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.
The skill provides actionable, executable commands for competitor intelligence gathering across multiple platforms, which is its strongest aspect. However, it suffers from a bloated Actor lookup table that should be extracted to a reference file, and the workflow lacks validation checkpoints between steps (e.g., verifying schema fetch success before proceeding, validating JSON input). The error handling section is present but disconnected from the workflow rather than integrated as feedback loops.
Suggestions
Move the 30+ row Actor lookup table to a separate reference file (e.g., ACTORS.md) and keep only a brief summary or top 5-6 most common use cases inline.
Add validation checkpoints in the workflow: verify schema fetch succeeded before Step 3, validate JSON input structure before Step 4, and check run status before Step 5.
Integrate error handling into the workflow as a feedback loop (e.g., 'If run fails, check error output → fix input → re-run') rather than listing errors in a separate section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The massive Actor lookup table (30+ rows) is verbose and could be condensed or moved to a reference file. The boilerplate limitations section and some explanatory text add tokens without much value. However, the workflow steps and commands themselves are reasonably lean. | 2 / 3 |
Actionability | Provides fully executable bash commands for fetching schemas, running actors in multiple output formats, and clear CLI syntax with placeholder substitution. The commands are copy-paste ready with concrete flags and arguments. | 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 error recovery beyond a basic error handling section at the end. | 2 / 3 |
Progressive Disclosure | The skill references scripts at `${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js` suggesting a bundle structure, but no bundle files were provided. The 30+ row Actor table should be in a separate reference file rather than inline, making the main skill unnecessarily long. The structure is present but content splitting is poor. | 2 / 3 |
Total | 9 / 12 Passed |