Simulation run on this device. Scenario values are not sent anywhere — the engine is fully local.
prompting studio · free
Prompt Linter
Lint prompt text for ambiguity, conflicts, stale rules, and token waste.
Which words in this prompt are doing nothing?
Engine 1.0.0 · studio
- Words
- 29
- Estimated tokens
- 49
- Findings
- 1
- Worst severity
- error
[info] Vague qualifier “Just” — the model can't measure it. Define it or delete it.
[info] Vague qualifier “basically” — the model can't measure it. Define it or delete it.
[info] Vague qualifier “clearly” — the model can't measure it. Define it or delete it.
[info] Vague qualifier “obviously” — the model can't measure it. Define it or delete it.
[error] Possible conflict (brevity vs depth): the prompt both requires and forbids overlapping behaviors.
Method
- Deterministic lint pass: duplicate instructions, vague qualifiers the model can't measure, contradiction pairs (always vs sometimes, concise vs thorough), staleness, and a rough tokens estimate.
- Rules are heuristic on purpose — reading the findings is the lesson; a clean pass still needs a behavioral eval.