granola-data-handling
Manage Granola data export, retention policies, GDPR/CCPA compliance, and archival workflows. Handle Subject Access Requests and Right to Erasure. Trigger: "granola export", "granola data", "granola GDPR", "granola retention", "granola delete data", "granola compliance".
78
75%
Does it follow best practices?
Impact
Pending
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-data-handling/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 its scope around Granola-specific data governance tasks including export, retention, compliance, and erasure. It provides explicit trigger terms prefixed with 'Granola' to minimize conflict risk, and covers both what the skill does and when to use it. The description is concise, uses third-person voice, and avoids vague language.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: data export, retention policies, GDPR/CCPA compliance, archival workflows, Subject Access Requests, and Right to Erasure. These are distinct, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' (manage data export, retention policies, GDPR/CCPA compliance, archival workflows, SARs, Right to Erasure) and 'when' via an explicit 'Trigger:' clause listing specific trigger phrases. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms like 'granola export', 'granola data', 'granola GDPR', 'granola retention', 'granola delete data', 'granola compliance' — these cover the main variations a user would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The 'Granola' prefix on all trigger terms and the specific focus on data governance (GDPR, CCPA, retention, erasure) for a named product creates a very clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill covers a broad and important topic with reasonable structure and some concrete code examples, but suffers from trying to do too much in a single file. The compliance tables and procedural checklists are informative but often lack the executable specificity needed for a high-actionability score, and the absence of validation/verification steps in workflows involving data deletion and compliance reporting is a notable gap. Tightening the prose, adding verification checkpoints, and splitting detailed content into referenced sub-files would significantly improve quality.
Suggestions
Add explicit validation/verification steps after key operations — e.g., after the cache export script, verify the count matches expected notes; after configuring retention policies, verify they're applied correctly; after SAR completion, verify all data was captured.
Split the detailed Python export script, GDPR compliance tables, and archival workflow into separate referenced files (e.g., EXPORT.md, GDPR.md, ARCHIVAL.md) to keep the main SKILL.md as a concise overview with navigation.
Remove explanatory content Claude already knows (e.g., what transcripts contain, what calendar metadata is) and trim the data types table to just the non-obvious facts like 'audio is deleted after transcription'.
Make the retention policy configuration actionable — provide the actual UI path or API call to set retention periods, rather than just recommending values in a table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but is verbose in places — the data types table explains things Claude would know (what a transcript is), the prerequisites include vague items like 'understanding of applicable regulations,' and some sections like CCPA are thin enough to be bullet points within GDPR rather than a separate step. The local cache export script is appropriately detailed but the overall document could be tightened significantly. | 2 / 3 |
Actionability | The Python cache export script and bash backup command are executable and concrete, which is good. However, much of the content is procedural guidance rather than executable steps — the retention policy section describes recommendations without concrete commands to configure them, the SAR procedure is a markdown checklist rather than actionable code, and the Zapier workflow is YAML pseudocode rather than an actual implementation. The Enterprise API example is concrete but depends on an undocumented API. | 2 / 3 |
Workflow Clarity | Steps are numbered and sequenced, and the SAR procedure includes a clear workflow. However, validation checkpoints are largely missing — the export script has no verification that all notes were captured, the archival workflow has no validation step to confirm completeness, and the retention policy configuration lacks a 'verify policies are applied' step. For operations involving data deletion and compliance, this is a significant gap. | 2 / 3 |
Progressive Disclosure | The document is quite long (~180 lines of substantive content) and could benefit from splitting detailed sections (like the full Python export script, GDPR tables, archival workflows) into separate referenced files. The Resources section at the end provides good external links, and the Next Steps reference is helpful, but the main body is monolithic with everything inline. | 2 / 3 |
Total | 8 / 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.