Agent skill

Compete

by Houseofmvps in Houseofmvps/ultraship

Competitive X-Ray — analyze any competitor URL vs your site.

MITAuto-check: notesMarketing & SEO

Install Compete

skills CLI
$ npx skills add Houseofmvps/ultraship --skill compete -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Houseofmvps/ultraship compete --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Houseofmvps/ultraship.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/compete .claude/skills/compete && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
compete
GitHub stars
123
Token cost
~1.1k tokens
SKILL.md length
592 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

Competitive X-Ray — analyze any competitor URL vs your site.

  • Works in 6 steps: Gather URLs → Run Analysis → Present Comparison → …
  • User wants to compare their site against a competitor
  • SKILL.md covers Process and Key Principles
  • Calls node

What it does

Compete is an agent skill from Houseofmvps/ultraship. Competitive X-Ray — analyze any competitor URL vs your site. Use when user wants to compare their site against a competitor, benchmark performance, or understand competitive positioning.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Positioning and messaging and AI search optimization. The repository describes itself as: "ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness… The licence is MIT.

When your agent uses it

  • User wants to compare their site against a competitor
  • Benchmark performance
  • Understand competitive positioning

Example prompts

  • “/compete”

Requirements

  • Pre-approved tools (allowed-tools): Bash, Read, Grep, Glob

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Gather URLs
  2. Run Analysis
  3. Present Comparison
  4. Strategic Analysis
  5. Comparison Card
  6. Action Items

What it can do on your machine

Read from SKILL.md and the folder at commit ed232cb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Grep
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Compete loads about 1.1k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 592 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Grep, Glob

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Houseofmvps/ultraship at commit ed232cb, republished under its MIT licence (© Houseofmvps). 592 words, ~1,136 tokens.

Download SKILL.mdSave it as .claude/skills/compete/SKILL.md (or your agent's skills folder).
name
compete
description
Competitive X-Ray — analyze any competitor URL vs your site. Use when user wants to compare their site against a competitor, benchmark performance, or understand competitive positioning.
allowed-tools
Bash, Read, Grep, Glob
argument-hint
<competitor-url>

Competitive X-Ray

Know what you're up against. Understand where you win, where you lose, and where the gaps are. This isn't just a technical comparison — it's a strategic assessment.

Process

Phase 1: Gather URLs

Ask the user for:

  1. Your site URL (production URL)
  2. Competitor URL (the site to compare against)

If the user provided both URLs already, skip asking.

Phase 2: Run Analysis
bash
node ${CLAUDE_PLUGIN_ROOT}/tools/compete-analyzer.mjs <your-url> <competitor-url>

Parse the JSON output.

Phase 3: Present Comparison

Present results in a clear head-to-head format:

Performance:

  • Response time comparison (who's faster, by how much)
  • Content size comparison
  • What the speed difference means for user experience and SEO

Tech Stack:

  • What each site is built with (framework, hosting, analytics, payments)
  • What their tech choices reveal about their stage and priorities
  • Overlap and differences

SEO:

  • Score comparison (out of 10)
  • Specific wins/losses (who has better meta tags, OG tags, sitemap, etc.)
  • GEO readiness comparison (llms.txt, AI-friendly robots.txt, structured data)
  • AEO readiness comparison (FAQPage schema, answer formatting)

Security:

  • Header comparison
  • HTTPS status
  • What missing headers reveal about their security posture
Phase 4: Strategic Analysis

Go beyond raw data. A principal-level competitive analysis answers:

1. Moat Assessment

  • What is their defensible advantage? (network effects, data, integrations, brand, switching costs)
  • What is YOUR defensible advantage?
  • Which moat is stronger, and what would it take to erode theirs?

2. Positioning Gap Analysis

  • What market segment are they targeting? (enterprise, SMB, developer, consumer)
  • Is there an underserved segment between you? (e.g., they target enterprise, you target solo founders — is there an SMB gap?)
  • Where do they over-serve (features their users don't need) or under-serve (features their users wish they had)?

3. Pricing & Value Perception

  • If pricing is visible, compare positioning: are they premium or budget? Is there room above, below, or between?
  • What does their pricing structure tell you? (per-seat = team play, usage-based = API/developer, flat = SMB simplicity)

4. Technical Debt Signals

  • Slow response time = legacy stack or unoptimized infrastructure
  • Missing security headers = early stage or no security focus
  • No structured data = SEO is an afterthought
  • Heavy bundle = frontend debt accumulating
  • These are exploitable advantages if you're faster, more secure, or more SEO-optimized

5. Your Advantages — where you're ahead, how to maintain and widen the lead 6. Their Advantages — where they beat you, how to close the gap 7. Quick Wins — low-effort improvements that would flip a loss into a win

Show full SKILL.md (204 more words)Show less
Phase 5: Comparison Card

Display the ASCII comparison card from the tool output. This is designed to be screenshot-shareable on Twitter/X.

Suggest the user share it with context like: "Ran a competitive analysis of [my product] vs [competitor]. Here's what the data shows:" — factual, not adversarial.

Phase 6: Action Items

Create a prioritized action plan:

This week (quick wins):

  • Technical gaps you can close in hours (add missing headers, optimize images, fix meta tags)
  • Low-effort improvements that flip a score

This month (strategic):

  • Feature or content gaps that require development work
  • SEO + AI visibility improvements that compound over time

This quarter (moat building):

  • Structural advantages to invest in (integrations, community, content library)
  • Things that get harder to replicate the earlier you start

Key Principles

  • Know thy enemy. This isn't about scores — it's about understanding what a competitor prioritizes and finding your unfair advantage.
  • Compete on strengths, not weaknesses. Don't try to match every feature — find where you win and amplify it.
  • Data over opinion. Every recommendation should be backed by the comparison data. No "I feel like you should" — only "the data shows X, so do Y."
  • Share the card. The comparison card is designed for virality. Factual competitive analysis gets engagement on Twitter.

© Houseofmvps, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/compete of Houseofmvps/ultraship.

Open the folder on GitHubat commit ed232cb

Compare with similar skills

Compete next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Compete compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Compete this skillHouseofmvps/ultraship123—~1.1kAutomated safety check: NotesMIT
Marketing OsYuzzyuk/marketing-os536—~2.5kAutomated safety check: PassMIT
Research Brandonvoyage-ai/gtm-engineer-skills1.3k—~1.3kAutomated safety check: PassMIT
Icp Evidence Analysiselvisun/newsjack1.5k—~1.4kAutomated safety check: PassMIT
Position MeVarnan-Tech/opendirectory674—~1kAutomated safety check: PassMIT
SEO Geoeunomia-bpf/eunomia.dev236—~2.1kAutomated safety check: PassMIT

Similar skills

  • Marketing Os

    Yuzzyuk/marketing-os

    A complete marketing department in one skill. An agent skill from Yuzzyuk/marketing-os.

    536 GitHub stars~2.5k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Research Brand

    onvoyage-ai/gtm-engineer-skills

    Researches a company from its URL and produces a Brand DNA file covering positioning, audience, competitors, voice, and messaging.

    1.3k GitHub stars~1.3k tokensUpdated 4 mo ago
    Marketing & SEOAuto-check passed
  • Icp Evidence Analysis

    elvisun/newsjack

    Turn a source-bound company and market dossier into testable ideal-customer-profile hypotheses, buying roles, triggers, constraints, disqualifiers, standing, counterevidence, and research gaps.

    1.5k GitHub stars~1.4k tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Position Me

    Varnan-Tech/opendirectory

    Elite Website Reviewer Agent for AEO, GEO, SEO, UI/UX Psychology, and Copywriting.

    674 GitHub stars~1k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • SEO Geo

    eunomia-bpf/eunomia.dev

    Technical-only page-level and site-level SEO/GEO checklist for eunomia.dev content.

    236 GitHub stars~2.1k tokensUpdated today
    Marketing & SEOAuto-check passed
  • Narrative Tracker

    indranilbanerjee/digital-marketing-pro

    Track what AI engines (ChatGPT, Perplexity, Gemini, AI Overviews, Copilot) say about the brand, score responses against desired positioning, and flag misrepresentations, drift, and competitor…

    855 GitHub starsUsed in 1 repo~2.3k tokens
    Marketing & SEOAuto-check passed

More from Houseofmvps/ultraship

All 28 skills in this repo
  • Using Ultraship

    Houseofmvps/ultraship

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    123 GitHub stars~2.2k tokensUpdated 3 mo ago
    Auto-check passed
  • A11y

    Houseofmvps/ultraship

    Accessibility audit + auto-fix (WCAG 2.2 A/AA). An agent skill from Houseofmvps/ultraship.

    123 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check: notes
  • Architecture

    Houseofmvps/ultraship

    Living Architecture Map — auto-generate Mermaid diagrams of your codebase.

    123 GitHub stars~708 tokensUpdated 3 mo ago
    Auto-check: notes
  • Clone Patterns

    Houseofmvps/ultraship

    Learn From the Best — analyze patterns from any codebase and apply them to yours.

    123 GitHub stars~682 tokensUpdated 3 mo ago
    Auto-check: notes
  • Code Review

    Houseofmvps/ultraship

    Code review with principal-engineer-level depth. An agent skill from Houseofmvps/ultraship.

    123 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Cost

    Houseofmvps/ultraship

    AI Build Cost Tracker — track how much AI is costing you per feature.

    123 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check: notes

Categories

Questions about Compete

What does Compete do?

Competitive X-Ray — analyze any competitor URL vs your site. Compete is an agent skill from Houseofmvps/ultraship. Competitive X-Ray — analyze any competitor URL vs your site.

When should I use Compete?

Compete fits situations like: user wants to compare their site against a competitor; benchmark performance; understand competitive positioning.

How do I install Compete in Claude Code?

Run `npx skills add Houseofmvps/ultraship --skill compete -a claude-code`. Or copy the skill folder (skills/compete in Houseofmvps/ultraship) into .claude/skills/compete in your project. Claude Code loads it when a task matches its description.

How do I install Compete in Codex?

Run `npx skills add Houseofmvps/ultraship --skill compete -a codex`. Or copy the skill folder (skills/compete in Houseofmvps/ultraship) into .agents/skills/compete in your project. Codex loads it when a task matches its description.

Can I use Compete in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Houseofmvps/ultraship --skill compete -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/compete, .gemini/skills/compete, .github/skills/compete and .opencode/skills/compete in your project.

What does Compete need to run?

Going by SKILL.md and its folder, Compete needs the command-line tools its instructions call (node). Its frontmatter pre-approves these tools: Bash, Read, Grep, Glob.

Does Compete access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Compete safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Compete use?

Compete is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Compete use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Compete?

Skills that share tags, products or a category with Compete: Marketing Os (Yuzzyuk/marketing-os, 536 stars), Research Brand (onvoyage-ai/gtm-engineer-skills, 1.3k stars), Icp Evidence Analysis (elvisun/newsjack, 1.5k stars) and Position Me (Varnan-Tech/opendirectory, 674 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Compete?

Houseofmvps (a GitHub user) maintains it in Houseofmvps/ultraship, which has 123 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on July 8, 2026.

Source: Houseofmvps/ultraship on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.