granola-enterprise-rbac

Configure enterprise role-based access control for Granola workspaces. Use when defining user roles, setting sharing permissions, configuring SSO group mappings, or implementing least-privilege access for meeting data. Trigger: "granola roles", "granola permissions", "granola access control", "granola RBAC", "granola admin roles".

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 body is highly actionable with concrete paths and matrices, and well-sequenced. It loses points for verbosity, missing validation checkpoints on destructive/batch operations, and poor progressive disclosure — the bundled reference is never linked and its content is largely duplicated inline.

Suggestions

Replace the inline permission-matrix and SSO-mapping tables with a one-line pointer to references/implementation.md (e.g. 'See [implementation.md](references/implementation.md) for full permission matrices and YAML configs') and keep SKILL.md to the overview and steps.

Add explicit validation checkpoints to the destructive/batch steps — e.g. after a role change or SCIM deprovisioning, 'Verify the user's access in Settings > Team before proceeding' — and an error-recovery loop.

Trim the inline quarterly checklist and explanatory prose that restates earlier steps; assume Claude's competence and keep only the non-obvious specifics.

Dimension	Reasoning	Score
Conciseness	The body is well-structured but runs ~225 lines with explanatory prose and a full inline quarterly checklist that mostly restates steps already given; it earns its place overall but could be tightened and pushes some detail to the reference file.	2 / 3
Actionability	Concrete navigation paths ('Organization Settings > Security > SSO > Group Mapping'), full permission matrices, sharing-policy configs, and named lifecycle steps give copy-ready, specific guidance with no vague abstraction.	3 / 3
Workflow Clarity	Seven steps are clearly sequenced, but for batch/destructive operations like role changes, SCIM deprovisioning, and access reviews there are no explicit validate-then-proceed checkpoints or feedback loops, which caps workflow clarity at 2 per the guideline.	2 / 3
Progressive Disclosure	A reference file (references/implementation.md) exists and holds deeper matrices/YAML, but SKILL.md duplicates much of that material inline and never signals or links to the reference, so content that should be split remains in the main file.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific, distinctive, and rich in natural trigger terms. Its weakness is completeness: the 'Use when' clause is fragmentary and the triggers are listed under a separate 'Trigger:' label rather than woven into one explicit when-to-use statement.

Suggestions

Merge the 'Use when defining...' clause and the 'Trigger:' list into a single explicit 'Use when the user wants to ... (e.g. "granola roles", "granola permissions", ...)' sentence so both what and when are answered in one clear statement.

Tighten the run-on phrasing ('setting sharing permissions, configuring SSO group mappings, or implementing least-privilege access for meeting data') into a cleaner list of actions.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'defining user roles', 'setting sharing permissions', 'configuring SSO group mappings', 'implementing least-privilege access' — matching the top anchor for listing several specific concrete actions.	3 / 3
Completeness	The 'what' is explicit, but the 'when' guidance is split across a weak 'Use when defining...' clause and a separately labeled 'Trigger:' list rather than a single clear 'Use when...' statement; this caps completeness at 2 per the missing/coy-trigger guideline.	2 / 3
Trigger Term Quality	Provides natural phrases a user would say — 'granola roles', 'granola permissions', 'granola access control', 'granola RBAC', 'granola admin roles' — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The Granola-enterprise-RBAC niche with role/permission/SSO triggers is narrow and specific, making it clearly distinguishable and unlikely to fire for the wrong skill.	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: 5 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.