CtrlK
BlogDocsLog inGet started
Tessl Logo

granola-common-errors

Troubleshoot common Granola errors — audio capture failures, transcription issues, calendar sync problems, and integration errors. Platform-specific fixes for macOS and Windows. Trigger: "granola error", "granola not working", "granola not recording", "fix granola", "granola troubleshoot".

65

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/granola-pack/skills/granola-common-errors/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-5

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

A well-organized, actionable troubleshooting guide with concrete commands and a useful triage table, but it lacks inline validation around its destructive fixes and fails to link the accompanying detailed-errors reference file.

Suggestions

Add inline validation checkpoints around destructive fixes (e.g., after `rm -rf ~/Library/Caches/Granola` or `defaults delete ai.granola.app`, instruct to relaunch and confirm the symptom is resolved before trying the next fix).

Link references/detailed-errors.md from the body (e.g., a "Detailed error reference" section pointing to it) so the bundle file is discoverable and progressive disclosure is complete.

Tighten prose-only fixes like "Keep your machine awake during meetings" into concrete commands (e.g., `caffeinate -d` on macOS) to raise actionability.

DimensionReasoningScore

Conciseness

Largely efficient with table-driven symptom/fix pairs and executable code blocks, but a few overview sentences and prose-only fixes (e.g., "Keep your machine awake during meetings") could be trimmed.

4 / 5

Actionability

Provides copy-paste bash commands (pgrep, defaults read, sudo killall coreaudiod, pkill, rm -rf) and exact Settings menu paths, with only minor gaps where fixes are prose-only without a concrete command.

4 / 5

Workflow Clarity

Has a clear Step 1 diagnostic → Step 2 symptom-match flow and an end "Output" verification list, but destructive operations (sudo killall coreaudiod, pkill -9, rm -rf caches, defaults delete) lack inline validate-then-proceed feedback loops, capping this dimension at 3.

3 / 5

Progressive Disclosure

The body is well-sectioned, but the provided bundle file references/detailed-errors.md is never linked or signaled from the body — the reference exists yet navigation to it is missing.

3 / 5

Total

14

/

20

Passed

Description

95%Weight 40%Scale 1-5

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

A strong, specific description that names concrete error categories, provides platform-specific scope, and includes explicit natural-language trigger phrases. Minor specificity gaps in error-type coverage keep it just below a perfect specificity score.

DimensionReasoningScore

Specificity

Lists several concrete error categories ("audio capture failures, transcription issues, calendar sync problems, and integration errors") plus "Platform-specific fixes for macOS and Windows" — multiple specific actions with minor coverage gaps (e.g., app crashes/processing not mentioned).

4 / 5

Completeness

Explicitly answers both "what" (the four error categories and platform-specific fixes) and "when" (a dedicated Trigger clause with concrete trigger phrases).

5 / 5

Trigger Term Quality

Includes five natural user phrases — "granola error", "granola not working", "granola not recording", "fix granola", "granola troubleshoot" — covering common variations a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Scoped to the Granola app with Granola-prefixed triggers, giving it a clear niche with minimal overlap risk against other skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.