Content
42%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 highly actionable, executable commands and a clear workflow structure, but is severely undermined by its massive inline reference tables consuming excessive tokens. The 55+ actor listings should be offloaded to separate reference files or replaced by reliance on the search-actors command, and validation checkpoints should be integrated into the workflow steps rather than relegated to a separate error handling section.
Suggestions
Move the actor reference tables (Instagram, Facebook, TikTok, YouTube, Google Maps, Other) to a separate ACTORS_REFERENCE.md file and link to it from SKILL.md, keeping only the use-case mapping table and the search-actors command inline.
Add explicit validation checkpoints in the workflow: verify schema fetch succeeded before Step 3, validate input JSON structure before Step 4, and check run status before Step 5.
Integrate error handling into the workflow steps as inline feedback loops (e.g., 'If fetch-actor-details returns empty, verify Actor ID and retry or use search-actors') rather than listing errors in a separate section.
Remove the multi-actor workflows and follow-up suggestion tables from the main body—these could be in a separate WORKFLOWS.md file or generated dynamically based on results.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose with massive lookup tables (55+ actors across 6 categories) that consume enormous token budget. Most of this reference data could be offloaded to separate files or handled by the search-actors command. The use-case mapping tables, multi-actor workflow tables, and follow-up suggestion tables add further bloat. Claude doesn't need all 55 actor IDs inline when there's a search command available. | 1 / 3 |
Actionability | The skill provides fully executable bash commands for every step: searching actors, fetching schemas, and running scripts with concrete flags and formats. The commands are copy-paste ready with clear placeholder substitution patterns (ACTOR_ID, JSON_INPUT, SEARCH_KEYWORDS). | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with a progress checklist, but it lacks explicit validation checkpoints. There's no step to verify the actor schema was fetched successfully before proceeding, no validation that the input JSON matches the schema, and no feedback loop for handling partial results or retrying failed runs. The error handling section is separate rather than integrated into the workflow steps. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with no bundle files provided to offload the massive actor reference tables. The 55+ actor listings, use-case mappings, and multi-actor workflow tables should be in separate reference files. Everything is crammed into a single SKILL.md, making it extremely long and poorly organized for progressive disclosure. | 1 / 3 |
Total | 7 / 12 Passed |