Strip overspecified instructions from an artifact. Trust the model's intuition — prescribe intent, not format.
You're over-specifying. The artifact tells the reader how to format output instead of what to accomplish. That scaffolding was necessary for weaker models. It constrains stronger ones.
When writing skills, prompts, or instructions, you default to showing exactly what the output should look like — filled-in example tables, prescribed column names, template formats. This feels helpful but it creates a ceiling. The model matches your template instead of thinking about what the specific problem needs.
For each instruction in the artifact, ask: is this intent or format?
| Intent (keep) | Format (cut) |
|---|---|
| Summarize the results in a table | Use these columns: Name, Status, Duration, Owner |
| Assessments should be opinionated | Acceptable values: "ready", "blocked", "needs work" |
| Group items by category | Categories: Infrastructure, Frontend, Backend, Testing |
| Commit your changes after each step |
Run git add -A && git commit -m "step N: description" |
Filled-in example tables, prescribed column names, lists of acceptable values, step-by-step commands for things the model knows how to do. If an instruction only exists to show "what the output should look like" — cut it. The model knows how to make tables, pick column names, and write git commands.
Exception: Keep format prescriptions that encode domain insight or non-obvious constraints.
The user has an artifact that over-specifies. Distill it now.