greenhouse
Greenhouse 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 Greenhouse. Routes through Apideck with serviceId "greenhouse".
87
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 integration target (Greenhouse via Apideck), lists specific data entities (jobs, applicants, applications), and includes an explicit 'Use when' clause with natural trigger terms. The technical details about serviceId and unified API add useful context for disambiguation without being overly jargon-heavy.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'read, write, or sync jobs, applicants, and applications in Greenhouse.' Also mentions the technical mechanism (Apideck's ATS unified API, serviceId) which adds clarity about how it works. | 3 / 3 |
Completeness | Clearly answers both what ('read, write, or sync jobs, applicants, and applications in Greenhouse via Apideck's ATS unified API') and when ('Use when the user wants to read, write, or sync jobs, applicants, and applications in Greenhouse') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Greenhouse', 'jobs', 'applicants', 'applications', 'ATS', 'Apideck', 'sync'. These cover the main terms someone working with Greenhouse recruiting would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — specifies Greenhouse by name, routes through Apideck with a specific serviceId, and targets ATS-specific entities (jobs, applicants, applications). Unlikely to conflict with other skills unless there's another Greenhouse integration skill. | 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 solid connector-specific skill with excellent progressive disclosure and actionable code examples. Its main weaknesses are moderate verbosity (marketing-style repetition of the portability value proposition) and missing validation/error-handling steps in workflows, particularly around auth failures and multi-step operations. Trimming the promotional content and adding error-handling checkpoints would elevate this skill significantly.
Suggestions
Remove or condense the 'Portable across 11 ATS connectors' section — the portability point is already made in the intro and the sibling connectors section; the repeated pitch wastes tokens.
Add error handling/validation to the multi-step 'create candidate + application' example — e.g., check for 403 from wrong key type, verify applicant creation succeeded before proceeding to application creation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity — the 'Portable across 11 ATS connectors' section repeats the portability pitch already made in the intro, and phrases like 'This is the compounding advantage of using Apideck over integrating Greenhouse directly' are marketing fluff rather than actionable content. The entity mapping table and coverage highlights are valuable, but the overall document could be tightened by ~30%. | 2 / 3 |
Actionability | The skill provides fully executable TypeScript examples for listing applicants, creating candidates/applications, moving pipeline stages, and using the Proxy escape hatch with a complete curl command. Key details like auth type requirements (Harvest vs Job Board keys) and the On-Behalf-Of header are specific and actionable. | 3 / 3 |
Workflow Clarity | The 'create a candidate and an application in one flow' example shows a clear two-step sequence, and the coverage table clearly delineates what requires the Proxy escape hatch. However, there are no validation checkpoints — no error handling for 403s from wrong key types, no verification that the candidate was created before creating the application, and no feedback loops for common failure modes. | 2 / 3 |
Progressive Disclosure | The skill is well-structured as an overview with clear one-level-deep references to SDK skills, OpenAPI specs, best practices, and connector coverage tools. The 'See also' section and inline links to sibling connectors and language SDK skills provide excellent navigation without nesting references more than one level deep. | 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.