Content
11%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 well-sectioned but hollow: it lists capabilities and edge-case titles yet provides virtually no executable code, commands, or sequenced workflow with validation. It reads as a scaffold awaiting real examples rather than a usable skill.
Suggestions
Fill each Pattern with a complete, copy-pasteable code example (task definition, OpenAI integration with retries, cron-scheduled task).
Expand Sharp Edges solutions into actual commands/snippets (e.g. `export async function task(...)`, `task.tool({ idempotencyKey: ... })`) instead of bare comments.
Add a sequenced workflow with a validation checkpoint for at least one batch/long-running scenario, and remove the duplicated persona paragraph.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and sectioned, but the opening persona paragraphs ('You are a Trigger.dev expert...', 'You've built AI pipelines...') duplicate the frontmatter and add no actionable knowledge, matching 'mostly efficient but includes some unnecessary explanation'. | 3 / 5 |
Actionability | The Patterns are bare titles with no code ('Basic Task Setup / Setting up Trigger.dev in a Next.js project'), and the Sharp Edges 'solutions' are inert comments ('# Configure explicit timeouts:') with no executable code or commands, matching 'entirely vague or abstract; only describes rather than instructs'. | 1 / 5 |
Workflow Clarity | No multi-step sequence exists anywhere in the body and there are no validation/checkpoint steps despite the skill covering batch and long-running tasks; this fits 'steps missing or incoherent; no sequence; no validation for risky operations'. | 1 / 5 |
Progressive Disclosure | Content is organized into clearly labeled sections (Capabilities, Patterns, Anti-Patterns, Sharp Edges, Related Skills) with no bundle files to navigate; structure is good with minor gaps (thin stub sections), placing it at the 4 anchor rather than the fully-realized 5. | 4 / 5 |
Total | 9 / 20 Passed |