lever
Lever integration via Apideck's ATS unified API — same methods work across every connector in ATS, switch by changing `serviceId`. Use when the user wants to read, write, or sync jobs, applicants, and applications in Lever. Routes through Apideck with serviceId "lever".
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 platform (Lever), the integration mechanism (Apideck ATS unified API), concrete actions (read, write, sync jobs/applicants/applications), and explicit trigger conditions. It uses third person voice appropriately and provides enough detail for Claude to distinguish it from other ATS or Apideck skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'read, write, or sync jobs, applicants, and applications in Lever.' Also mentions the integration mechanism (Apideck's ATS unified API) and the serviceId pattern. | 3 / 3 |
Completeness | Clearly answers both what ('Lever integration via Apideck's ATS unified API — read, write, or sync jobs, applicants, and applications') and when ('Use when the user wants to read, write, or sync jobs, applicants, and applications in Lever') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Lever', 'jobs', 'applicants', 'applications', 'ATS', 'Apideck', 'sync', 'serviceId'. Covers both the product name and the domain objects a user would reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets Lever specifically via Apideck with serviceId 'lever'. The combination of the specific ATS platform (Lever), the integration layer (Apideck), and the serviceId makes it very unlikely to conflict with other skills. | 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 integration skill with strong actionability through executable examples and a clear entity mapping table. Its main weaknesses are moderate verbosity (repeated emphasis on portability/serviceId switching, marketing language) and lack of validation/error-handling workflows for write operations. The progressive disclosure and reference structure are excellent.
Suggestions
Remove or consolidate the 'Portable across 11 ATS connectors' section — the portability concept is already stated in the intro and demonstrated in the minimal example; repeating it with marketing language wastes tokens.
Add a brief error handling/validation note after write operations (e.g., check response status, handle rate limits), especially for the create applicant and proxy examples.
Trim the 'When to use this skill' section to 1-2 lines — Claude doesn't need a numbered list explaining what the skill teaches.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity — the 'Portable across 11 ATS connectors' section repeats the serviceId-switching concept already explained in the intro and quick facts. The 'When to use this skill' section over-explains activation triggers. The marketing-style language ('compounding advantage') adds no instructional value. | 2 / 3 |
Actionability | Provides fully executable TypeScript examples for listing applicants, creating candidates with source attribution, 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 multiple operations (list, create, proxy) but doesn't provide a clear multi-step workflow with validation checkpoints. There's no error handling guidance, no verification steps after creating applicants/applications, and no feedback loop for failed API calls. For an integration skill involving writes, this is a gap. | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise overview, quick facts, minimal examples inline, and well-signaled one-level-deep references to SDK skills, OpenAPI specs, best practices, and connector coverage. The 'See also' section and inline links to sibling connectors provide clear navigation without nesting. | 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.