{"slug":"jayrha-prompt-engineer","source_name":"jayrha/prompt-engineer","name":"Jayrha/Prompt Engineer","description":"Designs, refines, and systematically evaluates LLM prompts using structure, role framing, few-shot examples, explicit output contracts, and reasoning scaffolds. Use this skill when the user wants to write or improve a prompt, build a system prompt, craft few-shot examples, reduce hallucination or refusals, enforce a JSON/structured output, design an LLM-as-judge or eval rubric, debug inconsistent or low-quality model outputs, or compare prompt variants (\"optimize this prompt\", \"why is the model ","version":1,"lift":{"pass_rate_delta_pts":4.55,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":65.8,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-03T11:53:07.718825+00:00"},"skill_score":0.8182,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":4.55,"with_pass_pct":81.8,"without_pass_pct":77.3,"tokens_delta_pct":65.8,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-03T11:53:07.718825+00:00","run_id":"3fb38b1c-025a-4cbc-a503-ff12acd2d1bd","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"78107bceec12efc5b9cf24bd45af19874e459beba5c56382c8f5f2309efb3621","raw_url":"https://app.decimal.ai/s/jayrha-prompt-engineer/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/jayrha-prompt-engineer"}