guidewire-core-workflow-b
Automate the ClaimCenter FNOL→investigation→reserve→payment→settlement→close pipeline including the failure paths — duplicate FNOL from multi-source intake, reserve-must-precede-payment ordering, supervisor-authorization tiers, premature settlement, and reopen-vs-new-claim ambiguity. Use when building claim intake from caller portals, IVR, or partner systems; automating reserve-setting jobs; or integrating settlement events with finance. Trigger with "claimcenter automation", "FNOL", "claim reserve", "claim payment", "claim settlement", "claim reopen".
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 thoroughly covers the ClaimCenter claim lifecycle automation domain. It excels in specificity by naming concrete pipeline stages and failure paths, provides comprehensive trigger guidance with both contextual use cases and explicit trigger terms, and occupies a clearly distinct niche in insurance claim processing automation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions across the entire claim lifecycle: FNOL, investigation, reserve, payment, settlement, close pipeline, plus specific failure paths like duplicate FNOL, reserve-must-precede-payment ordering, supervisor-authorization tiers, premature settlement, and reopen-vs-new-claim ambiguity. | 3 / 3 |
Completeness | Clearly answers both 'what' (automate the full ClaimCenter pipeline including failure paths) and 'when' (explicit 'Use when' clause covering intake from portals/IVR/partner systems, reserve-setting jobs, settlement-finance integration, plus explicit 'Trigger with' terms). | 3 / 3 |
Trigger Term Quality | Includes a rich set of natural trigger terms users would actually say: 'claimcenter automation', 'FNOL', 'claim reserve', 'claim payment', 'claim settlement', 'claim reopen', plus contextual terms like 'caller portals', 'IVR', 'partner systems', and 'reserve-setting jobs'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in ClaimCenter insurance claim automation. The domain-specific terminology (FNOL, ClaimCenter, reserve-must-precede-payment, supervisor-authorization tiers) makes it very unlikely to conflict with other skills. | 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, highly actionable skill that covers a complex multi-step insurance workflow with executable code, explicit validation gates, and comprehensive error handling. Its main weakness is moderate verbosity in explanatory prose and references to bundle files that don't exist, slightly undermining progressive disclosure. The workflow clarity is excellent with proper feedback loops for destructive/ordering-sensitive operations.
Suggestions
Trim explanatory prose that Claude can infer — e.g., remove sentences like 'Reserves communicate the carrier's expected outflow per cost category' and 'claim numbers must remain stable for the underlying loss event so finance, analytics, and regulatory reporting continue to roll up correctly'.
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 could infer (e.g., explaining what reserves communicate, why claim numbers must remain stable). The five-failure preamble is useful but slightly verbose. Overall it respects Claude's intelligence but could be tightened by ~20%. | 2 / 3 |
Actionability | Every step includes executable TypeScript code with real API endpoints, HTTP methods, headers, request bodies, and response handling. The code is copy-paste ready with concrete URL patterns, JSON payloads, and status-code handling. The error table maps specific HTTP errors to specific solutions. | 3 / 3 |
Workflow Clarity | The five-step workflow is clearly sequenced (FNOL → reserve → payment → settlement → reopen) with explicit validation gates: dedup check before FNOL, reserve-before-payment ordering, `isReadyToSettle()` gate before close, and status checks before reopen. Feedback loops are present (check blockers → fix → re-check). The error handling table provides recovery paths for each failure mode. | 3 / 3 |
Progressive Disclosure | The skill references external files (references/implementation-guide.md, references/API_REFERENCE.md) and related skills, but no bundle files are provided to back these references. The main file is quite long (~200+ lines of substantive content) and some sections like the detailed error table or examples could potentially be split out. However, the structure within the file is well-organized with clear headers. | 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
3a2d27d
- 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.