What makes site-launch-checklist notable?

1K downloads. Trust evidence available

How should site-launch-checklist be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

site-launch-checklist

Pre-launch checklist for shipping a new website. Orchestrates analytics setup (GA4, PostHog, Google Search Console, Ahrefs), legal compliance, security headers and audit, SEO and GEO with keyword research validated against Google Trends (robots.txt, sitemaps, llms.txt, AI policy, schema markup, hreflang), copywriting consistency via a TONE.md and a humanizer pass in the matching language, OpenGraph and social previews, full favicon set with manifest, quality gates (Lighthouse, Core Web Vitals, WCAG accessibility, mobile testing), and setup of a weekly SEO agent. Use this skill whenever the user mentions launching a site/app, deploying a domain to production, pre-launch audit, shipping a marketing/docs/SaaS site or lead magnet, or says "checklist for the site", "ready to ship", "before I go live", "audit before launch", "ready for prod", or asks for a site review.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.2.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.2.0release · observed Aug 21, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s173arkhs3131fq5jf769qq75583hdgt:site-launch-checklist

Install using `clawhub skill install s173arkhs3131fq5jf769qq75583hdgt:site-launch-checklist` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/samber/site-launch-checklist before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-samber-site-launch-checklist/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

144,279 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: site-launch-checklist
description: Pre-launch checklist for shipping a new website. Orchestrates analytics setup (GA4, PostHog, Google Search Console, Ahrefs), legal compliance, security headers and audit, SEO and GEO with keyword research validated against Google Trends (robots.txt, sitemaps, llms.txt, AI policy, schema markup, hreflang), copywriting consistency via a TONE.md and a humanizer pass in the matching language, OpenGraph and social previews, full favicon set with manifest, quality gates (Lighthouse, Core Web Vitals, WCAG accessibility, mobile testing), and setup of a weekly SEO agent. Use this skill whenever the user mentions launching a site/app, deploying a domain to production, pre-launch audit, shipping a marketing/docs/SaaS site or lead magnet, or says "checklist for the site", "ready to ship", "before I go live", "audit before launch", "ready for prod", or asks for a site review.
license: MIT
compatibility: Designed for Claude Code, Codex or similar harness.
user-invocable: true
metadata:
  author: samber
  version: "1.2.0"
  openclaw:
    emoji: "📊"
    homepage: https://github.com/samber/cc-skills
    install:
      - kind: npm
        package: skills
        bins: [skills]
      - kind: brew
        formula: jq
        bins: [jq]
    requires:
      bins:
        - curl
        - npm
        - npx
        - jq
allowed-tools: Read Edit Write Glob Grep Agent AskUserQuestion
---

**Questions:** Ask the user through the environment's question tool — never as plain-text prose. One question at a time, 2–4 tappable options, wait for the answer. If the environment has no question tool, ask in prose with the same options, one at a time.

# Site Launch Checklist

Pre-launch audit and setup workflow for shipping a new website. Opinionated for Cloudflare DNS + Vercel hosting + PostHog + Legal context.

## Interaction style (READ FIRST)

This skill is intentionally interactive. Ask aggressively instead of assuming. The user will tap, not type.

**Always ask these questions at the start of a run** (one at a time, in this order):

1. Site type: `doc-site` | `marketing/lead-gen` | `SaaS-app` | `training/paid-course` | `personal-portfolio`
2. Migration: `greenfield-new-domain` | `migration-need-301-redirects` | `replacing-existing-on-same-domain`
3. Multilingual: `single-locale` | `en` | `fr+en` | `other-multi`
4. PostHog setup: `hogpost.samber.dev` | `set-up-new-proxy` | `skip-PostHog`
5. AI scraper policy: `use-default-for-site-type` | `customize-per-bot` | `block-all`
6. Browser tool available: `claude-chrome-extension` | `playwright` | `neither-skip-browser-checks`

**Ask again at every decision point throughout the phases**, including:

- Whether to install Sentry / BetterStack / Crisp (depends on site type, ask explicitly)
- www vs apex canonical preference (most sites: apex; ask anyway)
- Which AI bots to allow if user chose `customize-per-bot`
- CSP tightness level: `strict-default-src-none` | `balanced-allow-self` | `permi

_meta.json

{
  "ownerId": "kn72rhnkwjfeex9wr1n7y24qa983cjn3",
  "slug": "site-launch-checklist",
  "version": "1.2.0",
  "publishedAt": 1787314429125
}

references/decisions.md

# Decisions and matrices

Repeating decisions for site launches. Apply the matrix based on the site type the user confirmed at the start of the session. When a decision is ambiguous or borderline, ask through the question tool, one at a time, rather than assuming.

## AI scraper policy by site type

Decide which AI training and AI-search crawlers to allow per site type. Encode the decision in `robots.txt` (see `templates.md`).

### Marketing / lead-gen page (consulting, training landing)

Allow all AI scrapers. Your conversion copy is intellectual property; training it into LLMs that may recommend competitors is anti-value. But AI citations on a sales page is good.

### Paid course / training page

Block all. Content is the product.

### Personal portfolio / personal blog

Allow the citing crawlers (ClaudeBot, GPTBot, PerplexityBot, Google-Extended). Useful for "who is X" or "what does X work on" queries.

### SaaS app

- App subdomain (e.g., app.example.com): block all AI scrapers. The app is gated, no value in scraping.
- Landing / marketing subdomain: apply the marketing rules above.

### Default when site type is unclear

Block all. Ask the user. Better to surface the decision than to silently expose content to crawlers.

---

## Observability tier by site type

Decide which analytics and observability tools to install. Always confirm conditional tools with the user.

### Doc site / lib homepage

| Tool | Install? |
| --- | --- |
| GA4 | Yes |
| PostHog (via hogpost.samber.dev or new proxy) | Yes |
| Google Search Console | Yes |
| Bing Webmaster + IndexNow | Yes |
| Ahrefs | Yes |
| Crisp | **No** (doc readers don't chat, it tanks Lighthouse) |
| Sentry | **No** (static, no app logic to crash) |
| BetterStack | **No** (Vercel uptime is enough) |

### Marketing / lead-gen

All of the doc-site tools, plus:

| Tool        | Install?                                       |
| ----------- | ---------------------------------------------- |
| Crisp       | Yes (conversion intent)                        |
| Sentry      | Yes if there are forms or interactive elements |
| BetterStack | Only if you publish an SLA                     |

### SaaS app

All of the above, plus:

| Tool              | Install?                       |
| ----------------- | ------------------------------ |
| Sentry            | **Mandatory**                  |
| BetterStack       | Yes, with a public status page |
| Crisp or Intercom | Yes                            |

### Personal portfolio

| Tool        | Install? |
| ----------- | -------- |
| GA4         | Yes      |
| PostHog     | Yes      |
| GSC         | Yes      |
| Ahrefs      | Optional |
| Crisp       | No       |
| Sentry      | No       |
| BetterStack | No       |

---

## www vs apex canonical

Default: **apex is canonical, www redirects to apex via 308**.

Exception: if the site is hosted on a platform that requires CNAME (which cannot be set on apex per DNS RFCs), the platform's flattening / ALIAS / ANAME f

references/templates.md

# Templates

File and header templates for site launches. Apply per the matrices in `decisions.md`.

## robots.txt

### Template: doc site for OSS lib (allow AI scrapers)

```
User-agent: *
Allow: /

Sitemap: https://EXAMPLE.com/sitemap.xml

# AI scrapers (per decisions.md: doc-site policy)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Blocked low-value scrapers
User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /
```

### Template: marketing / lead-gen (block all AI scrapers)

```
User-agent: *
Allow: /

Sitemap: https://EXAMPLE.com/sitemap.xml

# Block all AI scrapers (per decisions.md: marketing policy)
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /
```

Note: regular search engine crawlers (Googlebot, Bingbot) are not in the AI bot list and remain governed by the `User-agent: *` rule.

---

## llms.txt

Per llmstxt.org spec. Place at root.

```
# Project Name

> One-line description of the project, written for an LLM consumer.

Markdown paragraph giving more context on what the project does, who it's for, and why it exists.

## Docs

- [Getting started](https://example.com/docs/getting-started): how to install and run the first example
- [API reference](https://example.com/docs/api): full API documentation
- [Examples](https://example.com/docs/examples): working code samples

## Optional

- [Changelog](https://example.com/changelog): version history
- [Contributing](https://github.com/owner/repo/blob/main/CONTRIBUTING.md): how to contribute
```

For richer LLM consumption, also publish `llms-full.txt` with the full content of all documentation pages concatenated.

---

## manifest.json

Minimum modern PWA manifest. Place at root or `/manifest.json`.

```json
{
  "name": "Site Full Name",
  "short_name": "Site",
  "description": "One-line description matching meta description.",
  "start_url": "/",
  "display": "standalone",
  "background_color": "#ffffff",
  "theme_color": "#000000",
  "icons": [
    {
      "src": "/web-app-manifest-192x192.png",
      "sizes": "192x192",
      "type": "image/png",
      "purpose": "maskable"
    },
    {
      "src": "/web-app-manifest-512x512.png",
      "sizes": "512x512",
      "type": "image/png",
      "purpose": "maskable"
    },
    {
      "src": "/web-app-manifest-192x192.png",
      "sizes": "192x192",
      "type": "image/png",
      "purpose": "any"
    },
    {
      "src": "/web-app-manifest-512x512.png",
      "sizes": "512x512",
      "

references/weekly-seo-agent.md

# Weekly SEO maintenance sub-agent

Definition for a scheduled background agent — a subagent or custom agent on any harness (see "Agent definition file" below for the concrete equivalents), such as Hermes or Claude Cowork Routines — that runs weekly post-launch to monitor SEO health and surface action items.

## Setup

1. Copy the agent definition for your harness (see "Agent definition file" below) into the location that harness's block specifies, in the site's repo (or a dedicated ops repo if you manage multiple sites).
2. Confirm the following MCP servers (or equivalent API access) are connected:
- **Ahrefs MCP** (required, for backlinks and rankings)
- **PostHog MCP** (required, for traffic correlation)
- **Google Search Console** (recommended, via community MCP such as `gsc-mcp`; if no MCP, fall back to `curl` with a service account credential file)
- **Web search** (built-in on most harnesses, for SERP feature checks and competitor monitoring)
3. Confirm the agent has access to the project source code if they apply to the site's content.
4. Schedule weekly execution. Options:
- Cron running that harness's headless/non-interactive invocation (e.g. `claude --dangerously-skip-permissions -p "/agents weekly-seo"` on Claude Code, `copilot -p "/agent weekly-seo"` on Copilot CLI) — only in a trusted environment
- The harness's own scheduled/background-agent feature, where one exists (e.g. Claude Cowork, Hermes)
- GitHub Actions weekly schedule, posting the report to a Slack channel
- Manual invocation each Monday morning

When MCP servers are not available, fall back to a browser extension or headless browser where the harness supports one, or to direct API calls per the "MCP usage" section in each harness's block below.

## What the agent does

Run all 10 tasks below in one weekly pass. Each task produces a section of the final report.

### 1. Ranking changes (GSC + Ahrefs)

- Pull top 50 queries by impressions for the last 7 days from Google Search Console.
- Compare positions, impressions, clicks, and CTR to the prior 7 days.
- Flag any (page, query) pair that:
- Dropped more than 5 positions
- Lost more than 20% impressions
- Lost more than 30% clicks while position is stable (CTR collapse, often a SERP feature stealing clicks)
- Output: ordered list of (page, query, delta, hypothesis, recommended action).

### 2. Page-2 opportunities (GSC)

- Identify queries ranking positions 11 through 20 with more than 100 impressions in 7 days.
- For the top 5: fetch the current page 1 SERP via `web_search` and compare structure, depth, and recency of the top 3 results to the site's current content.
- Output: content gap analysis with specific edit suggestions (add FAQ section, expand introduction, add benchmark table, etc.).

### 3. New backlinks (Ahrefs MCP)

- Pull new referring domains acquired in the last 7 days.
- Categorize each: high authority (DR > 50), niche relevant (matches site topic), neutral, spam.
- Flag spam

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.