MRI Software integration via Apideck's Accounting unified API — same methods work across every connector in Accounting, switch by changing `serviceId`. Use when the user wants to read, write, or reconcile invoices, bills, payments, ledger accounts, and journal entries in MRI Software. Routes through Apideck with serviceId "mrisoftware".
84
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
92%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 well-crafted description that clearly specifies concrete capabilities, includes explicit trigger guidance with a 'Use when' clause, and uses natural keywords. Its main weakness is the inherent overlap with other Apideck accounting connector skills, since the description explicitly acknowledges the same methods work across connectors. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'read, write, or reconcile invoices, bills, payments, ledger accounts, and journal entries.' Also specifies the integration mechanism (Apideck's Accounting unified API) and the serviceId parameter. | 3 / 3 |
Completeness | Clearly answers both 'what' (MRI Software integration via Apideck's Accounting unified API for invoices, bills, payments, etc.) and 'when' (explicit 'Use when the user wants to read, write, or reconcile invoices, bills, payments, ledger accounts, and journal entries in MRI Software'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'MRI Software', 'invoices', 'bills', 'payments', 'ledger accounts', 'journal entries', 'reconcile', 'Apideck', 'Accounting', and the serviceId 'mrisoftware'. Good coverage of domain-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | While 'MRI Software' and 'serviceId mrisoftware' are distinctive, the description itself notes that 'same methods work across every connector in Accounting, switch by changing serviceId,' which implies many similar skills exist for other Apideck accounting connectors. The accounting actions (invoices, bills, payments) would overlap heavily with other Apideck accounting connector skills. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid connector-specific skill that provides actionable code examples, a useful entity mapping table, and clear coverage caveats for MRI Software's beta status. Its main weaknesses are some marketing-style verbosity around the portability story and a lack of explicit verification/error-handling steps for a beta connector where failures are expected. The progressive disclosure and cross-referencing to other skills is well done.
Suggestions
Trim the 'Portable across 34 Accounting connectors' section — the portability point is already made in the intro paragraph; the code example showing serviceId swap is sufficient without the surrounding prose.
Add a concrete step for verifying MRI Software connection health or coverage before making calls, e.g., show how to use the connector-coverage skill or a health-check API call, especially given the beta status.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity — the 'Portable across 34 Accounting connectors' section is marketing-like and repeats the portability point already made in the intro. The 'When to use this skill' section explains obvious things. However, the entity mapping table and coverage highlights are genuinely useful and earn their tokens. | 2 / 3 |
Actionability | Provides fully executable TypeScript examples for listing invoices, listing journal entries with filters, and using the Proxy API escape hatch with a complete curl command. The entity mapping table and coverage highlights give concrete, specific guidance on what works and what doesn't. | 3 / 3 |
Workflow Clarity | The skill covers a connector integration rather than a multi-step destructive process, so explicit validation loops are less critical. However, there's no guidance on error handling, verifying connection status, or checking coverage programmatically before making calls — it just references another skill for coverage checks without showing how. The beta status warning lacks a concrete verification step. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure — the skill provides a concise overview with clear, well-signaled one-level-deep references to SDK skills, OpenAPI specs, best practices, and connector coverage tools. Content is appropriately split between this overview and the referenced materials. | 3 / 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 |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
9e04d86
Table of Contents
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.