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".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 solid skill description with strong trigger coverage and clear completeness. Its main weakness is that the capability descriptions lean toward general optimization language rather than listing specific concrete actions. The explicit trigger terms and 'Use when' clause make it highly functional for skill selection.
Suggestions
Replace generic optimization language with specific concrete actions, e.g., 'Adjust audio input settings, configure transcription templates, tune noise reduction, optimize AI prompt templates for Granola notes.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Granola transcription) and some actions (optimize accuracy, note quality, processing speed), but the actions are somewhat generic optimization terms rather than listing specific concrete techniques or operations like 'adjust audio settings', 'configure template parameters', or 'calibrate noise reduction'. | 2 / 3 |
Completeness | Clearly answers both 'what' (optimize Granola transcription accuracy, note quality, and processing speed) and 'when' (explicit 'Use when' clause with multiple trigger scenarios plus a dedicated 'Trigger' list). Both components are explicitly stated. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms that users would naturally say: 'granola performance', 'granola accuracy', 'granola quality', 'improve granola', 'granola transcription better'. Also includes natural phrases in the 'Use when' clause like 'improving transcription quality' and 'reducing processing time'. Good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'Granola' and the niche focus on transcription performance optimization. Very unlikely to conflict with other skills given the unique combination of product name and task domain. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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-crafted skill with strong actionability and clear workflow sequencing, including validation checkpoints and error recovery. Its main weakness is length — the content is thorough but could be more concise by trimming explanatory 'why' columns and splitting detailed reference tables into separate files. The skill successfully provides concrete, measurable guidance for improving Granola performance.
Suggestions
Trim the 'Why It Helps' column from the meeting practices table — Claude can infer why stating names helps attribution
Move the detailed hardware comparison table and error handling table to a referenced file (e.g., GRANOLA-AUDIO-SETUP.md) to reduce the main skill's token footprint
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some unnecessary verbosity. The 'Prerequisites' section and 'Output' section add little value. Some table entries explain obvious things (e.g., why one speaker at a time helps). The overview explains what Granola's AI is, which Claude likely knows. However, most content is practical and not excessively padded. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific hardware recommendations with priority ordering, exact checklists for audio configuration, a copy-paste-ready template with format hints, specific chat prompts with expected outcomes, and measurable targets with thresholds. The guidance is specific enough to act on immediately. | 3 / 3 |
Workflow Clarity | The six steps are clearly sequenced from setup (audio) through practices, templates, post-meeting review, gap-filling, and measurement. Step 4 serves as an explicit validation checkpoint with a checklist. Step 6 provides a feedback loop: if accuracy drops, follow a prioritized troubleshooting sequence. The error handling table adds another layer of recovery guidance. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and tables, but it's quite long for a single SKILL.md file. The template design section, meeting practices table, and error handling could be split into referenced files. External resources are linked at the end, and there's a reference to 'granola-cost-tuning', but the main body is monolithic at ~150+ lines of substantive content. | 2 / 3 |
Total | 10 / 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
70e9fa4
- 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.