freeagent
FreeAgent 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 FreeAgent. Routes through Apideck with serviceId "freeagent".
87
86%
Does it follow best practices?
Impact
—
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 a strong skill description that clearly identifies the specific integration (FreeAgent via Apideck), lists concrete accounting operations (read, write, reconcile invoices, bills, payments, etc.), and includes an explicit 'Use when' clause with natural trigger terms. The mention of serviceId switching and the unified API pattern adds useful context for disambiguation from similar Apideck accounting connectors.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: read, write, 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' (FreeAgent integration via Apideck's Accounting unified API for invoices, bills, payments, ledger accounts, journal entries) and 'when' (explicit 'Use when the user wants to read, write, or reconcile...' clause with specific triggers). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'FreeAgent', 'invoices', 'bills', 'payments', 'ledger accounts', 'journal entries', 'reconcile', 'Apideck', and 'accounting'. These cover the main terms a user working with FreeAgent accounting would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific mention of 'FreeAgent' as the target system, 'Apideck' as the integration layer, and the serviceId 'freeagent'. This clearly distinguishes it from other accounting connector skills that would use different serviceIds. | 3 / 3 |
Total | 12 / 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 well-structured connector skill with good progressive disclosure and actionable code examples. Its main weaknesses are moderate verbosity from repeated portability messaging and marketing language, and a lack of explicit error handling or validation steps for a beta connector where failures are expected. The entity mapping table and coverage highlights are particularly valuable.
Suggestions
Remove or condense the 'Portable across 34 Accounting connectors' section — the portability point is already made in the intro and the code example; the paragraph about 'compounding advantage' is marketing copy that wastes tokens.
Add a brief error handling/validation note for the beta connector, e.g., how to check response status codes or handle partial coverage failures, to improve workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity — the 'Portable across 34 Accounting connectors' section repeats the portability message already stated in the intro, and the marketing-style language about 'compounding advantage' adds no actionable value. The 'When to use this skill' section also over-explains. However, the entity mapping table and coverage highlights are efficient. | 2 / 3 |
Actionability | Provides fully executable TypeScript examples for listing invoices, filtering by status, 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's supported vs. what requires the Proxy. | 3 / 3 |
Workflow Clarity | The skill covers a clear happy path (use unified API, fall back to Proxy for unsupported operations) and the coverage table helps determine which path to take. However, there are no explicit validation checkpoints — e.g., no guidance on checking API responses for errors, verifying the connection is active, or handling beta-specific failures. | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise overview, quick facts, minimal example up front, and well-signaled one-level-deep references to SDK skills, OpenAPI specs, best practices, and connector coverage tools. Content is appropriately split between this file and referenced resources. | 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 | |
- Repository
- apideck-libraries/api-skills
- Commit
9e04d86
- 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.