checkout-friction-finder-ecommerce
Audits e-commerce cart and checkout flows from screenshots, funnel exports, policies, and support notes to find likely friction points.
Skill by mardab96
Chalk Labs
Need help deploying checkout-friction-finder-ecommerce?
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/mardab96-checkout-friction-finder-ecommerce
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: productivity
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/checkout-friction-finder-ecommerce
What's inside
- Skill name
checkout-friction-finder-ecommerce- Description
- Audits e-commerce cart and checkout flows from screenshots, funnel exports, policies, and support notes to find likely friction points. Use when cart abandonment is high, checkout conversion is weak, customers complain about checkout, or the user wants a pre-scale checkout review.
- License
- MIT
- Instructions
- 113 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Checkout Friction Finder - E-commerce ## Use this skill when The user wants to find likely reasons shoppers add to cart but do not complete purchase. Common requests: - "Audit this checkout before we scale traffic." - "Why are people abandoning checkout?" - "Review our cart and checkout friction." - "Find the biggest checkout fixes from these screenshots." ## Required input Minimum useful input: - Store type and category. - Cart screenshots. - Checkout screenshots across mobile and desktop if available. - Shipping, tax, payment, return, and account-creation rules. - Checkout funnel metrics if available. Optional: - Support questions about shipping, payment, discount codes, delivery, and returns. - Session recording notes. - Competitor checkout examples. ## Before analysis 1. Confirm whether the goal is conversion rate, AOV, lower support load, or checkout trust. 2. Ask whether the checkout can be edited or is locked by the platform. 3. Treat screenshots as evidence of friction, not proof of conversion loss. 4. Separate checkout friction from upstream product page or offer issues. ## Analysis workflow 1. Map the checkout path step by step. 2. Check for: - unexpected total cost - late shipping/tax disclosure - unclear delivery timing - forced account creation - weak trust signals - missing payment methods - discount-code confusion - mobile form friction - returns uncertainty - unclear error states 3. Rank issues by buyer impact and implementation difficulty. 4. Identify which issues need analytics validation. 5. Recommend the smallest testable fix first. ## Decision and evidence standard Every finding should include: - Evidence tag: `export`, `screenshot`, `url`, `review_cluster`, `support_ticket`, `return_reason`, `policy`, `feed_diagnostics`, `margin_csv`, `inventory_export`, `hypothesis`, or `needs_data`. - Severity: low, medium, high, or critical. - Confidence: low, medium, or high. - Business impact: revenue, margin, cashflow, retention, conversion, support_load, or risk. - Effort: XS, S, M, or L. - Owner decision: do_now, test, investigate, monitor, ignore, or approval_needed. If the evidence is weak, mark the finding as `hypothesis` or `needs_data` and lower confidence. ## Output format ### Checkout verdict Short summary with confidence: high / medium / low. ### Ranked friction table | Rank | Friction point | Evidence | Buyer risk | Fix | Effort | Measurement | |---|---|---|---|---|---|---| ### Quick fixes 3-5 fixes that can be reviewed or shipped quickly. ### Missing data List the data needed to improve confidence. ## Example input and output Input: - mobile cart screenshot - checkout step screenshots - shipping policy - support questions about delivery cost and delivery time Good output excerpt: | Finding | Evidence | Severity | Confidence | Business impact | Effort | Owner decision | |---|---|---|---|---|---|---| | Shipping cost appears only after contact details | `screenshot`, `policy` | high | high | conversion/support_load | S | do_now | | Delivery timing is unclear before payment step | `screenshot`, `support_ticket` | medium | medium | conversion | S | test | What not to do yet: promise conversion lift or redesign checkout without checking whether the platform allows the change. ## Guardrails - Do not promise conversion lift. - Do not recommend discounts unless price or shipping cost friction is evidenced. - Do not tell the user to change live checkout settings without approval. - Do not ignore mobile checkout. - Do not treat best practices as stronger than the store's actual data.
From mardab96/ecommerce-claude-skills, MIT.
Signals
- Stars
- 7
- Forks
- 3
- Open issues
- 0
- Last commit (this folder)
- Jun 1, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
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 checkout-friction-finder-ecommerce 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
checkout-friction-finder-ecommerce skill. Agent Mart. https://agentmart.dev/skills/mardab96-checkout-friction-finder-ecommerce (last updated 2026-10-24)