clerk-debug-bundle
Collect comprehensive debug information for Clerk issues. Use when troubleshooting complex problems, preparing support tickets, or diagnosing intermittent issues. Trigger with phrases like "clerk debug", "clerk diagnostics", "clerk support ticket", "clerk troubleshooting".
56
66%
Does it follow best practices?
Impact
—
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-debug-bundle/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 description with strong trigger terms and clear 'what/when' guidance. Its main weakness is that the capability description is somewhat general — 'collect comprehensive debug information' could be more specific about what concrete actions or outputs the skill produces. Overall it would perform well in skill selection scenarios.
Suggestions
Add specific concrete actions to improve specificity, e.g., 'Collects Clerk SDK versions, middleware configuration, auth state, session details, and environment variables for debugging Clerk issues.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Clerk issues) and a general action (collect comprehensive debug information), but doesn't list specific concrete actions like checking logs, inspecting auth tokens, verifying middleware config, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (collect comprehensive debug information for Clerk issues) and 'when' (troubleshooting complex problems, preparing support tickets, diagnosing intermittent issues) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger phrases like 'clerk debug', 'clerk diagnostics', 'clerk support ticket', 'clerk troubleshooting' — these are terms users would naturally say. Also includes contextual triggers like 'troubleshooting complex problems' and 'preparing support tickets'. | 3 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Clerk-specific debugging and diagnostics, with distinct trigger terms that are unlikely to conflict with general debugging skills or other authentication library skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable code for Clerk debugging across multiple surfaces (backend, frontend, middleware, CLI), which is its primary strength. However, it is far too verbose for a SKILL.md — the full implementations of components, endpoints, and scripts should be in separate bundle files with the SKILL.md serving as a concise overview. The workflow lacks explicit validation checkpoints between steps.
Suggestions
Extract the full code implementations (debug script, health endpoint, React component, middleware, bash script) into separate bundle files and reference them from SKILL.md with brief descriptions of what each does.
Remove the Prerequisites and Overview sections — Claude knows what Clerk SDK access and browser dev tools are.
Add validation checkpoints: after Step 1, verify the JSON output is valid; after Step 2, curl the health endpoint to confirm it works before proceeding to client-side steps.
Trim the React component to essential logic only — remove inline styles and let Claude infer UI presentation details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~180 lines with full component implementations, middleware, and bash scripts that could be significantly condensed. The 'Prerequisites' and 'Overview' sections explain things Claude already knows, and the full React component with inline styles is excessive detail for a debug skill. | 1 / 3 |
Actionability | Every step provides fully executable, copy-paste ready code — TypeScript scripts, API routes, React components, bash scripts, and curl commands. The code is complete and specific with proper imports and error handling. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, but there are no validation checkpoints between steps. There's no guidance on verifying each step succeeded before proceeding to the next, and no feedback loop for when the debug script itself fails or returns unexpected results. | 2 / 3 |
Progressive Disclosure | All content is monolithically inlined in a single file — the full debug script, health endpoint, React component, middleware, and bash script should be in separate referenced files. The error handling table and resources are good but the massive code blocks make this a wall of text with no bundle files to offload to. | 1 / 3 |
Total | 7 / 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
d41e58e
- 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.