comparison-page-builder
Write a comparison or alternatives page that a reader trusts and a competitor cannot get taken down.
Skill by mambalabsdev
Chalk Labs
Need help deploying comparison-page-builder?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mambalabsdev-comparison-page-builder
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/comparison-page-builder
What's inside
- Skill name
comparison-page-builder- Description
- Write a comparison or alternatives page that a reader trusts and a competitor cannot get taken down. Use when someone needs a versus page, an alternatives page, or wants to rank for competitor comparison queries.
- License
- MIT
- Compatibility
- Claude Code, Claude Desktop, Codex CLI, Cursor, Gemini CLI, and other agents that read SKILL.md. Live data steps need only what the Requirements section of the skill lists.
- Metadata
- tags: seo_content, seo_content_engine · title: Comparison Page Builder · version: 2.1.0 · category: seo-content · keywords: seo and content, write a versus page, alternatives page, comparison content, rank for competitor queries, compare us to a competitor · requirements: Needs no account, key or paid service: it works from the files, exports and answers you give it.
- Instructions
- 87 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (8)
- LICENSE
- SKILL.md
- cases.json · evals/
- listing.json · listing/
- logo.png · listing/
- logo.svg · listing/
- check-output.py · scripts/
- output-contract.json · scripts/
SKILL.md (first lines)
# Comparison Page Builder ## What this does Comparison pages convert better than almost any other page type and they are the easiest to write badly, because the temptation is to win every row. A page that wins every row is not read as information. This skill writes comparisons where the competitor genuinely wins some rows, every claim is dated and sourced, and the recommendation is conditional on the reader's situation. ## Requirements This skill needs no account, API key or paid service. It works from the files, exports and answers you give it, in any agent that reads SKILL.md. ## When to use it - write a versus page - alternatives page - comparison content - rank for competitor queries - compare us to a competitor ## Inputs - **us**: your product with its real limits - **them**: the competitor and what they are genuinely good at - **reader**: who is searching this and what decision they are making ## Shared context this skill reads Before doing anything else, read whichever of these exist at the project root and use them instead of asking the user to repeat themselves: - `BRAND.md` - `ICP.md` If none exist, do the work from what the user gives you, then offer to write the missing file so the next skill in the pack starts warmer. ## Tool connection This skill needs no live data tool. It works from the files, exports and answers you give it, so it runs the same in any agent with no setup. ## Method 1. Build the comparison table from what the reader decides on, not from your feature list. Features you have and they do not are only relevant if the reader cares. 2. Give the competitor the rows they win, plainly. A page where the competitor wins nothing is read as marketing and bounces. 3. Date and source every factual claim about the competitor. Pricing and features change and an out of date claim is both a trust problem and a legal one. 4. Do not compare against a competitor's deprecated behavior or a plan they no longer sell. 5. Write the conditional recommendation: who should pick them, and who should pick you. The first half is what makes the second half credible. 6. Add the migration or evaluation next step, because the reader on this page is close to a decision. 7. Set a review date on the page and put it in the content, since a comparison page is a maintenance commitment. 8. Check the output with `scripts/check-output.py` before you return it. ## Approval stop This skill does not send email or write to a CRM. If the user asks it to, stop first: show what would be sent or written and wait for an explicit yes. ## Output The comparison table with sources and dates, the honest wins on both sides, the conditional recommendation, the next step, and the review date. ## Check the output before you return it Save the output to a file and run `python3 scripts/check-output.py <file>`. The contract it checks is `scripts/output-contract.json`. - Exit 0, `COMPLETE`: return the output. - Exit 2, `INCOMPLETE`: do not present the output as finished. Fill what you can, run the check again, and if parts stay missing, return the output under the heading `Incomplete` with every reason the check printed. ## Quality bar - The competitor wins at least one row and it is a row readers care about - Every competitor claim carries a source and a date - The recommendation is conditional on the reader's situation - A review date appears in the published content ## Related skills - `programmatic-seo-planner` - `listing-page-optimizer` - `first-party-data-post` Ships in the **seo-content-engine** pack.
From mambalabsdev/mamba-labs-skills, MIT.
More from mambalabsdev/mamba-labs-skills
- 0.570score
agent-readability-audit
mambalabsdev
Check whether a website can be read and used by AI agents, and fix what blocks them.
SkillAFreshness: AClaude Code +9 - 0.570score
ai-adoption-signal-reader
mambalabsdev
Detect whether a company has shipped AI features or adopted AI vendors, and read that as a budget and priority signal.
SkillAFreshness: AClaude Code +9 - 0.570score
bounce-and-catchall-policy
mambalabsdev
Decide what to do with catch all domains, role addresses and soft bounces before they cost you a domain.
SkillAFreshness: AClaude Code +9 - 0.570score
cash-runway-snapshot
mambalabsdev
Work out how many months of cash are left and what actually changes it.
SkillAFreshness: AClaude Code +9 - 0.570score
clay-actor-column-wiring
mambalabsdev
Wire an external actor or API into a Clay column so the types survive the round trip.
SkillAFreshness: AClaude Code +9 - 0.570score
clay-conditional-gates
mambalabsdev
Write the run conditions that stop expensive Clay columns from firing on rows that will never qualify.
SkillAFreshness: AClaude Code +9 - 0.570score
clay-cost-audit
mambalabsdev
Price a Clay table before it runs and find the columns that are burning credits for no return.
SkillAFreshness: AClaude Code +9 - 0.570score
clay-credit-forecast
mambalabsdev
Forecast how far a Clay credit balance goes across a month of planned builds, and say which build to cut when it does not reach.
SkillAFreshness: AClaude Code +9 - 0.570score
clay-dedupe-and-merge
mambalabsdev
Deduplicate and merge people or company rows across Clay tables without losing enrichment or double counting a person.
SkillAFreshness: AClaude Code +9 - 0.570score
clay-failure-triage
mambalabsdev
Diagnose a Clay column that returns null, zero rows, or the wrong shape, by symptom rather than by guesswork.
SkillAFreshness: AClaude Code +9 - 0.570score
company-identity-resolution
mambalabsdev
Resolve a messy company name to the right domain and canonical record, and say how confident the match is.
SkillAFreshness: AClaude Code +9 - 0.570score
contact-classification
mambalabsdev
Classify contacts by department, seniority and role from their job title, and route them to the right persona.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 12, 2026 (18 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 2.1.0
- License
- MIT
- Website
- mambabuilt.com/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mambalabsdev
- 0.570score
ai-adoption-signal-reader
mambalabsdev
Detect whether a company has shipped AI features or adopted AI vendors, and read that as a budget and priority signal.
SkillAFreshness: AClaude Code +9 - 0.570score
bounce-and-catchall-policy
mambalabsdev
Decide what to do with catch all domains, role addresses and soft bounces before they cost you a domain.
SkillAFreshness: AClaude Code +9 - 0.570score
cash-runway-snapshot
mambalabsdev
Work out how many months of cash are left and what actually changes it.
SkillAFreshness: AClaude Code +9 - 0.570score
clay-actor-column-wiring
mambalabsdev
Wire an external actor or API into a Clay column so the types survive the round trip.
SkillAFreshness: AClaude Code +9 - 0.570score
clay-conditional-gates
mambalabsdev
Write the run conditions that stop expensive Clay columns from firing on rows that will never qualify.
SkillAFreshness: AClaude Code +9 - 0.570score
agent-readability-audit
mambalabsdev
Check whether a website can be read and used by AI agents, and fix what blocks them.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get comparison-page-builder running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
comparison-page-builder skill. Agent Mart. https://agentmart.dev/skills/mambalabsdev-comparison-page-builder (last updated 2026-10-24)