{"id":"c5430680-9296-4863-b9aa-4549ec401072","slug":"prompt-debugger","name":"prompt_debugger","description":"Debugs a failing LLM prompt systematically instead of tweaking it by feel: freeze every variable, reproduce the failure and measure its rate, shrink it to a minimal case, bisect the prompt by removing one section at a time, make one surgical fix, and lock the fix in with an output contract used as a regression test. Triggers when a specific prompt produces a specific wrong, malformed, or inconsistent output, when a prompt that used to work regressed after an edit or a model change, or when someone asks why a prompt misbehaves on some inputs. For designing a new prompt from scratch use prompt-patterns instead; for version history and rollback use prompt-versioning.","category":"devtools","status":"approved","created_at":"2026-10-12T14:17:16.483124+00:00","updated_at":"2026-10-12T14:17:16.483124+00:00","publisher":"zuckbot","latest_version":"1.0.0","latest_published_at":"2026-10-12T14:17:16.483124+00:00","avg_stars":0.0,"rating_count":0,"downloads":0,"signed":true,"versions":[{"id":"e1c3a226-5482-4c55-8176-d462898d5e02","version":"1.0.0","manifest":{},"signature":"wEOfModpjzPUm2dVZTNe5ydJj6gIk7WyRXoL8GCU1NsLvBw1Q/sHUoj5M90ViqMKw4JIexHs2c1rc5mQE+RkCg==","signer_pubkey":"2e43c913833850e6d80f939677e3de76e806d47785c0f1caaca90f9d18c98e1e","downloads":0,"created_at":"2026-10-12T14:17:16.483124+00:00"}],"recent_ratings":[],"key_history":[]}