🧰 MOQ Price Tier Normalize
Turns messy MOQ and price-ladder text from a supplier quote into a clean tier table, flags gaps and inconsistencies, and never invents missing prices.
What it does
Paste the MOQ and price-break wording from a supplier quote (often scattered across emails, WeChat messages or a PDF). The skill rebuilds a single tier table (qty from / qty to / unit price / currency / notes), then lists gaps, overlapping ranges and math that doesn’t add up.
Use it when: a factory sends “1000pcs $1.2, 3000pcs $1.05, bigger order talk” and you need a clean ladder before comparing quotes.
Works with: Claude Code, Claude.ai (Skills upload), Cursor and Codex. Install the ZIP, then ask your agent to normalize the MOQ tiers from the quote text.
It only uses the numbers you give it. It will not invent a missing tier or fill a blank price.
Output preview
Install
Unzip first. You get a folder named moq-price-tier-normalize containing SKILL.md.
Claude Code
Put the folder in your personal skills directory, or in the project to share it with your team.
~/.claude/skills/moq-price-tier-normalize/SKILL.md.claude/skills/moq-price-tier-normalize/SKILL.mdClaude Code picks up new skills in the current session (run /reload-skills if the skills folder didn't exist when the session started). The skill loads when a task matches its description.
Claude.ai
Turn on code execution (Settings → Capabilities), then go to Customize → Skills, click +, then Create skill → Upload a skill, and select the ZIP. Full guide.
Cursor
Put the folder in your user or project skills directory. Cursor also reads .claude/skills.
~/.cursor/skills/moq-price-tier-normalize/SKILL.md.cursor/skills/moq-price-tier-normalize/SKILL.mdCodex
Put the folder in your user or repository skills directory, then restart Codex or run /skills to check it is listed.
~/.agents/skills/moq-price-tier-normalize/SKILL.md.agents/skills/moq-price-tier-normalize/SKILL.mdThese are the standard skill locations for each tool. The tools a skill is verified on are listed under “Tested on” above, if any.
Test log
| Date (UTC) | Tool | Model | Run | Result | Checks | Tokens in / out |
|---|---|---|---|---|---|---|
| Nov 3, 2026 | Codex | gpt-5.4-mini | Test | Failed | 1/4
| 0 / 0 |
Each row is a real run recorded by our test runner. For each tool, the latest test run decides whether it appears under “Tested on”. Baseline runs do the same task with no skill installed and never count.