@growthub/cli 0.14.4 → 0.14.6

package/assets/worker-kits/growthub-geo-seo-v1/runtime-assumptions.md

@@ -1,175 +0,0 @@
-# Runtime Assumptions
-
-**Frozen at kit creation: 2026-04-14. Update this file when upstream fork behavior changes.**
-
----
-
-## Execution Mode Overview
-
-| Mode | Requirements | Fork Used? | Python Scripts? | PDF? | Accuracy |
-|---|---|---|---|---|---|
-| `local-fork` | Python 3.8+, Playwright, geo-seo-claude clone | Yes | Yes | Yes | Highest |
-| `agent-only` | Nothing (Claude Code only) | No | No | No | Good |
-| `hybrid` | ANTHROPIC_API_KEY + fork | Yes | Yes | Yes | Highest |
-
-### Choosing a Mode
-
-- **Use `local-fork`** when you need the most accurate citability scores (Python parser), real Playwright-rendered page content, or PDF output.
-- **Use `agent-only`** when the fork is not installed or when speed matters more than exact precision. All outputs are still produced using the same templates and formulas.
-- **Use `hybrid`** when you want agent reasoning layer on top of Python data collection — useful for complex competitor comparisons or detailed content rewrites.
-
----
-
-## geo-seo-claude Upstream Assumptions
-
-These are the assumptions frozen at kit creation time about the `geo-seo-claude` fork at https://github.com/zubair-trabzada/geo-seo-claude.
-
-### Python Environment
-
-| Requirement | Value | Notes |
-|---|---|---|
-| Python version | 3.8+ | Tested on 3.10 and 3.11 |
-| Package manager | pip | `pip install -r requirements.txt` |
-| Key dependencies | BeautifulSoup4, Playwright, ReportLab, Flask, Rich, validators | See requirements.txt |
-| Playwright browser | chromium | `playwright install chromium` |
-
-### 14 CLI Skills (Commands)
-
-All 14 `/geo` commands are available in `skills/` directory:
-
-| Command | File | Status |
-|---|---|---|
-| `/geo audit` | `skills/audit.md` | Available |
-| `/geo citability` | `skills/citability.md` | Available |
-| `/geo crawlers` | `skills/crawlers.md` | Available |
-| `/geo brands` | `skills/brands.md` | Available |
-| `/geo report` | `skills/report.md` | Available |
-| `/geo report-pdf` | `skills/report-pdf.md` | Available |
-| `/geo content` | `skills/content.md` | Available |
-| `/geo schema` | `skills/schema.md` | Available |
-| `/geo technical` | `skills/technical.md` | Available |
-| `/geo llmstxt` | `skills/llmstxt.md` | Available |
-| `/geo quick` | `skills/quick.md` | Available |
-| `/geo proposal` | `skills/proposal.md` | Available |
-| `/geo prospect` | `skills/prospect.md` | Available |
-| `/geo compare` | `skills/compare.md` | Available |
-
-### 5 Parallel Subagents
-
-All 5 subagent definitions are in `agents/` directory:
-
-| Subagent | File | Weight |
-|---|---|---|
-| geo-ai-visibility | `agents/geo-ai-visibility.md` | 25% |
-| geo-content | `agents/geo-content.md` | 20% |
-| geo-platform-analysis | `agents/geo-platform-analysis.md` | 10% |
-| geo-schema | `agents/geo-schema.md` | 10% |
-| geo-technical | `agents/geo-technical.md` | 15% |
-
-### Key Python Scripts
-
-| Script | Path in Fork | Purpose |
-|---|---|---|
-| fetch_page.py | `scripts/fetch_page.py` | Playwright-based page fetcher |
-| citability_scorer.py | `scripts/citability_scorer.py` | 5-metric citability algorithm |
-| brand_scanner.py | `scripts/brand_scanner.py` | 8-platform brand mention scanner |
-| generate_pdf_report.py | `scripts/generate_pdf_report.py` | ReportLab PDF generator |
-| llmstxt_generator.py | `scripts/llmstxt_generator.py` | llms.txt generator |
-| crm_dashboard.py | `scripts/crm_dashboard.py` | Flask CRM dashboard |
-
-### Schema Templates
-
-6 JSON-LD templates in `schema/` directory:
-
-| Template | Type |
-|---|---|
-| organization.json | Organization |
-| article.json | Article |
-| faqpage.json | FAQPage |
-| product.json | Product |
-| localbusiness.json | LocalBusiness |
-| breadcrumblist.json | BreadcrumbList |
-
----
-
-## Execution Surface Flows
-
-### Local-Fork Mode
-
-```
-User request → Environment gate (Step 0)
-  ↓
-Read skills.md + brand kit (Step 1)
-  ↓
-Read runtime docs (Step 2)
-  ↓
-Inspect fork: README, skills/, agents/, scripts/ (Step 3)
-  ↓
-3-question gate (Step 4)
-  ↓
-Select /geo command (Step 5)
-  ↓
-Phase 1: python fetch_page.py <url> → phase1_data.json (Step 6)
-  ↓
-Phase 2: 5 subagents in parallel → component scores (Step 7)
-  ↓
-GEO Score synthesis → composite score (Step 8)
-  ↓
-Artifact package: 9–11 Markdown files (Step 9)
-  ↓ (if PDF requested)
-python generate_pdf_report.py --input geo_score_data.json (Step 9)
-  ↓
-Log deliverable → brand kit DELIVERABLES LOG (Step 10)
-```
-
-### Agent-Only Mode
-
-```
-User request → Environment gate (Step 0 — confirm agent-only)
-  ↓
-Read skills.md + brand kit (Step 1)
-  ↓
-Read runtime docs (Step 2)
-  ↓
-Skip fork inspection (Step 3 — N/A)
-  ↓
-3-question gate (Step 4)
-  ↓
-Select /geo command (Step 5)
-  ↓
-Phase 1: fetch page via Claude built-in fetch → parse manually (Step 6)
-  ↓
-Phase 2: 5 subagents via Claude reasoning → component scores (Step 7)
-  ↓
-GEO Score synthesis → composite score (Step 8)
-  ↓
-Artifact package: 9–11 Markdown files + geo_score_data.json (Step 9)
-  ↓ (PDF not available — note Markdown equivalent)
-Log deliverable → brand kit DELIVERABLES LOG (Step 10)
-```
-
----
-
-## Output Assumption
-
-All outputs are Markdown files written to:
-
-```
-output/<client-slug>/<project-slug>/
-```
-
-The operator does not write directly to client systems. Outputs are produced locally and then shared with clients via the agreed delivery channel.
-
----
-
-## Flask CRM Dashboard Assumption
-
-The CRM dashboard (`crm_dashboard.py`) runs as a separate process. It is not started automatically during an audit session.
-
-To launch manually from the fork directory:
-```bash
-python scripts/crm_dashboard.py
-# Accessible at http://localhost:5000 (or FLASK_PORT if set)
-```
-
-The dashboard reads from the `output/` directory and displays audit history across all clients.

package/assets/worker-kits/growthub-geo-seo-v1/setup/check-deps.sh

@@ -1,80 +0,0 @@
-#!/usr/bin/env bash
-# check-deps.sh — Verify dependencies for geo-seo-claude local-fork workflows
-# Usage: bash setup/check-deps.sh
-set -e
-
-PASS=0
-FAIL=0
-
-check() {
-  local name="$1" cmd="$2" hint="$3"
-  if command -v "$cmd" >/dev/null 2>&1; then
-    echo "OK   $name ($(command -v $cmd))"
-    PASS=$((PASS+1))
-  else
-    echo "MISS $name — $hint"
-    FAIL=$((FAIL+1))
-  fi
-}
-
-echo "=== Growthub GEO SEO Studio — Dependency Check ==="
-echo ""
-
-check "python3"     "python3"     "https://python.org — install Python 3.8+"
-check "pip"         "pip"         "Comes with Python — try: python3 -m pip"
-check "playwright"  "playwright"  "pip install playwright && playwright install chromium"
-check "git"         "git"         "https://git-scm.com"
-check "node"        "node"        "https://nodejs.org — required for setup/verify-env.mjs"
-
-echo ""
-
-# Check Python version is 3.8+
-if command -v python3 >/dev/null 2>&1; then
-  PY_VERSION=$(python3 -c "import sys; print(f'{sys.version_info.major}.{sys.version_info.minor}')")
-  PY_MAJOR=$(python3 -c "import sys; print(sys.version_info.major)")
-  PY_MINOR=$(python3 -c "import sys; print(sys.version_info.minor)")
-  if [ "$PY_MAJOR" -ge 3 ] && [ "$PY_MINOR" -ge 8 ]; then
-    echo "OK   Python version: $PY_VERSION (3.8+ required)"
-    PASS=$((PASS+1))
-  else
-    echo "MISS Python version: $PY_VERSION — geo-seo-claude requires Python 3.8+"
-    FAIL=$((FAIL+1))
-  fi
-fi
-
-# Check Playwright chromium is installed (not just the CLI)
-if command -v playwright >/dev/null 2>&1; then
-  if playwright browsers 2>/dev/null | grep -q "chromium"; then
-    echo "OK   Playwright chromium browser installed"
-    PASS=$((PASS+1))
-  else
-    echo "MISS Playwright chromium browser not found — run: playwright install chromium"
-    FAIL=$((FAIL+1))
-  fi
-fi
-
-# Check for the fork directory
-FORK_DIR="${GEO_SEO_HOME:-${GEO_SEO_FORK_PATH:-$HOME/geo-seo-claude}}"
-if [ -d "$FORK_DIR" ]; then
-  echo "OK   geo-seo-claude fork at $FORK_DIR"
-  PASS=$((PASS+1))
-else
-  echo "MISS geo-seo-claude fork not found at $FORK_DIR"
-  echo "     Run: bash setup/clone-fork.sh"
-  echo "     Or set GEO_SEO_HOME (legacy alias: GEO_SEO_FORK_PATH) to your fork path in .env"
-  FAIL=$((FAIL+1))
-fi
-
-echo ""
-echo "Passed: $PASS  |  Missing: $FAIL"
-
-if [ "$FAIL" -gt 0 ]; then
-  echo ""
-  echo "Install missing dependencies before running local-fork workflows."
-  echo "Agent-only mode (no fork required) is always available as a fallback."
-  exit 1
-fi
-
-echo ""
-echo "All dependencies present. Local-fork mode is ready."
-echo "Next: node setup/verify-env.mjs"

package/assets/worker-kits/growthub-geo-seo-v1/setup/clone-fork.sh

@@ -1,56 +0,0 @@
-#!/usr/bin/env bash
-# clone-fork.sh — Clone geo-seo-claude and install dependencies
-# Usage: bash setup/clone-fork.sh
-set -e
-
-FORK_DIR="${GEO_SEO_HOME:-${GEO_SEO_FORK_PATH:-$HOME/geo-seo-claude}}"
-REPO_URL="https://github.com/zubair-trabzada/geo-seo-claude"
-
-echo "=== Growthub GEO SEO Studio — Fork Setup ==="
-echo ""
-
-if [ -d "$FORK_DIR" ]; then
-  echo "Fork already exists at $FORK_DIR — skipping clone."
-  echo "To re-clone, remove the directory first: rm -rf $FORK_DIR"
-else
-  echo "Cloning geo-seo-claude → $FORK_DIR"
-  git clone "$REPO_URL" "$FORK_DIR"
-  echo "Clone complete."
-fi
-
-echo ""
-echo "Installing Python dependencies..."
-cd "$FORK_DIR"
-pip install -r requirements.txt
-echo "Python dependencies installed."
-
-echo ""
-echo "Installing Playwright browsers..."
-playwright install chromium
-echo "Playwright chromium installed."
-
-echo ""
-echo "Verifying key scripts..."
-SCRIPTS_OK=0
-for script in fetch_page.py citability_scorer.py brand_scanner.py generate_pdf_report.py llmstxt_generator.py; do
-  if [ -f "scripts/$script" ]; then
-    echo "  OK   scripts/$script"
-  else
-    echo "  MISS scripts/$script — may not exist in this fork version"
-    SCRIPTS_OK=1
-  fi
-done
-
-echo ""
-if [ "$SCRIPTS_OK" -eq 0 ]; then
-  echo "geo-seo-claude is ready at $FORK_DIR"
-else
-  echo "geo-seo-claude cloned at $FORK_DIR — some scripts may be missing."
-  echo "Check the fork's README for the correct script paths."
-fi
-
-echo ""
-echo "Quick test:"
-echo "  python $FORK_DIR/scripts/fetch_page.py https://example.com"
-echo ""
-echo "Run the GEO audit operator by pointing Claude Code at this kit."

package/assets/worker-kits/growthub-geo-seo-v1/setup/verify-env.mjs

@@ -1,152 +0,0 @@
-#!/usr/bin/env node
-// verify-env.mjs — Verify the geo-seo-claude environment is ready
-// Usage: node setup/verify-env.mjs
-// No network calls are made. All checks are local filesystem only.
-
-import { existsSync, readFileSync } from "fs";
-import { homedir } from "os";
-import { resolve, join } from "path";
-
-// ─── Helpers ───────────────────────────────────────────────────────────────
-
-function parseEnvFile(filePath) {
-  if (!existsSync(filePath)) return {};
-  const lines = readFileSync(filePath, "utf8").split("\n");
-  const env = {};
-  for (const line of lines) {
-    const trimmed = line.trim();
-    if (!trimmed || trimmed.startsWith("#")) continue;
-    const eqIdx = trimmed.indexOf("=");
-    if (eqIdx === -1) continue;
-    const key = trimmed.slice(0, eqIdx).trim();
-    const val = trimmed.slice(eqIdx + 1).trim().replace(/^["']|["']$/g, "");
-    env[key] = val;
-  }
-  return env;
-}
-
-function pass(label, note = "") {
-  console.log(`  PASS  ${label}${note ? " — " + note : ""}`);
-}
-
-function fail(label, message) {
-  console.log(`  FAIL  ${label} — ${message}`);
-  failures.push(label);
-}
-
-function warn(label, message) {
-  console.log(`  WARN  ${label} — ${message}`);
-}
-
-// ─── State ─────────────────────────────────────────────────────────────────
-
-const failures = [];
-
-// ─── Load .env ─────────────────────────────────────────────────────────────
-
-const envPath = resolve(process.cwd(), ".env");
-const envExamplePath = resolve(process.cwd(), ".env.example");
-
-console.log("=== Growthub GEO SEO Studio — Environment Verification ===");
-console.log("");
-
-let env = {};
-if (existsSync(envPath)) {
-  env = parseEnvFile(envPath);
-  pass(".env file", `found at ${envPath}`);
-} else if (existsSync(envExamplePath)) {
-  warn(".env file", ".env not found — using .env.example for reference only. Run: cp .env.example .env");
-} else {
-  warn(".env file", ".env and .env.example both missing — proceeding with process.env only");
-}
-
-// Merge with process.env (process.env takes priority over .env file)
-const config = { ...env, ...process.env };
-
-console.log("");
-console.log("--- Fork Path Check ---");
-
-// ─── Fork Path ─────────────────────────────────────────────────────────────
-
-const forkPathRaw = config["GEO_SEO_HOME"] || config["GEO_SEO_FORK_PATH"] || join(homedir(), "geo-seo-claude");
-const forkPath = resolve(forkPathRaw);
-
-if (existsSync(forkPath)) {
-  pass("GEO_SEO_FORK_PATH", `fork found at ${forkPath}`);
-
-  // Check key scripts exist in the fork
-  const requiredScripts = [
-    "scripts/fetch_page.py",
-    "scripts/citability_scorer.py",
-    "scripts/brand_scanner.py",
-    "scripts/generate_pdf_report.py",
-    "scripts/llmstxt_generator.py",
-  ];
-
-  for (const scriptPath of requiredScripts) {
-    const fullPath = join(forkPath, scriptPath);
-    if (existsSync(fullPath)) {
-      pass(scriptPath);
-    } else {
-      warn(scriptPath, `not found in fork at ${fullPath} — may be in a different path in this fork version`);
-    }
-  }
-} else {
-  warn(
-    "GEO_SEO_FORK_PATH",
-    `fork not found at ${forkPath}. Run: bash setup/clone-fork.sh\n         Agent-only mode is available without the fork.`
-  );
-}
-
-console.log("");
-console.log("--- API Key Check ---");
-
-// ─── Anthropic API Key (optional) ─────────────────────────────────────────
-
-const anthropicKey = config["ANTHROPIC_API_KEY"];
-if (!anthropicKey) {
-  warn("ANTHROPIC_API_KEY", "not set — agent-enhanced analysis requires this key. Core Python analysis works without it.");
-} else if (!anthropicKey.startsWith("sk-ant-")) {
-  fail("ANTHROPIC_API_KEY", `key does not start with 'sk-ant-' — this may be an invalid key. Check https://console.anthropic.com`);
-} else if (anthropicKey.length < 40) {
-  fail("ANTHROPIC_API_KEY", "key appears too short — verify you copied the full key from https://console.anthropic.com");
-} else {
-  pass("ANTHROPIC_API_KEY", "key format looks valid (starts with sk-ant-, adequate length)");
-}
-
-// ─── Optional Config ───────────────────────────────────────────────────────
-
-console.log("");
-console.log("--- Optional Config ---");
-
-const flaskPort = config["FLASK_PORT"] || "5000 (default)";
-pass("FLASK_PORT", `${flaskPort} — Flask CRM dashboard will use this port`);
-
-const outputRoot = config["GEO_OUTPUT_ROOT"] || "./output (default)";
-pass("GEO_OUTPUT_ROOT", outputRoot);
-
-const playwrightBrowser = config["PLAYWRIGHT_BROWSER"] || "chromium (default)";
-pass("PLAYWRIGHT_BROWSER", playwrightBrowser);
-
-// ─── Summary ───────────────────────────────────────────────────────────────
-
-console.log("");
-console.log("=== Summary ===");
-
-if (failures.length === 0) {
-  const forkReady = existsSync(forkPath);
-  if (forkReady) {
-    console.log("Environment is ready. Fork found. Run your first audit with /geo audit.");
-  } else {
-    console.log("Environment OK. Fork not found — agent-only mode available.");
-    console.log("To enable local-fork mode: bash setup/clone-fork.sh");
-  }
-  process.exit(0);
-} else {
-  console.log(`${failures.length} check(s) failed:`);
-  for (const f of failures) {
-    console.log(`  - ${f}`);
-  }
-  console.log("Resolve these before running local-fork mode workflows.");
-  process.exit(1);
-}

package/assets/worker-kits/growthub-geo-seo-v1/skills/README.md

@@ -1,23 +0,0 @@
-# `skills/` — nested sub-skill convention (primitive #5)
-
-A **sub-skill** is a full `SKILL.md`-addressable lane that a parent skill can spawn as a parallel sub-agent.
-
-## Convention
-
-```
-skills/
-├── README.md                        # this file
-└── <slug>/                          # kebab-case; matches the SKILL.md name
-    ├── SKILL.md                     # frontmatter + routing body (≤ 500 lines)
-    ├── references/                  # optional — long docs loaded on demand
-    ├── templates/                   # optional — reusable text/JS templates
-    └── scripts/                     # optional — deterministic helpers
-```
-
-Each sub-skill's frontmatter follows `@growthub/api-contract/skills::SkillManifest`. Sub-skills share the parent's `.growthub-fork/project.md` journal — they do not branch it.
-
-## Parallelism
-
-Spawn a sub-skill sub-agent when (a) the sub-skill's work is fully scoped by its own criteria, and (b) the parent's next step does not depend on intermediate state from the sub-skill. Each sub-skill run appends a row to `project.md::subSkillRuns` so the parent can read the outcome on return.
-
-See the parent `SKILL.md` `subSkills[]` array for the current roster.