEP 1: Parse Arguments
-
-```
-URL = first argument (required - ask if missing)
-DEPTH = quick (default), deep, ultradeep, or extreme
-MAX_PAGES = 50 (default)
-```
-
-**DEPTH behavior**:
-- `quick` (default): Deploy all 6 analyzers in-process. Standard analysis.
-- `deep`: Deploy all 6 analyzers in-process. More thorough per-analyzer, includes lower-priority findings.
-- `ultradeep`: Spawn each analyzer as a separate Claude Code session in tmux. Requires tmux. Falls back to `deep` if tmux unavailable.
-- `extreme`: Partition-based multi-agent audit. Site pages are split into groups and each group runs ALL analyzers.
-
-**ULTRADEEP mode** (DEPTH=ultradeep):
-1. Show cost estimate:
-   ```bash
-   node .agileflow/scripts/spawn-audit-sessions.js --audit=seo --target=URL --model=MODEL --dry-run
-   ```
-2. Confirm with user before launching
-3. Spawn sessions (use `--json` to capture trace ID):
-   ```bash
-   node .agileflow/scripts/spawn-audit-sessions.js --audit=seo --target=URL --model=MODEL --json
-   ```
-   Parse the JSON output to get `traceId`. Example: `{"ok":true,"traceId":"abc123ef",...}`
-4. Wait for all analyzers to complete:
-   ```bash
-   node .agileflow/scripts/check-sessions.js wait TRACE_ID --timeout=1800
-   ```
-   - Exit 0 = all complete (JSON results on stdout)
-   - Exit 1 = timeout (partial results on stdout, `missing` array shows what's left)
-   - To check progress without blocking: `node .agileflow/scripts/check-sessions.js status TRACE_ID`
-   - To retry stalled analyzers: `node .agileflow/scripts/check-sessions.js retry TRACE_ID`
-5. Parse `results` array from the JSON output. Pass all findings to consensus coordinator (same as deep mode).
-6. If tmux unavailable (spawn exits code 2), fall back to `DEPTH=deep` with warning
-
-**EXTREME mode** (DEPTH=extreme):
-Partition-based multi-agent audit. Instead of auditing the entire site as one unit, pages are split into groups and each group runs ALL 6 analyzers.
-1. Fetch sitemap or crawl to discover pages. Group pages into 3-7 logical partitions:
-   - By section: `/blog/`, `/docs/`, `/products/`, `/about/`
-   - By priority: high-traffic landing pages, content pages, utility pages
-   - If user provided PARTITIONS=N (a number), split into exactly N groups
-   - If user provided PARTITIONS=/blog,/docs,/products, use those URL path prefixes
-2. Show the partition plan and agent count to the user, confirm before launching:
-   Example: "4 page groups x 6 analyzers = 24 agents. Estimated cost: $X. Proceed?"
-3. Spawn sessions with partitions:
-   ```bash
-   node .agileflow/scripts/spawn-audit-sessions.js --audit=seo --target=URL --depth=extreme --partitions=/blog,/docs,/products --model=MODEL --json
-   ```
-4. Wait and collect results (same as ultradeep - use check-sessions.js)
-5. Run consensus on combined results from all partitions
-
-**PARTITIONS argument** (only used with DEPTH=extreme):
-| Value | Behavior |
-|-------|----------|
-| Not set | AI decides partitions (3-7 based on site structure) |
-| `PARTITIONS=5` | AI creates exactly 5 page groups |
-| `PARTITIONS=/blog,/docs,/products` | Use these exact URL path prefixes |
-
----
-
-### DEPTH ROUTING GATE
-
-| DEPTH | Route |
-|-------|-------|
-| `quick` or `deep` | Continue to STEP 2 below |
-| `ultradeep` | STOP. Follow ULTRADEEP instructions above. Do NOT proceed to STEP 2. |
-| `extreme` | STOP. Follow EXTREME instructions above. Do NOT proceed to STEP 2. |
-
-**CRITICAL**: STEPs 2-4 are for `quick`/`deep` ONLY. For `ultradeep`/`extreme`, the analyzers run in separate tmux sessions — NOT in-process via Task calls. If you deploy Task calls for ultradeep/extreme, you are doing it wrong. Follow the spawn-audit-sessions.js workflow above, then skip to the consensus step with the collected results.
-
----
-
-If URL is missing, ask:
-```xml
-<invoke name="AskUserQuestion">
-<parameter name="questions">[{
-  "question": "Which website would you like to audit?",
-  "header": "Target URL",
-  "multiSelect": false,
-  "options": [
-    {"label": "Enter URL", "description": "e.g., https://example.com"}
-  ]
-}]</parameter>
-</invoke>
-```
-
-### STEP 2: Detect Business Type
-
-Fetch the homepage with WebFetch and classify the business:
-
-| Type | Indicators |
-|------|-----------|
-| **SaaS** | Login/signup, pricing page, docs, API references, "free trial" |
-| **Local Business** | Address, phone, map, service areas, hours, "near me" |
-| **E-commerce** | Products, cart, checkout, categories, prices, reviews |
-| **Publisher** | Articles, blog, news, editorial, bylines, publication dates |
-| **Agency** | Portfolio, services list, team page, case studies, "hire us" |
-
-Also fetch:
-- `{URL}/robots.txt` - crawl rules, sitemap location
-- `{URL}/sitemap.xml` - page inventory
-
-### STEP 3: Deploy 6 Analyzers in Parallel (quick/deep ONLY)
-
-**CRITICAL**: Deploy ALL 6 analyzers in a SINGLE message with multiple Task calls.
-
-```xml
-<invoke name="Task">
-<parameter name="description">Technical SEO analysis</parameter>
-<parameter name="prompt">TASK: Analyze technical SEO for this website.
-
-TARGET URL: {url}
-DEPTH: {quick|deep}
-BUSINESS TYPE: {detected type}
-
-Analyze: crawlability, indexability, security headers, URL structure, mobile-friendliness, and CWV indicators.
-
-Also check robots.txt and basic crawl rules.
-
-OUTPUT your findings in standard format with Technical SEO Score X/100.</parameter>
-<parameter name="subagent_type">seo-analyzer-technical</parameter>
-<parameter name="run_in_background">true</parameter>
-</invoke>
-
-<invoke name="Task">
-<parameter name="description">Content quality E-E-A-T analysis</parameter>
-<parameter name="prompt">TASK: Analyze content quality and E-E-A-T signals.
-
-TARGET URL: {url}
-DEPTH: {quick|deep}
-BUSINESS TYPE: {detected type}
-
-Assess: Trustworthiness (30%), Expertise (25%), Authoritativeness (25%), Experience (20%), plus content depth, readability, and AI citation readiness.
-
-OUTPUT your findings with Content Quality Score X/100.</parameter>
-<parameter name="subagent_type">seo-analyzer-content</parameter>
-<parameter name="run_in_background">true</parameter>
-</invoke>
-
-<invoke name="Task">
-<parameter name="description">Schema/structured data analysis</parameter>
-<parameter name="prompt">TASK: Analyze schema markup and structured data.
-
-TARGET URL: {url}
-DEPTH: {quick|deep}
-BUSINESS TYPE: {detected type}
-
-Detect: existing JSON-LD/Microdata/RDFa, validate against Google standards, flag deprecated types, identify missing schema opportunities, generate ready-to-use snippets.
-
-OUTPUT your findings with Schema Score X/100.</parameter>
-<parameter name="subagent_type">seo-analyzer-schema</parameter>
-<parameter name="run_in_background">true</parameter>
-</invoke>
-
-<invoke name="Task">
-<parameter name="description">Image optimization analysis</parameter>
-<parameter name="prompt">TASK: Analyze image optimization.
-
-TARGET URL: {url}
-DEPTH: {quick|deep}
-BUSINESS TYPE: {detected type}
-
-Check: alt text quality, image sizing (CLS), modern formats (WebP/AVIF), lazy loading, LCP image priority, responsive images.
-
-OUTPUT your findings with Image Optimization Score X/100.</parameter>
-<parameter name="subagent_type">seo-analyzer-images</parameter>
-<parameter name="run_in_background">true</parameter>
-</invoke>
-
-<invoke name="Task">
-<parameter name="description">Core Web Vitals performance analysis</parameter>
-<parameter name="prompt">TASK: Analyze performance and Core Web Vitals.
-
-TARGET URL: {url}
-DEPTH: {quick|deep}
-BUSINESS TYPE: {detected type}
-
-Assess: LCP optimization, INP indicators, CLS risk factors, resource loading, render-blocking resources, third-party impact.
-
-OUTPUT your findings with Performance Score X/100.</parameter>
-<parameter name="subagent_type">seo-analyzer-performance</parameter>
-<parameter name="run_in_background">true</parameter>
-</invoke>
-
-<invoke name="Task">
-<parameter name="description">Sitemap validation analysis</parameter>
-<parameter name="prompt">TASK: Analyze XML sitemap.
-
-TARGET URL: {url}
-DEPTH: {quick|deep}
-BUSINESS TYPE: {detected type}
-
-Validate: sitemap existence, XML structure, URL coverage, quality gates, robots.txt reference.
-
-OUTPUT your findings with Sitemap Score X/100.</parameter>
-<parameter name="subagent_type">seo-analyzer-sitemap</parameter>
-<parameter name="run_in_background">true</parameter>
-</invoke>
-```
-
-### STEP 4: Collect Results
-
-Wait for all analyzers to complete using TaskOutput with block=true. Collect all 6 outputs.
-
-### STEP 5: Run Consensus Coordinator
-
-Pass all analyzer outputs to the consensus coordinator:
-
-```xml
-<invoke name="Task">
-<parameter name="description">SEO audit consensus and scoring</parameter>
-<parameter name="prompt">You are the SEO Consensus Coordinator.
-
-TARGET URL: {url}
-BUSINESS TYPE: {detected type}
-DEPTH: {depth}
-
-## Analyzer Outputs
-
-### Technical SEO Results:
-{technical_output}
-
-### Content Quality Results:
-{content_output}
-
-### Schema Results:
-{schema_output}
-
-### Image Optimization Results:
-{images_output}
-
-### Performance Results:
-{performance_output}
-
-### Sitemap Results:
-{sitemap_output}
-
----
-
-Follow your consensus process:
-1. Confirm business type classification
-2. Parse all findings into normalized structure
-3. Calculate category scores (each out of 100)
-4. Apply weights: Technical 20%, Content 20%, Schema 15%, Performance 15%, Images 15%, Sitemap 15%
-5. Compute overall Health Score 0-100
-6. Cross-reference findings flagged by multiple analyzers
-7. Prioritize: Critical → High → Medium → Low
-8. Generate action plan with quick wins
-9. Save report to docs/08-project/seo-audits/seo-audit-{YYYYMMDD}.md</parameter>
-<parameter name="subagent_type">seo-consensus</parameter>
-</invoke>
-```
-
-### STEP 6: Present Results
-
-After consensus completes, show summary and offer next steps:
-
-```xml
-<invoke name="AskUserQuestion">
-<parameter name="questions">[{
-  "question": "SEO Audit complete: Health Score {X}/100 ({rating}). Business type: {type}. {N} findings ({critical} critical, {high} high).",
-  "header": "Next steps",
-  "multiSelect": false,
-  "options": [
-    {"label": "Fix {critical} Critical issues now (Recommended)", "description": "{top_issue_summary}"},
-    {"label": "Deep-dive into {lowest_category}", "description": "Lowest score: {category} at {score}/100"},
-    {"label": "Generate schema markup for this site", "description": "Run /agileflow:seo:schema to get ready-to-use JSON-LD"},
-    {"label": "Create SEO improvement plan", "description": "Run /agileflow:seo:plan for strategic roadmap"}
-  ]
-}]</parameter>
-</invoke>
-```
-
----
-
-## Example Output
-
-```
-SEO Audit: https://example.com
-══════════════════════════════════════════════════════════════
-
-Business Type: SaaS
-Depth: quick
-
-Deploying 6 SEO analyzers...
-✓ Technical SEO Analyzer
-✓ Content Quality Analyzer
-✓ Schema Analyzer
-✓ Image Optimization Analyzer
-✓ Performance Analyzer
-✓ Sitemap Analyzer
-
-Running consensus...
-✓ Consensus complete
-
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-HEALTH SCORE: 72/100 (Good)
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-
-| Category         | Score  | Weight | Weighted |
-|-----------------|--------|--------|----------|
-| Technical SEO   | 85/100 | 20%    | 17.0     |
-| Content Quality | 68/100 | 20%    | 13.6     |
-| Schema          | 45/100 | 15%    |  6.8     |
-| Performance     | 78/100 | 15%    | 11.7     |
-| Images          | 82/100 | 15%    | 12.3     |
-| Sitemap         | 75/100 | 15%    | 11.3     |
-
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-CRITICAL: 1 | HIGH: 3 | MEDIUM: 5 | LOW: 2
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-
-[Full report saved to docs/08-project/seo-audits/seo-audit-20260225.md]
-```
-
----
-
-<!-- COMPACT_SUMMARY_START -->
-## Compact Summary
-
-**Command**: `/agileflow:seo:audit` - Full website SEO audit with 6 parallel analyzers
-
-**Quick Usage**:
-```
-/agileflow:seo:audit https://example.com                     # Quick audit
-/agileflow:seo:audit https://example.com DEPTH=deep           # Deep audit
-/agileflow:seo:audit https://example.com DEPTH=ultradeep      # Tmux sessions
-/agileflow:seo:audit https://example.com DEPTH=extreme        # Page partition audit
-```
-
-**What It Does**: Fetch homepage → Detect business type → Deploy 6 analyzers in parallel → Consensus weights scores → Health Score 0-100 → Prioritized action plan
-
-**Analyzers (all 6 deploy in parallel)**:
-- `seo-analyzer-technical` - Crawlability, indexability, security, URLs, mobile
-- `seo-analyzer-content` - E-E-A-T scoring, readability, AI citation readiness
-- `seo-analyzer-schema` - JSON-LD detection, validation, deprecated types
-- `seo-analyzer-images` - Alt text, sizing, formats, lazy loading
-- `seo-analyzer-performance` - LCP, INP, CLS, resource loading
-- `seo-analyzer-sitemap` - XML validation, coverage, quality gates
-
-**Category Weights**: Technical 20%, Content 20%, Schema 15%, Performance 15%, Images 15%, Sitemap 15%
-
-**Output**: `docs/08-project/seo-audits/seo-audit-{YYYYMMDD}.md`
-<!-- COMPACT_SUMMARY_END -->
-
----
-
-## Related Commands
-
-- `/agileflow:seo:page` - Deep-dive into a single page
-- `/agileflow:seo:schema` - Generate schema markup
-- `/agileflow:seo:geo` - AI search optimization
-- `/agileflow:seo:plan` - Strategic SEO planning
-- `/agileflow:seo:technical` - Technical SEO deep-dive

package/src/core/commands/seo/competitor.md

@@ -1,174 +0,0 @@
----
-description: SEO competitor comparison - analyze competing pages, generate feature matrices, and create comparison content with schema markup
-argument-hint: "YOUR_URL COMPETITOR_URL [COMPETITOR_URL_2]"
-compact_context:
-  priority: medium
-  preserve_rules:
-    - "ACTIVE COMMAND: /agileflow:seo:competitor - Competitor SEO comparison"
-    - "Fetch both your page and competitor page(s)"
-    - "Generate feature comparison matrix"
-    - "Produce comparison page content with Product schema"
-  state_fields:
-    - your_url
-    - competitor_urls
-    - comparison_matrix
----
-
-# /agileflow:seo:competitor
-
-Analyze competitor pages and generate SEO-optimized comparison content with feature matrices and structured data.
-
----
-
-## Quick Reference
-
-```
-/agileflow:seo:competitor https://you.com https://competitor.com          # 1v1 comparison
-/agileflow:seo:competitor https://you.com https://comp1.com https://comp2.com  # Multi-competitor
-```
-
----
-
-## Arguments
-
-| Argument | Values | Default | Description |
-|----------|--------|---------|-------------|
-| YOUR_URL | Any valid URL | Required | Your product/service page |
-| COMPETITOR_URL | Any valid URL(s) | Required | Competitor page(s) to compare (1-3) |
-
----
-
-## Process
-
-### STEP 1: Fetch All Pages
-
-Use WebFetch to retrieve your page and each competitor page. Extract:
-- Product/service name
-- Features list
-- Pricing (if visible)
-- Key differentiators
-- Schema markup present
-- Meta title/description
-
-### STEP 2: Build Feature Matrix
-
-Create a comparison matrix:
-
-```markdown
-| Feature | Your Product | Competitor A | Competitor B |
-|---------|-------------|-------------|-------------|
-| {feature 1} | Yes/No/Value | Yes/No/Value | Yes/No/Value |
-| {feature 2} | Yes/No/Value | Yes/No/Value | Yes/No/Value |
-| Pricing | {price} | {price} | {price} |
-| Free Trial | Yes/No | Yes/No | Yes/No |
-```
-
-### STEP 3: SEO Comparison
-
-Compare SEO elements:
-
-| Element | You | Competitor |
-|---------|-----|-----------|
-| Title tag | {length, keywords} | {length, keywords} |
-| Meta description | {present, quality} | {present, quality} |
-| H1 | {text} | {text} |
-| Schema types | {types} | {types} |
-| Word count | {count} | {count} |
-| Internal links | {count} | {count} |
-| Image optimization | {score} | {score} |
-
-### STEP 4: Generate Comparison Content
-
-Produce draft comparison page content:
-
-```markdown
-# {Your Product} vs {Competitor}: {Year} Comparison
-
-## Quick Summary
-
-{2-3 sentence overview}
-
-## Feature Comparison
-
-[Feature matrix table]
-
-## {Your Product} Advantages
-
-1. {advantage with evidence}
-2. {advantage}
-
-## When to Choose {Competitor}
-
-{Fair, balanced assessment}
-
-## Pricing Comparison
-
-[Pricing table]
-
-## Verdict
-
-{Balanced recommendation}
-```
-
-### STEP 5: Generate Schema
-
-```json
-{
-  "@context": "https://schema.org",
-  "@type": "WebPage",
-  "name": "{Your Product} vs {Competitor}",
-  "description": "Compare {Your Product} and {Competitor} features, pricing, and capabilities",
-  "mainEntity": {
-    "@type": "ItemList",
-    "itemListElement": [
-      {
-        "@type": "Product",
-        "name": "{Your Product}",
-        "url": "{your_url}"
-      },
-      {
-        "@type": "Product",
-        "name": "{Competitor}",
-        "url": "{competitor_url}"
-      }
-    ]
-  }
-}
-```
-
-### STEP 6: Output
-
-```markdown
-# Competitor Analysis: {You} vs {Competitor(s)}
-
-## SEO Comparison
-[Side-by-side SEO element comparison]
-
-## Feature Matrix
-[Feature comparison table]
-
-## Content Gaps
-[What competitor has that you're missing]
-
-## Generated Comparison Page
-[Draft content ready to publish]
-
-## Schema Markup
-[JSON-LD for the comparison page]
-
-## SEO Recommendations
-1. {Priority improvement}
-2. {Next priority}
-```
-
----
-
-<!-- COMPACT_SUMMARY_START -->
-## Compact Summary
-
-**Command**: `/agileflow:seo:competitor` - Competitor SEO comparison
-
-**Output**: Feature matrix, SEO comparison, draft comparison page content, schema markup
-
-**Usage**: `/agileflow:seo:competitor YOUR_URL COMPETITOR_URL [COMPETITOR_URL_2]`
-<!-- COMPACT_SUMMARY_END -->