Content
75%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, actionable integration skill body with concrete commands and a clear connection-readiness workflow. Validation checkpoints on action results and some structural tightening would push it higher.
Suggestions
Add explicit validation after running actions and proxy requests, e.g. check the `output`/`error` field and retry or surface the error before proceeding.
Dedupe the 'action list' command between 'Searching for actions' and 'Popular actions', keeping a single canonical example.
Group the long flat entity overview (Constituents, Gifts, Reports, etc.) into a few labeled categories so it scans faster.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with concrete commands and a flag reference table, avoiding basic-concept padding; the long flat entity overview and a near-duplicate 'action list' command in 'Popular actions' could be trimmed. | 4 / 5 |
Actionability | It provides copy-paste-ready bash commands (login, connection ensure, action list/run, request) with flags explained, covering common cases; it stops short of showing how to parse the --json output. | 4 / 5 |
Workflow Clarity | The connection-readiness flow is well sequenced with polling and state-based branching (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR), but action-running and proxy paths lack explicit verification checkpoints for results or errors. | 4 / 5 |
Progressive Disclosure | No bundle files exist; the single SKILL.md is organized with clear section headers and an overview, though the flat entity list could be grouped for cleaner navigation. | 4 / 5 |
Total | 16 / 20 Passed |