Content
65%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is highly actionable with concrete executable commands and a clear phased workflow, but it is token-heavy due to verbose inline templates and lacks validation checkpoints and external reference files.
Suggestions
Move the large markdown report template and CSV export format into a separate reference file (e.g. references/report-template.md) and link to it, reducing SKILL.md bulk.
Add an explicit validation checkpoint after Phase 1 (e.g. verify issue counts and required fields before proceeding to analysis) to support this batch operation.
Tighten the report template by showing one representative row per table instead of repeating placeholder rows for every section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with concrete commands, but the inline markdown report template and distribution-chart examples are padded with repeated placeholder rows ([N], [#], [Title]) that could be tightened. | 2 / 3 |
Actionability | It provides fully executable, copy-paste-ready commands — e.g. `gh issue list --repo ... --state open --json number,title,... --limit 500`, JQL queries, and specific MCP tool calls — with parameters clearly flagged via [CUSTOMIZE] markers. | 3 / 3 |
Workflow Clarity | The five-phase sequence is clear and fallback/error handling tables help, but this batch collection workflow has no explicit validation checkpoint verifying collected data before analysis, which caps clarity at 2. | 2 / 3 |
Progressive Disclosure | Sections and phases give some structure, but the ~300-line body is monolithic with a large inline report template that should be split into a reference file; no bundle files are provided. | 2 / 3 |
Total | 9 / 12 Passed |