granola-migration-deep-dive
Migrate to Granola from Otter.ai, Fireflies, Fathom, tl;dv, or manual note-taking. Covers data export from source tools, parallel-run strategy, team transition, and historical data preservation. Trigger: "migrate to granola", "switch to granola", "granola from otter", "granola from fireflies", "replace meeting tool with granola".
72
67%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/granola-pack/skills/granola-migration-deep-dive/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines a narrow, specific use case—migrating to Granola from competing meeting note tools. It names concrete actions (data export, parallel-run strategy, team transition, historical data preservation), lists specific competing tools by name, and provides explicit trigger phrases that users would naturally use. The description is concise, well-structured, and uses appropriate third-person voice.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: data export from source tools, parallel-run strategy, team transition, and historical data preservation. These are clear, actionable migration steps rather than vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (migrate to Granola covering data export, parallel-run strategy, team transition, historical data preservation) and 'when' (explicit trigger phrases provided). The trigger section serves as an explicit 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Includes highly natural trigger phrases users would actually say: 'migrate to granola', 'switch to granola', 'granola from otter', 'granola from fireflies', 'replace meeting tool with granola'. Also names specific competing tools (Otter.ai, Fireflies, Fathom, tl;dv) which users would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Extremely specific niche: migration to one particular tool (Granola) from named competitors. The combination of specific product names and migration-focused language makes it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive but overly verbose migration guide that tries to cover too much in a single file. While the step-by-step structure and checklists provide reasonable workflow guidance, the content is padded with templates, comparison tables, and explanations that Claude could generate contextually. The actionability is moderate — export instructions are surface-level and the archival script contains a bug.
Suggestions
Cut the content by 50%+: remove the comparison tables, email templates, and the Python script — Claude can generate these on demand. Focus on the non-obvious specifics (exact export paths, known limitations, gotchas).
Add explicit validation checkpoints: after export, verify file counts match expected totals; after archival, confirm all files were moved; after cutover, define specific success criteria (e.g., '95% capture rate over 3 days').
Fix the Python script bug: the catch-all branch tries `(ARCHIVE_DIR / 'general' / file.name).rename(file)` which reverses source and destination, and the file was already not placed so this will fail.
Split source-specific export details into a separate reference file to keep the main SKILL.md as a concise workflow overview with pointers to details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~200+ lines. It explains obvious concepts (what a parallel run is, what export formats are), includes lengthy template emails, comparison tables that Claude could generate on the fly, and a Python script for a trivial file-sorting task. Much of this content doesn't add value beyond what Claude already knows about migration planning. | 1 / 3 |
Actionability | The skill provides some concrete guidance (source-specific export paths, a Python archival script, checklist items) but much of it is fill-in-the-blank templates and comparison tables rather than executable instructions. The export steps are vague ('Settings > Export > Download All') without verifiable specifics, and the Python script has a bug (the catch-all rename logic is incorrect). | 2 / 3 |
Workflow Clarity | The 7-step sequence is clearly laid out with checklists and a logical progression. However, validation checkpoints are weak — there's no explicit verification that exports are complete before proceeding, no feedback loop for the archival step, and the parallel run comparison is a blank template rather than actionable validation criteria. The cutover checklist is good but lacks rollback guidance. | 2 / 3 |
Progressive Disclosure | The skill references other skills (granola-install-auth, granola-core-workflow-a, granola-performance-tuning) which is good, but the main document is monolithic with inline content that could be split (e.g., source-specific export details, the Python script, the comparison table). No bundle files are provided to offload this content, and the document tries to cover everything in one long file. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.