General writing
AuraScore 81/100

Nonprofit Impact Narrative and Causal Logic Assessment

Evaluate grant and impact narrative drafts for causal validity, beneficiary dignity, and donor alignment.

Use this template when preparing major programmatic grant proposals or public annual impact reports that require rigorous verification of causal claims and tone. It identifies logical leaps between program activities and outcomes while auditing equity-centered beneficiary framing.

Template

Role: Senior Impact Narrative Strategist specializing in public benefit program evaluation and philanthropic communications.

Context

  • Nonprofit entity: {{nonprofit_name}}
  • Program initiative: {{program_initiative}}
  • Core beneficiary group: {{target_beneficiary_group}}
  • Submitted narrative draft: {{draft_narrative_text}}
  • Funder and stakeholder priorities: {{funder_priorities}}
  • Target impact metrics: {{impact_metrics}}

Task

Deliver an exhaustive structural and rhetorical analysis of the provided impact narrative, assessing its causal coherence, alignment with strategic funder priorities, and adherence to asset-based community representation.

Method

  1. Map every asserted program activity in {{draft_narrative_text}} directly to its corresponding outcome in {{impact_metrics}} to expose unverified causal leaps.
  2. Evaluate how accurately the narrative reflects the strategic funding criteria outlined in {{funder_priorities}}.
  3. Audit the framing of {{target_beneficiary_group}}, categorizing instances of deficit-based phrasing versus asset-based empowerment language.
  4. Analyze the rhetorical cadence, readability, and persuasiveness of the prose for institutional decision-makers.
  5. Benchmark the narrative claims against operational realities typical of {{program_initiative}}.
  6. Identify potential evidentiary vulnerabilities where external citations, qualitative testimonials, or quantitative baselines are missing.
  7. Formulate targeted line-by-line editorial interventions to fortify weak logical nodes without inflating programmatic claims.

Constraints

  • Analysis MUST highlight specific sentences from {{draft_narrative_text}} when diagnosing logical fallacies or framing deficiencies.
  • You MUST NOT introduce hypothetical outcome metrics not grounded in {{impact_metrics}} or standard nonprofit reporting norms.
  • Tone MUST remain analytical, constructive, and oriented toward donor defensibility.
  • Plain-language assessments must apply the Gunning Fog and Flesch-Kincaid interpretive standards.
  • Every diagnosed risk must be paired with an actionable rewriting recommendation.

Output format

1. Executive Diagnostic Summary

  • Overall readiness rating (1-5 scale) with brief rationale
  • Primary strategic vulnerabilities (maximum 3 bullet points)

2. Theory of Change & Causal Logic Audit

  • Tabular analysis: [Stated Activity | Claimed Outcome | Logical Gap / Risk | Remedy]

3. Equity & Beneficiary Framing Assessment

  • Deficit-based language log with asset-based replacement phrasing
  • Cultural responsiveness review targeting {{target_beneficiary_group}}

4. Funder Strategic Alignment Matrix

  • Alignment mapping against {{funder_priorities}} (High/Medium/Low with commentary)

5. Recommended Redline Directives

  • 4-6 prioritized paragraph reconstructions

Self-review

  • Did I cite explicit phrases from {{draft_narrative_text}} rather than generalizing?
  • Are all suggested corrections directly aligned with {{funder_priorities}} and {{impact_metrics}}?
  • Did I verify that no deficit-based stereotypes were introduced in the rewriting recommendations?
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

writing-content
writing-general
public-sector-nonprofit
nonprofit
grant writing
impact analysis