guidewire-core-workflow-a
Automate the PolicyCenter account→submission→quote→bind→issue→endorse→renew pipeline including the failure paths — underwriting issues blocking bind, quotes expiring before bind, referrals stuck pending approval, and mid-term endorsements that trigger unexpected premium audit recalculation. Use when building outbound integrations against PolicyCenter Cloud API (CRM-driven submission, broker-portal binding, automated renewal jobs). Trigger with "policycenter automation", "submission to bind", "policy renewal", "policy endorsement", "underwriting issue".
71
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 an excellent skill description that clearly defines a specific domain (Guidewire PolicyCenter automation), lists concrete actions and failure scenarios, and provides explicit trigger guidance. It covers both the 'what' and 'when' comprehensively, uses third-person voice correctly, and occupies a highly distinctive niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: account→submission→quote→bind→issue→endorse→renew pipeline, plus failure paths like underwriting issues blocking bind, quotes expiring, referrals stuck pending approval, and mid-term endorsements triggering premium audit recalculation. | 3 / 3 |
Completeness | Clearly answers both 'what' (automate the full PolicyCenter pipeline including failure paths) and 'when' (explicit 'Use when building outbound integrations against PolicyCenter Cloud API' plus a 'Trigger with' clause listing specific trigger terms). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'policycenter automation', 'submission to bind', 'policy renewal', 'policy endorsement', 'underwriting issue', plus contextual terms like 'PolicyCenter Cloud API', 'broker-portal binding', 'automated renewal jobs', and 'CRM-driven submission'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (Guidewire PolicyCenter automation pipeline) with domain-specific terminology that is unlikely to conflict with other skills. The combination of insurance-specific terms and PolicyCenter API references creates a clear, unique identity. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, production-oriented skill that excels at actionability and workflow clarity — it provides executable code for every lifecycle step and explicitly addresses the five most common failure modes with concrete detection and remediation patterns. The error handling table and examples are particularly valuable. Minor weaknesses include some verbosity in explanatory prose and references to bundle files that don't exist, slightly undermining progressive disclosure.
Suggestions
Trim explanatory prose that restates what the code already demonstrates (e.g., the paragraph after the idempotency key code, the explanation of what quote expiry means) to improve conciseness.
Provide the referenced bundle files (references/implementation-guide.md, references/API_REFERENCE.md) or remove the references to avoid broken navigation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and domain-specific, but includes some unnecessary explanatory prose that Claude would already know (e.g., explaining what idempotency keys do, explaining that quotes expire). Some inline commentary could be trimmed, though the domain-specific failure modes and gotchas genuinely earn their tokens. | 2 / 3 |
Actionability | Provides fully executable TypeScript code for each step of the pipeline, with concrete API paths, HTTP methods, headers, and response handling. The code is copy-paste ready and covers both happy paths and failure branches with specific error types and remediation actions. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit validation checkpoints: UW issue inspection before bind, quote expiry check before bind, premium drift detection before endorsement bind, and renewal window verification. Feedback loops are present (re-quote on expiry, route to referral queue on blocking issues, resume after referral approval). The error handling table provides a comprehensive state-transition failure matrix. | 3 / 3 |
Progressive Disclosure | The skill references external files like `references/implementation-guide.md` and `references/API_REFERENCE.md`, plus related skills like `guidewire-install-auth` and `guidewire-sdk-patterns`, but no bundle files are provided to back these references. The main content is well-structured with clear sections, but the inline content is quite long (~200 lines) and some of the error handling table or examples could potentially be split out. | 2 / 3 |
Total | 10 / 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
a04d1a2
- 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.