guidewire-debug-bundle
Collect Guidewire diagnostic info including Cloud API responses, Gosu stack traces, and server logs. Trigger: "guidewire debug bundle", "debug-bundle".
67
61%
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/guidewire-pack/skills/guidewire-debug-bundle/SKILL.mdQuality
Discovery
85%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 solid, focused description that clearly identifies a niche domain (Guidewire diagnostics) with specific capabilities. The explicit trigger clause satisfies completeness requirements. The main weakness is limited trigger term coverage—users might describe their need using terms like 'logs', 'stack trace', or 'troubleshoot Guidewire' that aren't captured.
Suggestions
Expand trigger terms to include natural variations users might say, such as 'Guidewire logs', 'Gosu stack trace', 'Guidewire troubleshooting', 'diagnostic collection', or 'server logs'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: collecting Cloud API responses, Gosu stack traces, and server logs. These are concrete, domain-specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (collect Guidewire diagnostic info including Cloud API responses, Gosu stack traces, and server logs) and 'when' (explicit trigger terms provided via 'Trigger:' clause). | 3 / 3 |
Trigger Term Quality | Includes some relevant trigger terms like 'guidewire debug bundle' and 'debug-bundle', but misses natural variations users might say such as 'diagnostic info', 'collect logs', 'stack trace', 'Guidewire troubleshooting', or 'Gosu error'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the very specific domain (Guidewire), specific technologies (Gosu, Cloud API), and niche use case (debug bundle). Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is extremely concise but at the cost of being almost entirely non-actionable. It reads more like a table of contents entry than a skill — there are no concrete steps, commands, API calls, or examples for collecting diagnostic information. The referenced implementation guide may contain the real content, but the SKILL.md itself provides insufficient guidance for Claude to act on.
Suggestions
Add a concrete, sequenced workflow with numbered steps for collecting each diagnostic artifact (e.g., 'Step 1: Verify OAuth token with `curl -X POST ...`').
Include at least one executable code example, such as a Cloud API call to retrieve server logs or batch process status.
Add validation checkpoints (e.g., 'Verify the token response contains a valid access_token before proceeding') to ensure each collection step succeeded before moving to the next.
Briefly describe what the implementation guide covers so Claude knows when to reference it versus acting on the SKILL.md content directly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean — no unnecessary explanations. Every token serves a purpose, listing exactly what to collect and where to find it without over-explaining concepts Claude already knows. | 3 / 3 |
Actionability | No concrete commands, code snippets, API calls, or step-by-step instructions are provided. The overview is a vague list of items to collect without any executable guidance on how to actually collect them. | 1 / 3 |
Workflow Clarity | There is no sequenced workflow, no steps to follow, and no validation checkpoints. Collecting a debug bundle is inherently a multi-step process, but the skill provides only a comma-separated list of items with no ordering or verification. | 1 / 3 |
Progressive Disclosure | There is a reference to an implementation guide and external resources, which is good structure. However, the overview itself is too thin — it's essentially just a single sentence — making it unclear what the referenced implementation guide covers or how the resources relate to the workflow. | 2 / 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
3e83543
- 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.