clerk-performance-tuning
Optimize Clerk authentication performance. Use when improving auth response times, reducing latency, or optimizing Clerk SDK usage. Trigger with phrases like "clerk performance", "clerk optimization", "clerk slow", "clerk latency", "optimize clerk".
76
72%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/clerk-pack/skills/clerk-performance-tuning/SKILL.mdQuality
Discovery
79%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 excels at trigger term coverage, completeness (both what and when), and distinctiveness due to its focus on a specific product (Clerk). However, it is weak on specificity of capabilities — it says 'optimize' without describing what concrete actions or techniques the skill actually performs (e.g., caching, middleware tuning, token refresh strategies).
Suggestions
Add specific concrete actions the skill performs, e.g., 'Configures middleware caching, optimizes token refresh intervals, reduces redundant API calls to Clerk backend, and tunes SDK initialization.'
Replace the vague 'Optimize Clerk authentication performance' opener with a list of 2-4 specific techniques or outputs the skill provides.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'Optimize Clerk authentication performance' but does not list any concrete actions. It lacks specifics like caching strategies, middleware configuration, token handling, or SDK-specific optimizations. 'Optimize' and 'improving' are vague verbs. | 1 / 3 |
Completeness | Explicitly answers both 'what' (optimize Clerk authentication performance) and 'when' (improving auth response times, reducing latency, optimizing SDK usage) with explicit trigger phrases. Both clauses are present and clear. | 3 / 3 |
Trigger Term Quality | Includes good natural trigger terms: 'clerk performance', 'clerk optimization', 'clerk slow', 'clerk latency', 'optimize clerk'. These are phrases users would naturally say when experiencing Clerk performance issues. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche: Clerk authentication performance optimization. The combination of 'Clerk' (a specific product) and 'performance/optimization' creates a distinct trigger space unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent executable code examples covering multiple Clerk performance optimization strategies. Its main weaknesses are the lack of validation/measurement checkpoints integrated into the workflow (the perf measurement is an afterthought in Examples), and the content is somewhat long for a single SKILL.md without leveraging progressive disclosure to separate detailed implementations from the overview.
Suggestions
Integrate performance measurement as an explicit first and last step in the workflow (e.g., 'Step 0: Baseline measurement' and 'Step 7: Verify improvements'), creating a feedback loop for the optimization process.
Move detailed code implementations (caching patterns, token handling) into a separate reference file and keep SKILL.md as a concise overview with links to those details.
Remove the Prerequisites and Output sections — they add little value for Claude and consume tokens restating obvious context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples, but includes some unnecessary sections like 'Prerequisites' (Claude knows these), the 'Overview' paragraph restating the title, and the 'Output' section which just summarizes what was already shown. The 'Resources' section with basic doc links adds little value for Claude. | 2 / 3 |
Actionability | Every step includes fully executable, copy-paste-ready TypeScript code with clear file paths and inline comments. The code examples are complete and specific, covering middleware config, caching patterns, token handling, lazy loading, and performance measurement. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, but there are no validation checkpoints between steps. For performance optimization, there should be explicit 'measure before/after' verification steps — the measurement utility is buried in Examples rather than integrated into the workflow. No feedback loop for verifying improvements. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headings and a logical flow, and references 'clerk-cost-tuning' for next steps. However, the skill is quite long (~150 lines of content) and could benefit from splitting detailed patterns (e.g., caching strategies, token handling) into separate reference files while keeping the SKILL.md as a concise overview. | 2 / 3 |
Total | 9 / 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.