What do I need to use Importer Scaffolder?

A sample export; The source tool; Your data model; Your language and stack; Where unmatched data should go.

Is Importer Scaffolder free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Importer Scaffolder

Q: How do I know the Importer Scaffolder output is good?

The skill verifies itself against its own quality checks: Every source field in the sample appears in the mapping table; The code imports invalid records with a flag instead of dropping them; Unmapped fields are preserved in the named extras destination; Re-running the import on the same file creates no duplicates.

🔵 Stable🕐 updated 2026-10-04 ✅ 4.8/5 🔷 SkillSpec L3 pm-oss-launch

Use when asked to build an importer from a competitor's export, migrate users' data from another tool, map a CSV or JSON export onto my data model, or make switching to my project easy. Given a sample export (CSV or JSON), produces a field mapping table, an importer code skeleton, a rule that unmatched records are kept rather than dropped, and test fixtures including the awkward cases. For a database migration inside one system, use database-migration-plan.

▶ Run it free — no key needed 📝 Grade your existing draft 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“Build an importer for Trello JSON exports into my app.”“Here's a CSV export from Notion, map it onto my data model.”“Make it easy for users to switch from [competitor] to my project.”“Write a CSV importer that never drops rows.”

What to give it

▸A sample export — a few rows of CSV or a JSON excerpt, with any personal data replaced

▸The source tool — and how users produce the export

▸Your data model — the target fields, types and required fields

▸Your language and stack — for the importer

▸Where unmatched data should go — a notes field, an extras column, or a separate file

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Every source field in the sample appears in the mapping table

✓The code imports invalid records with a flag instead of dropping them

✓Unmapped fields are preserved in the named extras destination

✓Re-running the import on the same file creates no duplicates

✓A dry-run mode exists and writes nothing

✓Fixtures cover non-ASCII text, a malformed date and a duplicate row

✓The sample data contains no real personal data

⚠️ What it refuses to do

**Silent drops.** A skipped row is lost data the user may never notice.

**Mapping by column position.** Exports reorder columns; map by header name.

**Loading the whole file into memory.** Real exports are bigger than samples.

**Guessing ambiguous dates.** If 03/04 could be either order, ask or detect from the whole file, and record the choice.

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="importer-scaffolder"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Importer Scaffolder is one of 1307 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog