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".
83
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 highly distinguishable from other skills.
| 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
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured migration guide with a clear 7-step workflow and good validation checkpoints (parallel run, cutover checklist, post-migration monitoring). Its main weaknesses are verbosity — too much content inline that could be referenced or trimmed — and some actionability gaps where instructions are templates rather than executable guidance. The Python script is a nice touch but contains a bug, and source-specific export instructions lack verification steps.
Suggestions
Fix the Python archival script bug (the catch-all branch tries to rename the destination path instead of the source file) and add a verification step that counts archived files vs. source files.
Move the source-specific export details and the bot-vs-Granola comparison table into a referenced file (e.g., MIGRATION-SOURCES.md) to reduce the main skill's token footprint.
Add verification commands or checks after the export step (e.g., 'Verify export: count files, spot-check 3 random transcripts for completeness') since this is a data migration with potential for data loss.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity — the overview paragraph restates what the YAML description already covers, the comparison table at the end rehashes information Claude likely knows, and some sections (like the team announcement email template) are padded. The migration assessment template and parallel run comparison tables add useful structure but could be tighter. | 2 / 3 |
Actionability | The skill provides concrete checklists, a working Python script for archival, and specific export paths per tool. However, much of the guidance is fill-in-the-blank templates rather than executable steps, the source-specific export instructions are surface-level (e.g., 'Admin > Data Management > Export' without verification), and the Python script has a bug (the catch-all rename is inverted). It's a mix of concrete and vague. | 2 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with logical progression from assessment through post-migration optimization. It includes explicit validation checkpoints (parallel run quality comparison, cutover day checklist with monitoring period, post-migration verification). The parallel run strategy with Week 1/Week 2 phasing provides a clear feedback loop before committing to cutover. | 3 / 3 |
Progressive Disclosure | The skill references other skills appropriately (granola-install-auth, granola-core-workflow-a, granola-performance-tuning) and includes external resource links. However, the content is quite long and monolithic — the source-specific export details, the comparison table, and the archival script could be split into referenced files. The inline email template and multiple large tables make the main file heavier than necessary. | 2 / 3 |
Total | 9 / 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
3e83543
- 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.