Content
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that provides clear, actionable, and well-structured guidance for executing Atlassian API operations. The workflow is well-sequenced with appropriate validation checkpoints, error handling, and security constraints around credential handling. The only notable weakness is that all content is inline in a single file, which for a skill of this complexity could benefit from some progressive disclosure into supporting reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what Jira or Confluence are, assumes Claude understands REST APIs, authentication patterns, and JSON construction. Every section serves a clear purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides concrete, executable command patterns (e.g., the exact `uv run` invocation with flags), specific tool names to call (`atlassian-endpoint-resolver`, `atlassian-rich-text-formatter`, `atlassian-browser-authentication`), and precise rules for field handling, authentication modes, and body construction. The guidance is specific enough to be directly followed. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with explicit validation checkpoints: step 4 checks for missing fields and halts, step 6 has a fallback/retry on 401, and the authentication section includes error handling (stop and report). The feedback loop for browser auth retry on 401 is explicitly defined. Rich text formatting is called out as a mandatory pre-step before body construction. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections (Inputs, Preconditions, Workflow, Authentication, Request Construction, Sub-Agent Rules, Output), but it's all in a single file with no references to external documentation. Given the complexity of the skill (multiple tools, authentication modes, pagination, sub-agents), some content like the detailed request construction rules or output formatting could benefit from being split into referenced files. However, no bundle files are provided, so this is evaluated in isolation. | 2 / 3 |
Total | 11 / 12 Passed |