Purpose
Produce a rigorous, dimension-by-dimension readiness assessment that tells a nonprofit leader whether their program is actually ready to scale — with a numeric readiness score, the specific gaps most likely to derail expansion, and a sequenced plan to close them before committing resources. Replaces gut-feel expansion decisions with a defensible framework a board or funder will trust.
When to Use
Invoke this skill when the user asks to:
- Evaluate whether a program is ready to expand to new sites, cities, or regions
- Assess scaling readiness before a growth campaign or capital raise
- Answer a board or funder question about whether the organization can grow
- Diagnose why a previous replication attempt struggled and whether to try again
- Decide between deepening current impact vs. expanding reach
- Build the readiness case (or the "not yet" case) for a strategic plan
Inputs Required
Before starting, collect:
- Program description: What the program does, who it serves, and the core model in 3–5 sentences
- Current scale: Number of sites, participants served annually, years in operation
- Scale target: Where and how far they want to grow (e.g., 3 sites → 12 sites in 3 years; new geography; new population)
- Evidence available: Any outcome data, evaluations, RCTs, or measurement in place
- Leadership and team: Size, key roles filled/unfilled, tenure of leadership, and named second layer
- Funding picture: Annual budget, funding mix (grants/earned/individual/government), and reserve level
- Model documentation: Whether the model is written down, manualized, or lives in founders' heads
If evidence base or funding detail is thin, proceed with the information given, flag the gap explicitly as an assessment limitation, and score conservatively.
Instructions
Step 1: Score the Evidence Base (0–20 points)
Determine whether the program can prove it works well enough to be worth replicating.
- Outcome clarity: Are outcomes clearly defined and measured, or only outputs (attendance, sessions delivered)? Outputs alone cap this dimension.
- Strength of evidence: Anecdotal (0–5) → consistent internal outcome data (6–12) → external/quasi-experimental evaluation (13–17) → RCT or replicated study (18–20)
- Attribution: Is there a credible link between the program and the outcomes, or could other factors explain results?
- Consistency across sites/cohorts: Does the program produce similar results in different contexts, or only in the flagship site? Cap the score at 12 if outcomes are undefined or only outputs are tracked.
Step 2: Score Leadership & Organizational Capacity (0–20 points)
Determine whether the people and systems can absorb growth.
- Leadership depth: Founder-dependency is the top scaling risk. A named, capable second layer of leadership scores high; a single indispensable founder scores low.
- Operational systems: Are HR, finance, data, and reporting systems built for one site or many? Manual, personality-driven systems cap this dimension.
- Hiring and training pipeline: Can the org recruit and onboard staff who deliver the model faithfully at a new site?
- Board and governance readiness: Does governance support and stress-test growth, or rubber-stamp it? Cap the score at 10 if the program cannot run without the founder's daily involvement.
Step 3: Score Model Replicability (0–20 points)
Determine whether the model can be reproduced by people other than the originators.
- Codification: Is the model documented in a manual, curriculum, or playbook (high) or held tacitly (low)?
- Core vs. adaptable components: Has the org identified which elements are non-negotiable "active ingredients" vs. which can flex by context? Inability to name the core caps this dimension.
- Fidelity measurement: Is there a way to check whether a new site is actually running the model?
- Context dependence: Does the model rely on rare local conditions (a specific partner, a specific person, a unique regulation) that won't exist elsewhere? Cap the score at 10 if the model has never been documented.
Step 4: Score Funding Sustainability (0–20 points)
Determine whether growth is financially survivable.
- Funding diversity: Reliance on one funder for >50% of the budget is a critical scaling risk.
- Unit economics: Is the cost-per-participant known, and does it hold, improve, or worsen at scale?
- Growth capital vs. operating funding: Is there dedicated growth/risk capital, or would expansion cannibalize core operations?
- Reserves and runway: Months of operating reserve; ability to absorb a slow ramp at new sites.
- Revenue path at scale: Is there a credible plan to fund the larger organization, not just the pilot expansion? Cap the score at 10 if a single funder exceeds 60% of the budget or reserves are under two months.
Step 5: Score External Environment (0–20 points)
Determine whether the outside conditions support expansion.
- Demand and need: Is there verified demand in target locations, or an assumption of demand?
- Competitive/collaborative landscape: Are there existing providers, and is the org's role additive or duplicative?
- Policy and funding climate: Do policy trends and public funding availability favor or threaten the model?
- Partnership readiness: Are viable local partners identified in target geographies?
- Timing risk: Any near-term external shifts (elections, funding cycles, regulatory changes) that argue for waiting?
Step 6: Total the Score and Assign a Readiness Verdict
Sum the five dimensions (0–100) and assign a verdict:
- 80–100 — Ready to scale: Proceed; focus on execution discipline and fidelity.
- 60–79 — Scale with conditions: Growth is viable once named gaps are closed; specify the conditions.
- 40–59 — Not yet — build first: Real potential, but foundational gaps must be addressed before committing to expansion.
- Below 40 — Deepen, don't scale: Prioritize strengthening core impact and evidence over reach. State the single lowest-scoring dimension as the binding constraint.
Step 7: Rank the Gaps and Build the Pre-Scale Action Plan
- List the top 5 gaps in priority order, weighted by how likely each is to cause scaling failure (not by ease of fixing).
- For each gap: the specific risk it creates during expansion, the concrete action to close it, and a realistic time horizon (0–3 / 3–6 / 6–12 months).
- End with an explicit recommendation: scale now, scale after specified conditions, or hold — stated plainly, not hedged.
Output Format
- Structure: Five scored dimension sections, each with score, reasoning, and sub-factor notes; a scoring summary table; a verdict; a ranked gap list with actions
- Length: 1,000–1,400 words
- Format: Structured document — prose reasoning per dimension, a summary scoring table, numbered gap list
- Sections: Evidence Base → Leadership & Capacity → Model Replicability → Funding Sustainability → External Environment → Scoring Summary Table → Readiness Verdict → Top 5 Gaps & Pre-Scale Action Plan → Final Recommendation
- Tone: Strategic advisor to a nonprofit board — candid, evidence-driven, willing to say "not yet"; never inflates readiness to be encouraging
Quality Checklist
Before delivering output, verify:
- [ ] All five dimensions are scored on the 0–20 scale with stated reasoning
- [ ] The total score (0–100) is summed correctly and mapped to the matching verdict band
- [ ] Scoring caps are applied where triggers are met (founder-dependency, undocumented model, single-funder concentration, output-only measurement)
- [ ] The binding constraint (lowest dimension) is named explicitly
- [ ] Exactly 5 gaps are ranked by scaling-failure risk, each with a concrete action and time horizon
- [ ] A plain scale / scale-with-conditions / hold recommendation is stated without hedging
Notes
- Founder-dependency and single-funder concentration are the two most common reasons scaling attempts fail — weight them heavily even when other dimensions look strong.
- "Not yet" is a legitimate and often more valuable answer than "yes"; premature scaling of an under-evidenced or under-documented model damages both impact and reputation.
- When outcome evidence is weak, recommend a stronger evaluation before expansion rather than scaling and hoping the evidence follows.
- Distinguish scaling reach (more sites, more people) from scaling depth (better outcomes per participant); some organizations score low on readiness precisely because deepening is the wiser move.
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