clerk-cost-tuning

Optimize Clerk costs and understand pricing. Use when planning budget, reducing costs, or understanding Clerk pricing model. Trigger with phrases like "clerk cost", "clerk pricing", "reduce clerk cost", "clerk billing", "clerk budget".

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.

A highly actionable body with complete, runnable code for each optimization lever, but it is weakened by unnecessary conceptual explanation, a lack of validation/dry-run checkpoints around the destructive user-cleanup step, and a monolithic structure that fails to link to the bundled implementation guide.

Suggestions

Add a dry-run/confirmation gate to Step 5 before deleting users — e.g. require an explicit confirmation flag and report the count of affected accounts before any deletion — so the destructive step has a validation feedback loop.

Link to references/implementation-guide.md from the relevant sections (e.g. 'For full pricing-tier details and extended code patterns, see implementation-guide.md') and move the duplicated pricing table out of SKILL.md to avoid monolithic inline content.

Trim concept explanations Claude already knows (the MAU definition, the bot/crawler exclusion) to keep the body lean and token-efficient.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and built around executable code, but it recapitulates concepts Claude already knows (e.g. defining MAU as 'unique user who authenticates at least once per month', explaining that bot/crawler sessions are not counted) and the Error Handling and Examples sections add explanation beyond what the code already shows. It is tighter than verbose prose but carries some unnecessary explanatory padding, so it sits at the middle anchor rather than the lean top anchor.	2 / 3
Actionability	Each step provides complete, copy-paste-ready TypeScript (middleware route matching, React cache/unstable_cache usage, an admin usage endpoint, an inactive-user cleanup script, and a runnable cost estimator with sample outputs), matching the top anchor for fully executable, specific examples.	3 / 3
Workflow Clarity	The five steps are sequenced, but there are no validation checkpoints between them and the destructive 'Clean Up Inactive Users' step has no verification, dry-run, or confirmation gate before deletion. The rubric caps workflow clarity at 2 when destructive/batch operations lack validation feedback loops.	2 / 3
Progressive Disclosure	A reference file exists (references/implementation-guide.md) but the body never links to or signals it, and the SKILL.md is itself a long monolithic walkthrough that inlines pricing tables and full code blocks rather than pointing out to the separate guide. There is some section structure, but content that should be split is inline and references are not clearly signaled, matching the middle anchor.	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.

A strong, well-structured description that clearly states what the skill does and when to use it, with natural trigger phrases. Its only weakness is that the capability statement ('Optimize Clerk costs and understand pricing') is slightly broad rather than enumerating the concrete optimization levers covered in the body.

Suggestions

Replace the broad verb 'Optimize Clerk costs' with two or three concrete capabilities from the body (e.g. 'Reduce Clerk MAU by deferring authentication, cache Clerk API calls, and estimate monthly spend').

Dimension	Reasoning	Score
Specificity	Names the domain ('Clerk costs', 'pricing') and the actions 'optimize' and 'understand', but 'optimize costs' is somewhat broad rather than enumerating multiple concrete capabilities like reducing MAU or caching API calls. It is more than a single vague verb but less than a list of several specific actions, so it sits at the middle anchor.	2 / 3
Completeness	It explicitly answers both 'what' ('Optimize Clerk costs and understand pricing') and 'when' ('Use when planning budget, reducing costs, or understanding Clerk pricing model'), plus an explicit trigger clause, matching the top anchor that requires both what and an explicit 'Use when' trigger.	3 / 3
Trigger Term Quality	It provides natural phrases a user would actually say — 'clerk cost', 'clerk pricing', 'reduce clerk cost', 'clerk billing', 'clerk budget' — giving good coverage of common variations, matching the top anchor's coverage example.	3 / 3
Distinctiveness Conflict Risk	The Clerk-specific trigger phrases carve out a clear niche that is unlikely to fire for unrelated skills, matching the top anchor for a clear, distinct niche with low conflict risk.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 02d6341

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.