Content
64%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides actionable, executable commands for trend analysis across multiple platforms with a clear multi-step workflow. Its main weaknesses are the lack of validation checkpoints between steps (especially after schema fetch and before actor execution), the verbose Actor lookup table that could be externalized, and boilerplate sections that waste tokens. The error handling section is useful but presented as a flat list without recovery workflows.
Suggestions
Add a validation step after fetching the Actor schema (Step 2) to verify the response contains expected fields before proceeding, and add output verification after Step 4.
Move the large Actor ID lookup table to a separate reference file (e.g., ACTORS.md) and keep only a brief summary or top 5 most common actors inline.
Remove the generic 'When to Use' and 'Limitations' boilerplate sections — they add no skill-specific value and waste tokens.
Convert the error handling section into a structured troubleshooting flow with explicit recovery steps rather than a flat list.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The large Actor table is useful reference but could be more compact. The boilerplate 'When to Use' and 'Limitations' sections add no value. The workflow is mostly efficient but has some padding (e.g., 'Based on character of use case' is vague filler). | 2 / 3 |
Actionability | Provides fully executable bash commands for fetching schemas and running actors, with concrete examples for all three output formats. The mcpc command, run_actor.js invocations, and error handling are all copy-paste ready with clear placeholder substitution. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with a progress checklist, but lacks validation checkpoints. There's no step to verify the Actor schema was fetched correctly, no validation of the JSON input before running, and no feedback loop for handling partial failures or verifying output quality. | 2 / 3 |
Progressive Disclosure | References scripts at ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js but no bundle files are provided to verify. The Actor table is a large inline block that could be a separate reference file. The skill has reasonable section structure but the monolithic Actor table hurts organization. | 2 / 3 |
Total | 9 / 12 Passed |