Content
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has strong workflow clarity with a well-sequenced procedure, explicit confirmation gates, and validation checkpoints appropriate for destructive operations. Its main weaknesses are incomplete actionability (vague inputs/outputs, missing script bundle, no concrete output schema example) and moderate conciseness issues with some low-value sections. The structure is reasonable but would benefit from providing the referenced script and a concrete output example.
Suggestions
Provide the referenced script `clean-gone` in the bundle or inline its logic so the skill is self-contained and fully actionable.
Replace the vague 'Inputs' and 'Outputs' sections with a concrete example showing actual input context and the expected structured output JSON schema.
Remove the 'Full Context' section listing icon assets, as it adds no instructional value to the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some sections that could be tightened—'Inputs' is vague and adds little value, 'Full Context' listing icon assets is irrelevant to the skill's purpose, and 'Examples' are natural language prompts rather than concrete input/output pairs. The Failure Modes and Anti-Patterns sections are useful but slightly verbose. | 2 / 3 |
Actionability | The procedure references a concrete script path and provides executable bash commands for worktree/branch deletion, which is good. However, the script itself is not provided in the bundle, the 'Inputs' section is entirely vague ('Request, artifacts, repo context'), and the 'Outputs' section describes a schema without showing its actual structure. Key details like how to verify PR status (mentioned in examples) are missing. | 2 / 3 |
Workflow Clarity | The procedure is clearly sequenced with explicit validation checkpoints: discovery → check for __NONE__ → present candidates → single confirmation gate → worktree removal before branch deletion → report outcomes. The Validation section adds a fail-fast gate and specific checks (active branch protection, root worktree protection). The feedback loop for partial failures is explicitly addressed. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear section headers and logical organization. However, no bundle files are provided despite referencing a script path, and the 'Full Context' section references icon assets that don't contribute to the skill. The skill is moderately long but keeps everything inline rather than splitting detailed validation or anti-patterns into separate references. | 2 / 3 |
Total | 9 / 12 Passed |