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 with clear workflow sequencing and good scoping (when to use / when not to use). Its main weakness is the lack of concrete, executable examples — particularly for agent spawning and script invocation. The progressive disclosure pattern is sound but unverifiable without bundle files.
Suggestions
Add a concrete example of spawning parallel agents with the `task` tool, showing actual parameters and subagent_type values
Include at least one example script invocation with arguments, e.g., `python search-research.py 'authentication flow'` to make the research-tools references 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 but lacks concrete, executable examples. References to scripts like `list-research.py`, `gather-metadata.py` are mentioned but not shown with actual commands or arguments. The agent spawning step says to use the `task` tool but doesn't show a concrete example of how to invoke it with parameters. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (steps 0-5) with explicit ordering constraints ('read files BEFORE spawning agents', 'wait for ALL agents to complete before synthesizing'). Validation checkpoints are present as bold warnings about common mistakes. The feedback loop of checking past research before starting new work is well-structured. | 3 / 3 |
Progressive Disclosure | The skill references several external files (`research-tools.md`, `agent-selection.md`, `output-format.md`) which is good progressive disclosure structure, but no bundle files were provided to verify these exist. The references are one-level deep and clearly signaled, but the lack of verifiable bundle files and the inline content that could benefit from examples in separate files limits the score. | 2 / 3 |
Total | 10 / 12 Passed |