{ "schema_version": 2, "kind": "shortening-method", "format": "agent-skill", "id": "predictions", "name": "Prediction ledger", "category": "Work", "summary": "Extract forecasts with their dates, confidence, and checks.", "use_cases": [ "Forecast reports", "Strategy documents", "Prediction tracking" ], "word_count": 108, "url": "https://sho.rten.it/methods/predictions/", "instructions_url": "https://sho.rten.it/methods/predictions/SKILL.md", "skill_url": "https://sho.rten.it/methods/predictions/SKILL.md", "json_url": "https://sho.rten.it/methods/predictions/llms.txt", "plain_text_url": "https://sho.rten.it/methods/predictions/prompt.txt", "license": "MIT", "sources_url": "https://sho.rten.it/sources/#predictions", "skill_name": "predictions", "skill_description": "Extract forecasts with their dates, confidence, and checks. Use for Forecast reports, Strategy documents, Prediction tracking.", "agents_md_url": "https://sho.rten.it/methods/predictions/AGENTS.md", "sources": [ { "title": "Fabric ยท extract_predictions", "url": "https://github.com/danielmiessler/Fabric/blob/b682dad740f24e85ce9a48d23babc6780dd476ac/data/patterns/extract_predictions/system.md", "repository": "https://github.com/danielmiessler/Fabric", "revision": "b682dad740f24e85ce9a48d23babc6780dd476ac", "path": "data/patterns/extract_predictions/system.md", "license": "MIT", "license_url": "https://github.com/danielmiessler/Fabric/blob/b682dad740f24e85ce9a48d23babc6780dd476ac/LICENSE", "license_file": "licenses/danielmiessler--fabric.txt", "copyright": "Copyright (c) 2012-2024 Scott Chacon and others", "repository_stars": 43885, "checked_at": "2026-09-11T05:14:00Z", "license_scope": "Root MIT license covers this pinned prompt. No nested license or NOTICE applies.", "adaptation": "Retains concise prediction bullets plus a four-column ledger. Replaces source instruction to extract even without content with evidence requirements and explicit missing-value handling." } ], "instructions": "Extract the predictions actually present in the supplied content.\n\nFirst list each distinct prediction as a bullet of at most 16 words. Then create a Markdown table with these columns: Prediction, Confidence, Date, and How to verify.\n\nKeep the predicted event, scope, timeframe, and conditions accurate. Report confidence only when the source states it. Preserve dates and quantities exactly. Describe an objective verification test when the source supplies one; label a test you propose as \"Suggested.\"\n\nUse \"Not stated\" for missing dates or confidence. Do not fabricate forecasts from missing content or convert a possibility into a promise. Remove duplicates. Output the list and table without unrelated commentary.", "example": { "context": "Forecast extraction with a conditional target and missing confidence", "before": "The report forecasts that weekly deliveries in the pilot region will exceed 1,000 by 2027-06-30, provided the second warehouse opens on schedule. The authors give this forecast 70% confidence and say to verify it against the weekly operations report. They also predict that pilot-region cold-storage costs will fall after the second warehouse opens, but give no amount, deadline, confidence, or verification method for that prediction. The report makes no forecasts for other regions. These are forecasts rather than commitments; neither outcome has been observed yet.", "after": "- Pilot-region deliveries: >1,000/week by 2027-06-30, if the second warehouse opens on schedule.\n- Pilot-region cold-storage costs fall after the second warehouse opens.\n\n| Prediction | Confidence | Date | How to verify |\n| --- | --- | --- | --- |\n| Pilot-region deliveries >1,000/week if warehouse opens on schedule | 70% | 2027-06-30 | Weekly operations report |\n| Pilot-region cold-storage costs fall after warehouse opens | Not stated | Not stated | Suggested: Compare pre/post-opening costs. |", "must_preserve": [ "Pilot-region deliveries above 1,000/week by exact date", "Warehouse must open on schedule; 70% confidence; supplied weekly-report verification", "Separate cost-decrease prediction follows warehouse opening; no amount, deadline, confidence, or source verification method", "Suggested test is labelled; both outcomes remain forecasts", "Two prediction bullets each at most 16 words" ], "omitted": [ "Omits discussion of regions with no predictions. The cost comparison is labelled as a suggested verification test, not a source-provided method." ], "kind": "illustrative" } }