WRITING

Fact-preserving layered summary

Create one-line, key-point, and evidence layers in one pass.

PROMPT
Selector policy: Treat selected presets as operating requirements for strategy, format, and validation—not decorative labels. If a preset conflicts with supplied evidence, preserve the evidence and state the conflict and adjustment. Never invent unique facts absent from the preset or source.

Role: an evidence-led professional editor

Objective: Create a layered summary that preserves key facts and conditions.

Inputs:
- Source material: {{source_material}}
- Audience: {{audience}}
- Constraints: {{constraints}}

Workflow:
1. Identify the material’s purpose, author perspective, cutoff date, and structure.
2. Extract central claims, evidence, figures, dates, conditions, exceptions, and counterarguments.
3. Distinguish reported fact from opinion and do not invent causal links.
4. Compress into three layers: one-sentence takeaway, key points, and evidence detail.
5. Disclose material scope and uncertainty omitted by the summary.

Output format:
## One-sentence takeaway
## Key points
## Evidence and conditions
## Exceptions and counterarguments
## Omitted scope and uncertainty

Quality rules:
Use only supplied material and verifiable facts. When information is missing, do not guess: state the gap, any necessary assumption, and its effect on the result. Before concluding, check every constraint and required output field.

Negative prompt

Unsupported facts, fabricated citations, vague conclusions, missing constraints, unverified claims, and unrequested scope expansion

Workflow

  1. Fill variables with concrete facts, scope, actors, and desired outcomes rather than abstract adjectives.
  2. Check the assembled prompt for conflicting conditions, then paste it into a compatible tool.
  3. Treat the first answer as a draft and refine one failed condition at a time.

Verification

  • Confirm every goal, constraint, and output field is present.
  • Check figures, dates, quotations, and code against primary sources and real tests.
  • Keep a human responsible for evidence, feasibility, and final approval.