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".

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

70%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, well-structured workflow document with explicit checkpoints and real code, held back only by narrative padding and a reliance on undefined helper functions that keep some examples from being fully executable.

Suggestions

Define the helper functions referenced in the samples (createSubmission, bindSubmission, openEndorsement, quoteEndorsement, bindEndorsement, routeToReferralQueue, emitPremiumDriftEvent) inline or in references/API_REFERENCE.md so every example is copy-paste ready.

Tighten narrative asides such as 'The most-skipped step in naive automation' and lead each numbered section with the executable pattern, moving rationale into terse trailing bullets.

Collapse the per-step prose commentary (e.g., the endorsement and renewal paragraphs) into compact bullets to reduce token overhead while preserving the failure-mode guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific content that assumes Claude's competence, but narrative asides such as 'The most-skipped step in naive automation' and per-step commentary could be tightened to fully earn the top anchor.	2 / 3
Actionability	Real TypeScript fetch snippets with concrete logic are provided, but many rely on undefined helpers (createSubmission, bindSubmission, openEndorsement, quoteEndorsement, routeToReferralQueue) so the examples are not uniformly copy-paste ready.	2 / 3
Workflow Clarity	A clearly numbered 1–7 state-transition sequence with explicit validation checkpoints (blocking UW-issue check, quote-expiry re-quote, premium-drift threshold, renewal-window guard) and a feedback-oriented error-handling table.	3 / 3
Progressive Disclosure	Well-sectioned overview (Prerequisites, Instructions, Output, Examples, Error Handling, See Also, Resources) with two clearly signaled one-level-deep references — implementation-guide.md and API_REFERENCE.md — both present in references/.	3 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A dense, specific description that covers concrete capabilities, explicit use-when guidance, and natural trigger terms within a clearly bounded Guidewire PolicyCenter niche. Voice is imperative/third person with no first- or second-person penalty.

Dimension	Reasoning	Score
Specificity	Names the concrete account→submission→quote→bind→issue→endorse→renew pipeline plus specific failure paths (underwriting issues blocking bind, expired quotes, stuck referrals, premium audit recalculation), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both what (automate the pipeline including failure paths) and when via an explicit 'Use when building outbound integrations against PolicyCenter Cloud API' clause plus triggers, satisfying the top anchor.	3 / 3
Trigger Term Quality	Explicit 'Trigger with' clause supplies natural terms a user would say — "policycenter automation", "submission to bind", "policy renewal", "policy endorsement", "underwriting issue" — giving good coverage with common variations.	3 / 3
Distinctiveness Conflict Risk	The PolicyCenter/Guidewire niche with product-specific triggers is clearly distinguishable from sibling skills and unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/guidewire-pack/skills/guidewire-core-workflow-a/SKILL.md
Commit: 4c47e33

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.