granola-debug-bundle

Create diagnostic bundles for Granola support requests. Use when preparing support tickets, collecting system/audio/network info, or diagnosing complex issues that require Granola support team assistance. Trigger: "granola debug", "granola diagnostics", "granola support bundle", "granola logs", "granola system info".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

The skill body is highly actionable with executable macOS/Windows scripts and a clear step sequence, but it suffers from redundancy with its own reference bundle and lacks validation checkpoints before packaging. The bundled reference file is orphaned rather than woven into the navigation.

Suggestions

Add an explicit validation step before Step 6 (packaging) that confirms each expected output file (system-info.txt, audio-config.txt, network-test.txt, etc.) exists and is non-empty, re-running the failing collection step if not.

Either link references/collection-scripts.md from the body and move the duplicate script blocks there, or remove the reference file to eliminate the orphaned duplication — currently both inline scripts and the reference exist with overlapping content.

De-duplicate the system-information collection between the 'Current State' inline commands and Step 2 so the same data is not collected twice.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable commands, but it duplicates system-info collection between the "Current State" section and Step 2, and its inline scripts substantially overlap the bundled references/collection-scripts.md. Not a 3 because of this redundancy; not a 1 because it avoids explaining concepts Claude already knows and stays largely task-focused.	2 / 3
Actionability	Steps 1–6 provide complete, copy-paste-ready bash and PowerShell blocks (e.g. "mkdir -p \"$DEBUG_DIR\"", "curl -s -o /dev/null -w \"%{http_code}\" --connect-timeout 5 https://api.granola.ai/") with concrete file outputs. Not below 3 because the guidance is fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 1–6) and there is a Self-Diagnosis Checklist and Error Handling table, but the collection workflow has no validation checkpoint confirming each output file exists before the packaging zip runs. Not a 1 because the sequence is explicit; capped at 2 per the batch-operation guideline because verification before packaging is missing.	2 / 3
Progressive Disclosure	The body is organized into clear sections, but references/collection-scripts.md exists as a bundle file yet is never linked or signaled from the body, and it duplicates content that is already inline. Not a 3 because the reference is orphaned and inline content that could live in the reference is duplicated; not a 1 because the body itself is well-sectioned rather than a monolithic wall.	2 / 3
	Total	9 / 12 Passed

Description

90%

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 clearly communicates a Granola-specific diagnostic-bundle skill with explicit 'what' and 'when' guidance plus natural trigger phrases. Its only weakness is specificity, where the action list is one core action wrapped in use-case scenarios rather than a comprehensive set of distinct capabilities.

Dimension	Reasoning	Score
Specificity	Quotes "Create diagnostic bundles for Granola support requests" and "collecting system/audio/network info" name the domain and some actions, but the description centers on one core action with the rest framed as use-case scenarios rather than a comprehensive list of distinct skill actions. Not a 3 because it lacks the multiple distinct concrete actions seen in the top anchor (e.g. extract/fill/merge); not a 1 because the actions are concrete rather than abstract.	2 / 3
Completeness	It states what ("Create diagnostic bundles for Granola support requests") and when ("Use when preparing support tickets, collecting system/audio/network info, or diagnosing complex issues...") plus an explicit Trigger list, answering both what and when. Not a 2 because the 'when' is explicit rather than implied.	3 / 3
Trigger Term Quality	The explicit "Trigger:" clause lists "granola debug", "granola diagnostics", "granola support bundle", "granola logs", "granola system info" — natural phrases a user would say, with good coverage of variations. Not below 3 because the terms are concrete and user-natural, not jargon.	3 / 3
Distinctiveness Conflict Risk	The Granola-scoped triggers ("granola debug", "granola support bundle", etc.) carve a clear niche unlikely to fire for unrelated skills. Not a 2 because the domain and triggers are specific enough to avoid overlap with generic debugging skills.	3 / 3
	Total	11 / 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
Commit: 1628598

Reviewed: about 13 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.