Content
77%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-structured coordination skill that efficiently communicates a multi-step research workflow. Its strengths are clear sequencing, good scoping (when to use/not use), and concise writing that respects Claude's intelligence. The main weakness is that actionability depends heavily on external files for concrete details (script invocations, agent types, output formats), and without those bundle files present, the skill alone doesn't provide fully executable guidance.
Suggestions
Add a brief concrete example of a `task` tool invocation showing the subagent_type parameter and a sample task description, so the skill is actionable even without reading agent-selection.md
Include at least one example script invocation with arguments (e.g., `python .research/scripts/search-research.py 'authentication flow'`) to make the research-tools references immediately actionable
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining concepts Claude already knows (like what sub-agents are or how codebases work), uses terse bullet points, and every section earns its place. The 'When NOT to Use' section efficiently scopes the skill. | 3 / 3 |
Actionability | The workflow provides clear steps and references to scripts (list-research.py, search-research.py, etc.), but lacks concrete executable examples of how to invoke these scripts or the `task` tool. The guidance is specific in structure but relies heavily on external files (agent-selection.md, research-tools.md, output-format.md) for the actual executable details. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (steps 0-5) with explicit ordering constraints ('Read mentioned files first BEFORE spawning agents', 'Wait for ALL agents to complete before synthesizing'). Validation checkpoints are present (read context first, wait for all agents, synthesize only after completion). The common mistakes section reinforces the critical ordering requirements. | 3 / 3 |
Progressive Disclosure | The skill references several external files (agent-selection.md, research-tools.md, output-format.md) which is good progressive disclosure structure, but since no bundle files were provided, we cannot verify these references exist or are well-structured. The references are clearly signaled but some are mentioned multiple times and the navigation could be more consolidated (e.g., a single reference section rather than inline mentions). | 2 / 3 |
Total | 10 / 12 Passed |