guidewire-local-dev-loop
Configure Guidewire Studio local development with Gosu debugging, hot reload, and test data. Trigger: "guidewire local dev loop", "local-dev-loop".
56
47%
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-local-dev-loop/SKILL.mdQuality
Discovery
57%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 targets a clear niche (Guidewire Studio local development) which gives it strong distinctiveness, but it lacks depth in specifying concrete actions and natural trigger coverage. The 'Trigger' field lists exact phrases rather than describing scenarios in which Claude should select this skill, and the capabilities listed are more like feature categories than specific actions.
Suggestions
Expand the trigger guidance into a natural 'Use when...' clause, e.g., 'Use when the user asks about setting up Guidewire Studio locally, debugging Gosu code, configuring hot reload for Guidewire, or creating test data for PolicyCenter/ClaimCenter.'
Add more specific concrete actions, e.g., 'Sets up Guidewire Studio workspace, configures Gosu breakpoints and remote debugging, enables hot reload for plugin development, and generates test data for claim/policy workflows.'
Include additional natural trigger terms users might say, such as 'Guidewire setup', 'PolicyCenter local', 'ClaimCenter dev environment', 'Gosu development', or 'Guidewire plugin development'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Guidewire Studio local development) and some actions (Gosu debugging, hot reload, test data), but these are more like feature areas than concrete actions. It doesn't list specific steps like 'set up breakpoints', 'configure hot reload watchers', or 'generate test data fixtures'. | 2 / 3 |
Completeness | The 'what' is partially addressed (configure local development with debugging, hot reload, test data), and there is a 'Trigger' clause, but it only lists specific phrases rather than describing when Claude should use this skill in natural language (e.g., 'Use when the user needs to set up or troubleshoot a Guidewire local development environment'). | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'Guidewire Studio', 'Gosu debugging', 'hot reload', and 'local dev loop', but misses common variations users might say such as 'Guidewire setup', 'Gosu development', 'local environment', 'dev environment setup', or 'PolicyCenter/ClaimCenter local setup'. | 2 / 3 |
Distinctiveness Conflict Risk | Guidewire Studio with Gosu is a very specific niche technology stack, making this highly unlikely to conflict with other skills. The combination of Guidewire, Gosu, and local dev loop creates a clear, distinct trigger space. | 3 / 3 |
Total | 9 / 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.
This skill is extremely concise but at the cost of being almost entirely non-actionable. The body contains no concrete steps, commands, or code examples — it's essentially a one-line summary plus a link to an implementation guide and some external URLs. A good SKILL.md should at minimum include a quick-start workflow with key commands inline.
Suggestions
Add a concrete quick-start workflow with numbered steps (e.g., 1. Clone repo, 2. Run `gradle runServer`, 3. Open Guidewire Studio, 4. Set breakpoints, 5. Verify with a GUnit test) including actual commands.
Include at least one executable code/command example, such as the exact gradle command with common flags for running the local InsuranceSuite instance.
Add validation checkpoints to the workflow, e.g., how to verify the server started successfully, how to confirm hot deploy is working, and how to check test data loaded correctly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean — no unnecessary explanations of what Guidewire or IntelliJ is. Every token serves a purpose, though the content is arguably too sparse to be useful. | 3 / 3 |
Actionability | No concrete commands, code examples, or executable steps are provided. The overview is a vague summary ('use gradle runServer') with no actual configuration instructions, flags, or copy-paste ready commands. | 1 / 3 |
Workflow Clarity | There is no sequenced workflow at all — no steps for setting up the local dev loop, no validation checkpoints, no error recovery. The entire workflow is deferred to a referenced file with no inline guidance. | 1 / 3 |
Progressive Disclosure | There is a reference to an implementation guide and external resources, which is appropriate structure. However, the SKILL.md overview is too thin to serve as a useful entry point — it provides almost no quick-start content before pointing elsewhere. | 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
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.