Content
53%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 a well-sectioned coordination protocol spec with real concrete elements (memory key patterns, namespace rules, hook commands), but it never tells the reader how to perform the actual initialization, and its claimed validation steps have no executable form. The stray embedded agent-definition YAML block at the top of the body is a structural defect.
Suggestions
Add the concrete initialization commands (the actual npx claude-flow swarm/topology invocations) so the core task is executable, not just described.
Turn the Error Handling claims ('Validates topology selection', 'Checks resource availability') into explicit validation checkpoints with retry/fallback steps inside the workflow.
Remove or relocate the embedded second '---' YAML block — a stray frontmatter delimiter in the body confuses parsers and readers; move hook commands into a scripts/ file referenced from the body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The bullet lists are lean per-line, but vague filler lines pad several sections ('Handles initialization failures gracefully', 'Provides fallback configurations', 'Establishes message passing protocols') and the embedded agent-definition YAML duplicates information restated in the markdown. Mostly efficient with some unnecessary material — anchor 3, not anchor 4's 'minor instances'. | 3 / 5 |
Actionability | The memory protocol is genuinely concrete (specific key patterns like 'swarm/[agent-name]$status', a fixed 'coordination' namespace, and executable npx claude-flow commands in the hooks), but the core workflow — how to actually initialize a swarm — is described only abstractly ('Allocates compute resources based on task complexity', 'Validates topology selection') with no commands. Concrete guidance exists but the central task is incomplete, matching anchor 3. | 3 / 5 |
Workflow Clarity | Sequences are present (the 5-step MANDATORY memory protocol and the 'Initialize swarm → Spawn agents → Orchestrate tasks' handoff patterns), but there are no validation checkpoints or feedback loops anywhere — 'Checks resource availability' and 'Validates topology selection' are asserted in Error Handling without any steps. Anchor 3 ('steps listed but validation gaps') is the best fit. | 3 / 5 |
Progressive Disclosure | No bundle files exist, and the ~110-line single file is organized under clear section headers (Purpose, Core Functionality, Usage Examples, Integration Points, Best Practices, Error Handling) with nothing that clearly belongs in a separate file. It misses anchor 5 because the skill exceeds the simple-skill line and the stray second YAML frontmatter block at the top of the body muddies navigation. | 4 / 5 |
Total | 13 / 20 Passed |