adp-run
RUN Powered by ADP integration via Apideck's HRIS unified API — same methods work across every connector in HRIS, switch by changing `serviceId`. Use when the user wants to read or sync employees, departments, payrolls, and time-off records in RUN Powered by ADP. Routes through Apideck with serviceId "adp-run".
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 specific integration (RUN Powered by ADP via Apideck), lists concrete data entities it handles, and provides explicit trigger guidance with a 'Use when' clause. It uses proper third-person voice and includes distinctive identifiers like the serviceId. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'read or sync employees, departments, payrolls, and time-off records' and mentions the unified API pattern, serviceId switching, and the specific connector. | 3 / 3 |
Completeness | Clearly answers both what ('read or sync employees, departments, payrolls, and time-off records via Apideck HRIS unified API') and when ('Use when the user wants to read or sync employees, departments, payrolls, and time-off records in RUN Powered by ADP'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'RUN Powered by ADP', 'employees', 'departments', 'payrolls', 'time-off records', 'HRIS', 'Apideck', 'adp-run', and 'serviceId'. Good coverage of both product names and domain terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific product name 'RUN Powered by ADP', the serviceId 'adp-run', and the Apideck HRIS unified API context. Unlikely to conflict with other skills unless there are multiple ADP-related skills, but the specific connector name provides clear differentiation. | 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 strong actionability and excellent progressive disclosure through clear references to related skills and documentation. Its main weaknesses are moderate verbosity from marketing-style language and repeated portability messaging, plus a workflow that could be more explicitly sequenced given the beta status and coverage verification requirements.
Suggestions
Remove or condense the 'Portable across 58 HRIS connectors' section — the portability point is already made in the intro and the code example could be folded into the minimal example section.
Add an explicit numbered workflow: 1) Verify coverage via connector API, 2) If supported → use unified API, 3) If UnsupportedOperationError → use Proxy API, with a validation checkpoint after each step.
Trim the 'When to use this skill' section to just the SDK/spec references — Claude doesn't need to be told when to activate a skill in this much detail.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity — the 'Portable across 58 HRIS connectors' section repeats the marketing pitch from the intro, the 'When to use this skill' section over-explains activation triggers, and phrases like 'This is the compounding advantage of using Apideck' are promotional rather than instructional. However, the core technical content (serviceId, examples, proxy API) is reasonably efficient. | 2 / 3 |
Actionability | Provides fully executable TypeScript code for listing employees, a concrete curl command for verifying coverage, and a complete proxy API curl example with all required headers. The serviceId, auth type, and setup steps are specific and copy-paste ready. | 3 / 3 |
Workflow Clarity | There's an implicit workflow (check coverage → use unified API → fall back to proxy if unsupported), but it's not presented as a clear sequential process with validation checkpoints. The beta status warning mentions verifying coverage but doesn't integrate this into a step-by-step workflow with explicit error handling or feedback loops. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a concise overview and well-signaled one-level-deep references to SDK skills, best practices, connector coverage, OpenAPI specs, and sibling connectors. Content is appropriately split between this skill and 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 | |
- 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.