Grow logo

Grow

Community
Houseofmvps
grow

Post-Ship Growth Intelligence — track how your shipped product is performing. Use when user wants to check growth metrics, SEO trajectory, uptime, deploy frequency, or overall project health over time.

Overview

PublisherHouseofmvps
Repositoryultraship
Skill namegrow
Stars
122
Forks
14
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Houseofmvps on GitHub. Read the source before you install it.

Installation

Install the Grow AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Houseofmvps/ultraship.git /tmp/ultraship
mkdir -p .claude/skills
cp -r /tmp/ultraship/skills/grow .claude/skills/grow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Grow in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Grow on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Grow is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Post-Ship Growth Intelligence

Most indie builders ship and forget. The ones who win ship and measure. This skill makes growth visible, trackable, and actionable — like having a growth-stage CTO and a marketing analyst looking at your dashboards every week.

Process

Phase 1: Collect Metrics

bash
node ${CLAUDE_PLUGIN_ROOT}/tools/growth-tracker.mjs <project-directory> --url=<production-url> --save

Parse the JSON output for current snapshot and historical trends.

Phase 2: Growth Dashboard

Present a clear growth report:

Uptime & Performance:

  • Current status (up/down/degraded)
  • Response time trend (faster? slower?)
  • Compare to previous snapshot
  • Context: response time under 500ms is good, under 200ms is excellent, over 1s is a problem

Development Velocity:

  • Commits this week vs last week
  • Deploy frequency (30-day trend)
  • Active development days
  • Lines added vs removed (net growth)
  • Context: healthy velocity for a solo founder is 3-5 deploys/week. Less than 1 deploy/week means either the project is stable or stalling — check which.

SEO + AI visibility Trajectory:

  • Current SEO + AI visibility scores
  • Change since last check
  • Trend direction (improving/declining/stable)
  • Context: SEO score above 80 is solid, GEO above 70 means AI search engines can find and cite you, below 50 means you're invisible to AI search

Dependency Health:

  • Outdated packages count
  • Security vulnerabilities
  • Action needed?

Code Health:

  • Quality score trend
  • Improving or declining?

Phase 3: Growth Insights

Based on the data, provide strategic insights — not just metrics, but what they mean:

1. What's going well — metrics that are improving 2. What needs attention — metrics that are declining or stagnant 3. Benchmarks — how these metrics compare to typical indie SaaS projects:

MetricBelow AverageAverageGoodExcellent
Response time>1s500ms-1s200-500ms<200ms
Deploy frequency<1/week1-2/week3-5/weekDaily
SEO score<5050-7070-8585+
GEO score<4040-6060-8080+
Vulnerabilities>5 high1-5 high0 high0 total

4. The "One Thing" recommendation — if you could only do one thing this week to improve growth, what is it? Prioritize ruthlessly. Solo founders don't have time for 15 action items.

Phase 4: SEO Deep Dive (if GSC credentials available)

bash
node ${CLAUDE_PLUGIN_ROOT}/tools/gsc-client.mjs query <site-url> 28

Show:

  • Top keywords you rank for
  • Ranking changes (up/down movers)
  • New keywords discovered
  • Click-through rates
  • Strategic analysis: Which keywords are worth doubling down on? Which are vanity metrics?

Content gap identification:

  • Keywords you rank 5-20 for (striking distance — could reach page 1 with targeted content)
  • Keywords competitors rank for that you don't (use with /compete data)
  • Long-tail keywords with low competition but high intent

Phase 5: Bing Indexing Status (if Bing key available)

bash
node ${CLAUDE_PLUGIN_ROOT}/tools/bing-webmaster.mjs url-info <site-url> <page-url>

Show indexing status across Bing (which also powers ChatGPT Search and DuckDuckGo).

Why this matters for AI search: If Bing hasn't indexed your pages, ChatGPT Search can't find you. Submit your sitemap to Bing and verify key pages are indexed.

Phase 6: Growth Strategy by Stage

Tailor recommendations to where the product is:

Pre-launch (0 users):

  • Focus: landing page SEO, GEO readiness, community building
  • Key metric: email signups, waitlist size
  • Action: build in public, share progress, collect early feedback

Post-launch (1-100 users):

  • Focus: activation rate, first-week retention, user feedback loops
  • Key metric: signup → activation conversion rate
  • Action: talk to every user, fix the top 3 onboarding friction points

Growth (100-1000 users):

  • Focus: organic acquisition, content marketing, SEO compounding
  • Key metric: organic traffic growth rate, MRR
  • Action: publish 2-4 SEO-optimized articles/month, build referral loops

Scale (1000+ users):

  • Focus: retention, expansion revenue, operational efficiency
  • Key metric: net revenue retention, churn rate, LTV/CAC
  • Action: automate onboarding, build self-serve, reduce support load

Phase 7: Action Items

Generate a prioritized list:

  1. Quick wins — things you can do today (15 min or less)
  2. This week — improvements that take a few hours
  3. This month — strategic investments for long-term growth

Phase 8: Weekly Digest Format

If the user wants a recurring check, format as a weekly digest:

Weekly Growth Report — [Project Name]
Week of [date]

Uptime: 99.9% | Avg Response: 230ms (-15ms)
SEO: 85 (+3) | GEO: 72 (+2) | AEO: 68 (+5)
Commits: 15 | Deploys: 3 | Active Days: 5
Vulnerabilities: 0 critical, 1 high

Top Action: Update 3 outdated dependencies

Trend: Improving (3 consecutive weeks of SEO gains)

Key Principles

  • What gets measured gets improved. Run this weekly. Growth is invisible without data.
  • One thing at a time. Solo founders can't do 15 things. Recommend the highest-impact single action.
  • Compounding beats spikes. A 2% weekly improvement in SEO score compounds to 180% over a year. Consistency wins.
  • GEO is the new SEO. In 2026, AI search visibility is as important as Google ranking. Track both.

Frequently asked questions

What does the Grow AI skill do?

Post-Ship Growth Intelligence — track how your shipped product is performing. Use when user wants to check growth metrics, SEO trajectory, uptime, deploy frequency, or overall project health over time.

Why use Grow on TypingMind?

Because you install it once and use it with any model. Grow is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Grow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Houseofmvps/ultraship/tree/main/skills/grow. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Grow?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Grow?

As many as you like. As long as a model supports skills, you can use Grow with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Grow AI skill free?

Yes. It is published on GitHub by Houseofmvps under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇