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".

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete scripts, tables, and checklists across a well-sequenced migration workflow. Its main weaknesses are insufficient validation feedback loops around destructive operations and underused progressive disclosure that leaves the reference bundle unlinked while inlining content that belongs there.

Suggestions

Add an explicit verify-before-proceed checkpoint before Step 7's destructive account/data deletion (e.g., confirm archive completeness and 30-day stability before deletion) to satisfy the destructive-operations feedback-loop requirement.

Link references/implementation.md from the body (e.g., 'See implementation.md for conversion scripts, execution plan, and rollback') and move the inline archive Python script and announcement email template into that reference to reduce inline bulk.

Trim explanatory material Claude already knows, such as the bot-based-vs-system-audio comparison, keeping only Granola-specific guidance that is not obvious.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable, but it explains concepts Claude already knows (the bot-vs-system-audio differences) and inline-embeds the archive Python script and a full announcement email template that belong in references, so it could be tightened.	2 / 3
Actionability	It provides concrete, copy-paste-ready guidance: per-tool export menu paths, an executable Python archive script with real imports and paths, comparison tables, and a cutover checklist.	3 / 3
Workflow Clarity	The 7-step sequence is clear with checkpoints (parallel-run comparison, cutover checklist, 3-day monitoring), but destructive/batch operations like the file-moving archive script and Step 7's 'Delete source tool accounts and data' lack explicit validate-then-proceed feedback loops, so the rubric caps it at 2.	2 / 3
Progressive Disclosure	A references/implementation.md bundle exists with conversion scripts, execution plan, and rollback plan, but the body never links to it and instead inline-embeds content (archive script, announcement template) that should live in the reference; structure is present but not cleanly signaled.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, well-triggered, and complete, clearly stating both capabilities and when to use the skill. It is concise without fluff and uses third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('data export from source tools, parallel-run strategy, team transition, and historical data preservation') and enumerates specific source tools (Otter.ai, Fireflies, Fathom, tl;dv), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly answers both 'what' (migrate from named tools covering export, parallel-run, team transition, historical preservation) and 'when' via an explicit 'Trigger:' clause, matching the top anchor.	3 / 3
Trigger Term Quality	Explicit trigger phrases like 'migrate to granola', 'switch to granola', and 'replace meeting tool with granola' are natural terms a user would actually say, giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The narrow niche (Granola migration from specific named competitors) with distinct Granola-specific triggers makes it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/granola-pack/skills/granola-migration-deep-dive/SKILL.md
Commit: 4c47e33

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.