clerk-install-auth
Install and configure Clerk SDK/CLI authentication. Use when setting up a new Clerk integration, configuring API keys, or initializing Clerk in your project. Trigger with phrases like "install clerk", "setup clerk", "clerk auth", "configure clerk API key", "add clerk to project".
80
77%
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-install-auth/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description with strong trigger terms and clear 'what/when' guidance. The explicit trigger phrases are a notable strength. The main weakness is that the capability description could be more specific about the concrete actions performed (e.g., installing packages, setting environment variables, configuring middleware).
Suggestions
Add more specific concrete actions like 'install npm packages, set environment variables, configure middleware, generate API keys' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Clerk SDK/CLI authentication) and some actions (install, configure, initialize), but doesn't list multiple concrete specific actions like 'set up middleware', 'generate API keys', or 'configure environment variables'. | 2 / 3 |
Completeness | Clearly answers both 'what' (install and configure Clerk SDK/CLI authentication) and 'when' (setting up new Clerk integration, configuring API keys, initializing Clerk) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'install clerk', 'setup clerk', 'clerk auth', 'configure clerk API key', 'add clerk to project'. These are realistic phrases a user would type. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — Clerk is a specific authentication provider, and the triggers are all Clerk-specific. Unlikely to conflict with other authentication or SDK skills. | 3 / 3 |
Total | 11 / 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, highly actionable skill with complete, executable code for multiple frameworks. Its main weaknesses are that it's too long by including all framework variants inline rather than splitting them into separate files, and it lacks explicit validation checkpoints between steps (e.g., confirming env vars are loaded, confirming middleware is active before building auth pages).
Suggestions
Split framework-specific setups (React SPA, Express) into separate referenced files (e.g., CLERK_REACT.md, CLERK_EXPRESS.md) and keep only the Next.js primary path in the main skill.
Add an explicit validation checkpoint after Step 2 (e.g., 'Run `npx next dev` and confirm no missing key errors in console before proceeding') and frame Step 6 as a mandatory verification gate.
Remove boilerplate that Claude can generate (sign-in/sign-up pages are standard Clerk examples) or condense them to one-liners with file paths.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary verbosity—covering Next.js, React SPA, and Express setups all inline makes it long. The sign-in/sign-up page boilerplate and some comments are padding that Claude could generate on its own. However, most content is practical and not overly explanatory. | 2 / 3 |
Actionability | Every step includes fully executable, copy-paste-ready code with correct file paths, imports, and configurations. The error handling table provides specific error messages mapped to concrete solutions. The code examples are complete and production-realistic. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, but there's no explicit validation checkpoint between steps (e.g., 'verify env vars are loaded before proceeding' or 'run dev server and check for errors'). Step 6 provides a health check endpoint but it's not framed as a mandatory validation gate—it's just another step rather than a feedback loop. | 2 / 3 |
Progressive Disclosure | The skill includes three framework setups (Next.js, React, Express) all inline, making it quite long when most users need only one. These could be split into separate files with references. The Resources section links to external docs, and there's a reference to 'clerk-hello-world' for next steps, but the main content is monolithic. | 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
c8a915c
- 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.