Purpose
Turn a messy list of worthy causes into a defensible, ranked set of focus areas by scoring each against a structured framework — so a donor or foundation can commit capital with clear reasoning rather than intuition or momentum. Produces a decision artifact that survives board scrutiny and can be revisited annually.
When to Use
Invoke this skill when the user asks to:
- Decide which cause areas a donor or foundation should fund
- Narrow a long list of candidate causes into a focused giving strategy
- Compare cause areas using effective altruism or strategic philanthropy criteria
- Justify a philanthropic focus to a family, board, or investment committee
- Reassess an existing giving portfolio for concentration or drift
- Balance high-impact causes against personal or founder values
Inputs Required
Before starting, collect:
- Candidate cause areas: The list of causes under consideration (e.g., global health, criminal justice reform, climate adaptation, local education)
- Annual giving budget: Approximate capital to deploy per year
- Time horizon: Single-year, multi-year commitment, or perpetuity
- Funder's comparative advantages: Existing expertise, networks, geography, reputation, or capital scale that make certain causes a better fit
- Values and constraints: Personal, religious, family, or mission-driven priorities and any explicit exclusions
- Risk appetite: Preference for proven interventions vs. high-risk/high-reward or field-building bets
- Role preference: Sole funder, co-funder, or catalytic/first-money-in
If risk appetite or role preference is missing, assume moderate risk tolerance and an openness to co-funding, and note the assumption.
Instructions
Step 1: Normalize the Candidate List
Restate each candidate cause area at a consistent altitude. If the user mixes broad domains ("health") with narrow interventions ("bed nets"), flag the mismatch and reframe to comparable scope. Aim for 4–10 comparable candidates. If more than 10, cluster related causes before scoring.
Step 2: Score Each Cause on Five Criteria (1–10 scale)
Apply each criterion consistently across all candidates. Justify every score in one sentence — no bare numbers.
Criterion 1 — Scale (weight 25%) How large is the problem? Consider number of people or beings affected, severity of harm, and the size of the gap if left unaddressed.
- Anchor: 10 = affects hundreds of millions with severe, irreversible harm; 3 = affects a bounded local population with moderate, recoverable harm
Criterion 2 — Tractability (weight 25%) How much progress is achievable per dollar? Consider whether proven interventions exist, whether the problem yields to funding, and the marginal cost of measurable improvement.
- Anchor: 10 = well-evidenced interventions with clear cost-per-outcome; 3 = diffuse, systemic, or politically gridlocked with weak feedback loops
Criterion 3 — Neglectedness (weight 20%) How under-resourced is the area relative to its scale? More existing funding lowers the marginal value of an additional dollar.
- Anchor: 10 = severely underfunded, few active funders; 3 = crowded field with large government or philanthropic flows already present
Criterion 4 — Funder's Comparative Advantage (weight 20%) Does this funder have expertise, networks, geographic access, reputation, or capital structure that makes them unusually effective here? A cause where the funder can do something others cannot scores high.
- Anchor: 10 = funder brings a decisive edge no generic funder has; 3 = no particular advantage over any other donor
Criterion 5 — Values Fit (weight 10%) Alignment with the funder's mission, personal conviction, and durability of commitment. Low scores here predict abandonment; this criterion protects staying power, not just impact.
- Anchor: 10 = deep, durable personal conviction; 3 = intellectually interesting but no emotional or mission anchor
Step 3: Build the Weighted Scoring Matrix
Compute a weighted total for each cause: (Scale × 0.25) + (Tractability × 0.25) + (Neglectedness × 0.20) + (Comparative Advantage × 0.20) + (Values Fit × 0.10). Present all candidates in a single table, sorted by weighted total.
Step 4: Sensitivity Check
Identify any cause whose ranking flips under a plausible reweighting (e.g., a values-first funder weighting Values Fit at 30%). Name the 1–2 causes most sensitive to weighting choices and state what assumption is driving their position. This exposes where the ranking is genuinely close vs. decisive.
Step 5: Recommend a Portfolio
Do not simply pick the top score. Recommend an allocation:
- Anchor cause(s): 1–2 highest-scoring causes receiving the majority of capital
- Secondary cause(s): 1–2 causes for diversification, learning, or values expression
- Optional exploratory allocation: A small percentage (typically 5–15%) for a high-risk/high-upside or field-building bet, if risk appetite allows Assign a suggested percentage of the annual budget to each, summing to 100%.
Step 6: Name the Trade-offs and Next Steps
State plainly what the funder is giving up by this allocation. Then list 3–5 concrete next steps: organizations or intermediaries to diligence, questions to resolve, and a suggested review cadence.
Output Format
- Structure: Normalized candidate list → scoring rationale by cause → weighted matrix table → sensitivity note → portfolio allocation → trade-offs and next steps
- Length: 900–1,300 words
- Format: Prose reasoning plus one scoring matrix table; portfolio allocation as a labeled list with percentages
- Sections: Candidate List → Scoring Rationale → Weighted Scoring Matrix → Sensitivity Check → Recommended Portfolio → Trade-offs & Next Steps
- Tone: Strategic philanthropy advisor — rigorous, candid about uncertainty, willing to make a recommendation and defend it
Quality Checklist
Before delivering output, verify:
- [ ] Every candidate cause is scored on all five criteria with a one-sentence justification per score
- [ ] The weighted matrix uses the exact weights (25/25/20/20/10) and totals compute correctly
- [ ] The table is sorted by weighted total, highest first
- [ ] The portfolio allocation percentages sum to exactly 100%
- [ ] The sensitivity check names at least one cause whose rank depends on weighting
- [ ] Trade-offs are stated explicitly — what the funder gives up is named, not glossed
Notes
- The highest-scoring cause is not automatically the sole recommendation — durability (Values Fit) and diversification often justify a portfolio over a single bet.
- Neglectedness scores age quickly; if a cause is trending in the funding world, note that today's neglected area may be crowded within a few years.
- For funders with strong comparative advantage in a lower-scale area, that edge can outweigh raw scale — a decisive advantage in a small field often beats a marginal one in a large field.
- Recommend the funder revisit this matrix annually or whenever budget, capacity, or the funding landscape shifts materially.
How to use this skill
This file is a Claude Code skill in Anthropic's standard format — markdown with YAML frontmatter at the top.
Installing in Claude Code:
~/.claude/skills/<folder-name>/SKILL.md— auto-loads in every session anywhere on your machine (recommended for skills you'll use across multiple projects)<your-project>/.claude/skills/<folder-name>/SKILL.md— auto-loads only when working in that project (recommended for project-specific skills)
Restart Claude Code or open a new session to register.
Using in Claude.ai, ChatGPT, Gemini, or other AI tools:
- Drag this file into a new chat, or copy and paste its contents
- Send your task or request as your next message — the AI will apply the skill where it fits
For Claude Code skill details: https://docs.anthropic.com/en/docs/claude-code/skills