Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Deep dive into Evernote data migration strategies. Use when migrating to/from Evernote, bulk data transfers, or complex migration scenarios. Trigger with phrases like "migrate to evernote", "migrate from evernote", "evernote data transfer", "bulk evernote migration".
.claude/skills/jeremylongshore-evernote-migration-deep-dive/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 109% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 89% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 70% | 0% |
| case-20 | ✗→✓ | ▲ Improved | -2% | 0% |
!npm list 2>/dev/null | head -5
Comprehensive guide for migrating data to and from Evernote, including ENEX export/import, bulk API operations, format conversions (ENML to Markdown, HTML to ENML), and data integrity verification.
Assess the migration scope: count notes, notebooks, tags, and total resource size. Estimate API call count and quota consumption. Plan for rate limits (add delays between operations).
javascriptasync function assessMigration(noteStore) { const notebooks = await noteStore.listNotebooks(); const tags = await noteStore.listTags(); let totalNotes = 0; for (const nb of notebooks) { const filter = new Evernote.NoteStore.NoteFilter({ notebookGuid: nb.guid }); const spec = new Evernote.NoteStore.NotesMetadataResultSpec({}); const result = await noteStore.findNotesMetadata(filter, 0, 1, spec); totalNotes += result.totalNotes; } return { notebooks: notebooks.length, tags: tags.length, totalNotes, estimatedApiCalls: totalNotes * 2 + notebooks.length + tags.length, estimatedTimeMinutes: Math.ceil((totalNotes * 2 * 200) / 60000) // 200ms per call }; }
Export notes in three formats: ENEX (Evernote's XML format, preserves everything including resources), JSON (structured data for programmatic use), or Markdown (human-readable, loses some formatting).
javascriptasync function exportToMarkdown(noteStore, noteGuid) { const note = await noteStore.getNote(noteGuid, true, true, false, false); const text = enmlToMarkdown(note.content); return { title: note.title, content: text, tags: note.tagNames || [], created: new Date(note.created).toISOString(), resources: (note.resources || []).map(r => ({ filename: r.attributes.fileName, mime: r.mime, size: r.data.size })) }; }
Convert source data to ENML format, create notebooks to match source structure, and bulk-create notes with rate limit handling. Verify each import by comparing note counts and content hashes.
Build a migration runner with progress tracking, checkpointing (resume from failure), and verification. Log every operation for audit trail.
For the full migration planner, ENEX parser, format converters, migration runner, and verification tools, see Implementation Guide.
| Error | Cause | Solution | |-------|-------|----------| | QUOTA_REACHED | Upload quota exceeded during import | Wait for quota reset or upgrade account tier | | RATE_LIMIT_REACHED | Too many API calls during bulk migration | Increase delay between operations, use checkpointing | | BAD_DATA_FORMAT | Source content not valid ENML | Validate and sanitize content before import | | Lost resources | Attachments not migrated | Verify resource hashes match after migration |
Export all notes to Markdown: Iterate through all notebooks, export each note as a Markdown file with frontmatter (title, tags, date), save resources to assets/ directory, preserving notebook-as-folder structure.
Import from Notion: Parse Notion export (Markdown + CSV), convert to ENML, create matching notebooks, and bulk-import with checkpoint/resume for large exports (10,000+ pages).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 21,160 | 13,006 | -39% | 1 | 1 | 0% | 3,688 | 3,555 | -4% | 0 | 0 | — |
case-02 | fail→pass | 25,529 | 23,416 | -8% | 1 | 1 | 0% | 5,076 | 6,119 | +21% | 0 | 0 | — |
case-03 | pass→fail | 17,106 | 7,969 | -53% | 1 | 1 | 0% | 3,690 | 1,379 | -63% | 0 | 0 | — |
case-04 | pass→pass | 18,303 | 24,746 | +35% | 1 | 1 | 0% | 2,713 | 4,716 | +74% | 0 | 0 | — |
case-05 | pass→pass | 9,929 | 11,974 | +21% | 1 | 1 | 0% | 1,710 | 3,174 | +86% | 0 | 0 | — |
case-06 | pass→pass | 12,645 | 14,067 | +11% | 1 | 1 | 0% | 1,784 | 3,349 | +88% | 0 | 0 | — |
case-07 | fail→fail | 5,452 | 7,823 | +43% | 1 | 1 | 0% | 869 | 2,382 | +174% | 0 | 0 | — |
case-08 | pass→pass | 12,209 | 17,849 | +46% | 1 | 1 | 0% | 1,706 | 4,157 | +144% | 0 | 0 | — |
case-09 | pass→pass | 12,139 | 19,681 | +62% | 1 | 1 | 0% | 2,096 | 3,958 | +89% | 0 | 0 | — |
case-10 | pass→pass | 8,274 | 9,592 | +16% | 1 | 1 | 0% | 1,100 | 2,638 | +140% | 0 | 0 | — |
case-11 | pass→pass | 14,602 | 8,009 | -45% | 1 | 1 | 0% | 1,946 | 2,312 | +19% | 0 | 0 | — |
case-12 | fail→pass | 9,360 | 14,040 | +50% | 1 | 1 | 0% | 1,480 | 3,086 | +109% | 0 | 0 | — |
case-13 | pass→pass | 20,512 | 20,052 | -2% | 1 | 1 | 0% | 2,977 | 4,043 | +36% | 0 | 0 | — |
case-14 | pass→pass | 17,954 | 12,559 | -30% | 1 | 1 | 0% | 2,517 | 3,071 | +22% | 0 | 0 | — |
case-15 | fail→pass | 12,085 | 10,743 | -11% | 1 | 1 | 0% | 1,573 | 2,973 | +89% | 0 | 0 | — |
case-16 | pass→pass | 5,020 | 6,414 | +28% | 1 | 1 | 0% | 807 | 2,219 | +175% | 0 | 0 | — |
case-17 | fail→pass | 7,448 | 5,042 | -32% | 1 | 1 | 0% | 1,169 | 1,991 | +70% | 0 | 0 | — |
case-18 | pass→pass | 6,310 | 6,751 | +7% | 1 | 1 | 0% | 821 | 1,947 | +137% | 0 | 0 | — |
case-19 | pass→pass | 5,577 | 7,451 | +34% | 1 | 1 | 0% | 999 | 2,253 | +126% | 0 | 0 | — |
case-20 | fail→pass | 15,762 | 8,001 | -49% | 1 | 1 | 0% | 2,610 | 2,564 | -2% | 0 | 0 | — |
case-21 | pass→pass | 5,141 | 5,450 | +6% | 1 | 1 | 0% | 729 | 1,781 | +144% | 0 | 0 | — |
case-22 | pass→pass | 5,709 | 3,642 | -36% | 1 | 1 | 0% | 1,050 | 1,479 | +41% | 0 | 0 | — |
case-23 | pass→pass | 3,758 | 3,187 | -15% | 1 | 1 | 0% | 464 | 1,405 | +203% | 0 | 0 | — |
case-24 | pass→pass | 17,583 | 23,588 | +34% | 1 | 1 | 0% | 3,007 | 5,984 | +99% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted, and 23 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +17 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.