granola-reference-architecture

Enterprise reference architecture for meeting management with Granola. Use when designing org-wide meeting workflows, planning integration topology, or architecting meeting-to-action pipelines across departments. Trigger: "granola architecture", "granola enterprise design", "granola system design", "meeting system architecture".

Quality

64%

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-reference-architecture/SKILL.md

Quality

Content

38%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.

The body reads as an architecture reference document rather than an actionable skill: heavy on ASCII diagrams and descriptive tables, light on executable guidance and validation steps. Content that belongs in the bundled implementation.md reference is largely inlined, undercutting progressive disclosure.

Suggestions

Replace the verbose ASCII pipeline/workspace/security diagrams with concise prose plus pointers to references/implementation.md, cutting the bulk of the token spend.

Convert the descriptive 'Steps' into an actionable procedure: name the specific Granola/Zapier settings, folder fields, and Zap steps to configure, with copy-paste-ready values.

Add explicit validation checkpoints (e.g., 'After wiring each folder, send a test meeting and confirm it lands in the correct Slack channel + CRM record before enabling auto-trigger') so destructive/batch automation has a feedback loop.

Dimension	Reasoning	Score
Conciseness	The ~210-line body is padded with large ASCII diagrams, verbose multi-line architecture trees, and a step-4 block that restates Granola/SSO/TLS concepts Claude already knows; it does not assume Claude's competence and most tokens could be tightened.	2 / 5
Actionability	Guidance is predominantly descriptive architecture diagrams and tables rather than executable steps; the few concrete actions (Zapier Paths, folder names) are high-level hints without the specific commands or configuration needed to execute.	2 / 5
Workflow Clarity	Steps are numbered 1-6 and sequenced, but the steps describe deliverables ('document topology', 'design folder structure') rather than a procedure with validation checkpoints; the Error Handling table provides some recovery guidance but no validate-then-proceed loops.	3 / 5
Progressive Disclosure	The body has section structure and links out to external Granola docs, but it inlines large architecture diagrams and a routing table that partly duplicate the bundled references/implementation.md rather than signaling it as the one-level-deep detail file.	3 / 5
	Total	10 / 20 Passed

Description

90%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.

The description is well-crafted: it states concrete capabilities, gives an explicit 'Use when' clause, and lists natural trigger phrases. It is a strong, distinctive description with only minor room to expand the action list.

Dimension	Reasoning	Score
Specificity	Names the domain (Granola meeting management) and several concrete architectural actions—'designing org-wide meeting workflows, planning integration topology, architecting meeting-to-action pipelines'—but stops short of the comprehensive, granular action list of a 5.	4 / 5
Completeness	Clearly answers 'what' (enterprise reference architecture for meeting management with Granola) and 'when' ('Use when designing...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Explicitly enumerates four natural trigger phrases a user would say ('granola architecture', 'granola enterprise design', 'granola system design', 'meeting system architecture'), giving comprehensive keyword coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	Tightly scoped to Granola enterprise architecture with dedicated trigger phrases, occupying a clear niche with minimal risk of conflicting with other skills.	5 / 5
	Total	19 / 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-reference-architecture/SKILL.md
Commit: 8585d6d

Reviewed: 13 days 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.