grammaire/atlassian-rich-text-formatter
Generate Atlassian-ready rich text for Jira and Confluence fields, comments, pages, and blog posts.
96
96%
Does it follow best practices?
Impact
Pending
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 an excellent skill description that clearly defines its purpose, lists specific capabilities and output formats, and provides explicit trigger guidance. It uses third person voice, covers natural user terms comprehensively, and occupies a distinct niche that would be easily distinguishable from other skills. The description is concise yet thorough.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and outputs: 'Generate Atlassian-ready rich text', specifying formats (ADF JSON, Jira wiki markup, Confluence storage XHTML, Confluence wiki markup) and targets (Jira descriptions, comments, environment fields, textarea custom fields, Confluence pages, blog posts, comments). | 3 / 3 |
Completeness | Clearly answers both 'what' (generate Atlassian-ready rich text from raw content) and 'when' (explicit 'Use before creating or updating...' clause with detailed trigger scenarios covering specific Atlassian endpoints and format needs). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Jira', 'Confluence', 'ADF JSON', 'wiki markup', 'XHTML', 'rich text', 'Jira descriptions', 'comments', 'blog posts', 'Confluence pages'. These are terms users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on Atlassian rich text formatting across Jira and Confluence. The specific format mentions (ADF JSON, Jira wiki markup, Confluence storage XHTML) make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%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-crafted skill that efficiently covers four Atlassian rich text formats with concrete, executable examples and clear format selection guidance. Its main weakness is the lack of validation steps—there's no guidance on verifying that generated ADF JSON is structurally valid or that storage XHTML is well-formed before returning it. The conciseness and actionability are excellent, with every section providing immediately usable templates.
Suggestions
Add a brief validation checkpoint, e.g., 'Verify ADF output has version:1, type:doc root and all nodes use valid types before returning' to catch structural errors before they hit the API.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It assumes Claude knows what ADF, wiki markup, and Confluence storage format are without explaining them. Every section provides only the structural templates and rules needed, with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides concrete, copy-paste-ready JSON structures for ADF, exact wiki markup syntax, and complete Confluence storage XHTML examples. The format selection criteria are specific and tied to exact field names and endpoints. The field wrappers show exactly how to embed content in API payloads. | 3 / 3 |
Workflow Clarity | The 'Pick Format' section provides a clear decision tree for format selection, and the rules are well-sequenced. However, there are no explicit validation steps—for instance, no guidance on validating ADF JSON structure before returning it, or checking that storage XHTML is well-formed. Given that malformed ADF or XHTML can cause API failures, a validation checkpoint would be valuable. | 2 / 3 |
Progressive Disclosure | For a skill of this scope with no bundle files, the content is well-organized into clear sections (Pick Format, Rules, ADF, Wiki, Confluence Storage) that serve as a concise reference. Each format gets its own section with examples, making navigation easy. The length is appropriate for inline content without needing external files. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents