granola-performance-tuning

Optimize Granola transcription accuracy, note quality, and processing speed. Use when improving transcription quality, reducing processing time, optimizing templates for better AI output, or tuning audio setup. Trigger: "granola performance", "granola accuracy", "granola quality", "improve granola", "granola transcription better".

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/granola-pack/skills/granola-performance-tuning/SKILL.md

Quality

Content

63%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 thorough, actionable performance-tuning guide with strong tables, checklists, and a measurement loop, but it is held back by an orphaned reference file whose content is duplicated inline and by mild over-explanation. Linking implementation.md from the body and trimming restated prose would notably improve it.

Suggestions

Link references/implementation.md from the body (e.g., a '## Deep dive' section) and move the duplicated mic recommendations, room optimization, and processing-speed tables out of SKILL.md into that file to fix the orphaned reference and inline duplication.

Trim restating prose such as 'Transcription accuracy depends entirely on audio quality:' and the Overview's explanation that clean audio improves AI output, letting the tables and checklists carry the meaning.

Tighten qualitative checklist items (e.g., 'Minimal background noise') with concrete thresholds or examples to close the actionability gap toward fully executable guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient thanks to dense tables and checklists, but prose intros like 'Transcription accuracy depends entirely on audio quality:' and the Overview explaining that clean audio helps AI output restate what Claude can infer.	3 / 5
Actionability	Provides concrete hardware tables, system-path checklists, a copy-paste template, specific Chat prompts, and metric targets with thresholds; minor gaps remain in qualitative guidance like 'Minimal background noise'.	4 / 5
Workflow Clarity	Six clearly sequenced steps with a Step 4 QA checklist and a Step 6 measurement feedback loop ('If accuracy drops below target...'), though validation is advisory rather than the explicit validate-fix-retry pattern of the top anchor.	4 / 5
Progressive Disclosure	The body has clear section structure, but references/implementation.md is never linked or signaled from the body and its content (mic recommendations, room optimization, processing-speed tables) is duplicated inline, so content that belongs in the reference is inlined and the reference is undiscoverable.	3 / 5
	Total	14 / 20 Passed

Description

87%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, well-structured description that clearly states capability, use conditions, and concrete trigger phrases in a Granola-specific niche. Minor tightening of the awkward 'granola transcription better' phrase and more varied action verbs would lift specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete optimization targets (transcription accuracy, note quality, processing speed, templates, audio setup) but reuses the single verb 'Optimize'/'improving' rather than distinct concrete actions, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ('Optimize Granola transcription accuracy, note quality, and processing speed') and when ('Use when improving transcription quality...') plus concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good keyword coverage with natural phrases like 'granola performance', 'granola accuracy', and 'improve granola', though 'granola transcription better' reads as slightly unnatural and a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Every trigger is Granola-prefixed and the domain is a single product niche, giving clear distinct triggers with minimal conflict risk.	5 / 5
	Total	18 / 20 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-performance-tuning/SKILL.md
Commit: 0540a62

Reviewed: about 16 hours 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.