Content
36%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.
The body is an over-claimed mode catalog: well-sectioned but padded with non-actionable attributes, a duplicated frontmatter block, and invented invocation syntax, with no real workflow sequencing or validation. It reads as marketing-style enumeration rather than executable skill guidance.
Suggestions
Remove the duplicated YAML frontmatter block inside the body and the buzzword attribute lists; keep only concrete tool lists and invocation syntax.
Add at least one end-to-end sequenced workflow (e.g., PR review -> checks -> merge) with explicit validation checkpoints before destructive/batch actions.
Replace the non-executable '$github <mode>' pseudo-syntax with real, runnable gh CLI commands or document clearly that these are invocation conventions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is padded with buzzword attribute lists ('Intelligent', 'Advanced', 'Proactive', 'Automated') and a stray duplicated YAML frontmatter block that add no executable value. | 2 / 5 |
Actionability | Usage examples and bash/mcp snippets give some concrete form, but the mode entries rely on attribute descriptors and non-executable '$github <mode>' invocation syntax rather than runnable steps. | 3 / 5 |
Workflow Clarity | The content is a mode catalog with no sequenced workflow or validation checkpoints; the batch-operations section lacks validation, capping clarity well below 3. | 2 / 5 |
Progressive Disclosure | Clear section headers organize the modes, but everything is inlined in one monolithic file with no references to supporting files and no bundle structure to navigate. | 3 / 5 |
Total | 10 / 20 Passed |