Purpose
Produce a structured landscape map of a cause area — scale, actors, evidence, funding gaps, and leverage points — so a donor or program officer can see where a new commitment would do the most marginal good before any money moves. Replaces months of scattered reading with a single diligence brief that ends in a defensible entry strategy.
When to Use
Invoke this skill when the user asks to:
- Research a new cause area before making a philanthropic commitment
- Map the funders, organizations, and intervention models already active in an issue
- Find the funding gaps or neglected sub-issues within a broader cause
- Compare where a gift would have the highest marginal impact
- Build a diligence brief or board memo to justify entering a new issue area
- Decide between a few candidate sub-strategies within a cause they've already chosen
Inputs Required
Before starting, collect:
- Cause area: The issue to map (e.g., climate adaptation, early childhood development, criminal justice reform)
- Geographic scope: Local / national / global, and any priority regions
- Funding capacity: Approximate annual giving available for this area
- Time horizon: One-time gift, multi-year commitment, or open-ended program
- Risk appetite: Proven interventions only vs. willingness to fund early-stage or high-variance bets
- Donor's existing assets: Any non-cash leverage — network, convening power, advocacy capacity, prior grantees
- Outcome the donor cares most about: The specific change they want to see (e.g., fewer incarcerations, lower emissions, improved literacy)
If funding capacity or risk appetite is missing, assume a multi-year mid-size program with moderate risk tolerance and note the assumption.
Instructions
Step 1: Scale of the Problem
Quantify the issue so leverage can be judged against magnitude.
- Headline magnitude: The single number that frames the problem (people affected, tons emitted, dollars lost, lives at stake)
- Trend direction: Is the problem growing, stable, or shrinking — and how fast?
- Distribution: Who bears the burden most heavily (geography, demographic, sub-population)?
- Tractability signal: Is this a problem where additional resources plausibly move outcomes, or one constrained by politics/structure regardless of money?
- Flag the confidence level of each figure (well-established / contested / estimate) — do not present uncertain numbers as settled.
Step 2: Key Actors Map
Inventory who is already working in the space, organized by role.
- Implementers: Leading nonprofits, NGOs, and service providers — note their model and rough scale
- Researchers / evaluators: Academic centers, think tanks, and evidence shops shaping the field
- Government / policy actors: Agencies, programs, or legislation that dominate the funding or rule-setting
- Advocacy / movement actors: Coalitions and organizers driving narrative or political change
- For each category, name 3–5 actors and note the dominant model each represents. Identify which models are crowded and which are thinly staffed.
Step 3: Funder Landscape
Map who is already paying, so the donor can find the white space.
- Major institutional funders: The foundations and large donors who define the field's priorities
- Aggregate funding flow: Roughly how much philanthropic and public money enters this area annually, and is it rising or falling?
- Funder consensus vs. contrarian zones: What does "smart money" agree on, and where is conventional wisdom possibly wrong?
- Co-funding vs. lonely-funder dynamics: Are there pooled funds, collaboratives, or matching opportunities — or would the donor be acting alone?
Step 4: Evidence Base
Assess what's actually known to work. Rate each major intervention type on an evidence tier:
- Tier A — Strong: Multiple RCTs or rigorous quasi-experimental studies show effect
- Tier B — Promising: Some causal evidence, replication still thin
- Tier C — Theoretical / contested: Logic is sound but outcome evidence is weak or mixed
- Tier D — Faith-based: Popular and well-funded but no credible outcome evidence For each tier, note the most credible interventions and cite the type of evidence behind them. Explicitly flag any popular, heavily funded interventions sitting in Tier C or D — these are common misallocation traps.
Step 5: Funding Gaps
Identify where marginal dollars are scarcest relative to need or promise.
- Neglected sub-issues: High-need or high-evidence segments that few funders touch
- Geographic gaps: Regions where the problem is acute but philanthropic attention is thin
- Stage gaps: Is the gap in research, piloting, scaling, or sustaining proven programs?
- Function gaps: Is direct service overfunded while advocacy, infrastructure, or evaluation starves (or vice versa)?
- Rank the 3–4 most promising gaps by the combination of neglect, tractability, and fit with the donor's assets.
Step 6: Highest-Leverage Intervention Points
Synthesize Steps 1–5 into where this specific donor should act. For each of the top 3 leverage points:
- The point: What to fund and through what mechanism
- Why it's high-leverage: The scale × evidence × neglect logic in 2–3 sentences
- Fit with donor assets: Why this donor in particular is well-positioned for it
- Marginal impact estimate: Directional sense of what the donor's capacity could plausibly buy
- Key risk: The most likely reason it underdelivers
Step 7: Entry Strategy Recommendation
Make a clear, opinionated recommendation:
- The single highest-priority leverage point to start with and why
- A suggested first move (a learning grant, a flagship commitment, or a convening) calibrated to the donor's risk appetite
- The 2–3 questions to resolve in deeper diligence before deploying the full commitment
- Be decisive — name a path rather than listing equal options.
Output Format
- Structure: Seven labeled sections following the steps; actor and funder maps as grouped bullets; evidence base as a tiered list; leverage points as structured sub-entries
- Length: 1,100–1,500 words
- Format: Structured diligence brief — scannable headers, bullets within sections, prose only for synthesis and recommendation
- Sections: Scale of the Problem → Key Actors Map → Funder Landscape → Evidence Base → Funding Gaps → Highest-Leverage Intervention Points → Entry Strategy Recommendation
- Tone: Senior program officer — analytical, skeptical of fashionable interventions, honest about uncertainty, decisive at the close
Quality Checklist
Before delivering output, verify:
- [ ] All seven sections are present and in order
- [ ] Every quantitative figure carries a confidence flag (established / contested / estimate)
- [ ] Each actor category names 3–5 specific actors with their model noted
- [ ] Each major intervention is assigned an evidence tier (A/B/C/D) with the evidence type named
- [ ] At least one heavily funded but weakly evidenced intervention is explicitly flagged, if one exists in the field
- [ ] The top 3 leverage points each include scale × evidence × neglect reasoning and a named key risk
- [ ] The entry strategy ends with one clear recommended first move — not a menu of equal options
Notes
- The most valuable output is usually the funding-gap section: donors overwhelmingly cluster on visible, fashionable interventions, and neglect is where marginal dollars buy the most.
- Be willing to tell the donor the cause area is crowded and well-resourced — sometimes the honest answer is "the marginal value here is low, consider an adjacent gap."
- When evidence is thin, say so plainly rather than inflating Tier C interventions into Tier A; a donor entering on false confidence is a worse outcome than a cautious one.
- This map is a starting point for diligence, not a substitute for direct conversations with operators and grantees in the field — recommend the donor pressure-test the top leverage point with 3–5 practitioner interviews before committing.
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