Search the docs, videos, blog, apps, teams, skills and release notes.
At a glance
What it is
Guide to measuring and communicating social impact including logic models, theory of change, outcome indicators, data collection methods, reporting, and evaluation frameworks.
A skill is a written procedure a bot loads when a job calls for it. This one is a single file, SKILL.md, and the whole file is on this page.
Each of these library teams gives its bots this skill. Import one and look inside first.
The whole file, exactly as it downloads. Read it before you rely on it.
SKILL.md
403 lines · 2,567 words
Use this skill when:
The user needs to measure and communicate social impact using logic models or theory of change frameworks
The user wants help defining outcome indicators, designing data collection methods, or building evaluation frameworks
The user needs to create impact reports for funders, stakeholders, or board members
Guide to measuring and communicating social impact including logic models, theory of change, outcome indicators, data collection methods, reporting, and evaluation frameworks.
Nothing. It ships with Murage, which is open source. Your bots run on the AI plan you already have.
Yes. Open it in Settings → Skills to read, edit or duplicate it. Skill Guard scans it again after every edit.
Download the app, connect the AI you already pay for, and tell your Chief of Staff what needs doing. Plan on about ten minutes from install to a working team.
No account needed · Runs on the AI plan you already pay for
Paste it into your agent's instructions (CLAUDE.md, AGENTS.md or a custom GPT), or add it to a bot in Murage.
Ask Ember for the bot, then switch the skill on in its settings.
Step 1
Send your Chief of Staff this message. It proposes the bot and its role first, and creates it when you say go.
Send this to Ember
“Create a bot that uses the Social Impact Measurer skill, and show me the plan first.”
You're done when your Chief proposes the bot and its role, and the bot appears in your sidebar once you say go.
Step 2
You're done when you see the bot’s skills and the library.
Step 3
You're done when the skill shows as on for that bot.
Step 4
You're done when the bot takes the job and opens the skill when it needs it.
Prefer to do it yourself? Choose + in the sidebar, then New Bot.Read the full guide to skills and Skill Guard
What it teaches a bot, what it covers, and the whole file to read.
What it covers
When to Use
Process
Questions to Ask First
Logic Models
Theory of Change
Outcome Indicators
Data Collection Methods
Impact Reporting
Storytelling with Data
Evaluation Frameworks
Benchmarking
Technology Tools for Impact Measurement
Progression Path
Resources
Output Format
Example
Edge Cases
The user wants to demonstrate program effectiveness or compare intervention approaches
Do NOT use this skill when:
The user needs fundraising strategy rather than impact measurement (use fundraising-strategist instead)
The user wants to start a nonprofit rather than measure its impact (use nonprofit-starter instead)
The user needs general business analytics or KPIs (use relevant business skill)
Gather requirements. Ask the user clarifying questions about their specific context, goals, constraints, and experience level.
Analyze the situation. Review the information provided and identify key factors, challenges, and opportunities relevant to social impact measurer.
Develop the framework. Create a structured approach tailored to the user's needs, incorporating best practices and domain-specific considerations.
Deliver actionable output. Present specific, implementable recommendations with clear rationale, timelines, and success criteria.
Address edge cases. Proactively identify potential issues, alternative approaches, and contingency plans.
Use this skill when:
User needs guidance on social impact measurer
User asks about social impact measurer best practices or techniques
User wants a structured approach to social impact measurer
Do NOT use this skill when:
A more specialized skill exists for the specific subtopic
The request is outside the scope of social impact measurer
Before designing an impact measurement system:
What programs or services does your organization deliver?
What change are you trying to create in people's lives or in the community?
Who are your primary stakeholders (funders, board, community, government)?
What data do you currently collect? How?
What does your staff capacity for data collection look like?
Do funders require specific metrics or reporting formats?
What is your budget for evaluation? (Internal only / Can hire external evaluator)
How comfortable is your team with data and technology?
What decisions will impact data inform? (Program improvement, funding proposals, advocacy)
Have you measured impact before? What worked or didn't?
A visual representation of how your program works - the logical connection between what you invest, what you do, and what changes as a result.
INPUTS --> ACTIVITIES --> OUTPUTS --> OUTCOMES --> IMPACTInputs (Resources you invest):
Staff time and expertise
Funding
Facilities and equipment
Partnerships
Volunteer time
Curriculum or materials
Activities (What you do):
Deliver workshops
Provide counseling
Distribute food
Advocate for policy change
Mentor youth
Build housing
Outputs (Measurable products of activities):
Number of workshops delivered
Number of people served
Meals distributed
Policy briefs published
Mentor-mentee matches made
Units constructed
Outcomes (Changes in participants or community):
Short-term (during program): Increased knowledge, changed attitudes, new skills
Medium-term (after program): Changed behaviors, improved practices
Long-term (sustained): Improved conditions, new status
Impact (Broad, long-term change):
Systemic change in community conditions
Population-level improvements
Contribution to solving the root problem
| Component | Example |
|---|---|
| Inputs | 5 tutors, curriculum, classroom space, $50,000 budget, school partnership |
| Activities | Weekly 1-on-1 tutoring sessions, monthly parent workshops, teacher coordination |
| Outputs | 75 students tutored, 400 tutoring sessions delivered, 8 parent workshops held |
| Short-term outcomes | Students improve reading scores by 1 grade level, increased homework completion |
| Medium-term outcomes | Students pass standardized reading tests, improved school attendance |
| Long-term outcomes | Higher high school graduation rates, college enrollment |
| Impact | Reduced educational achievement gap in the community |
Start with your intended impact (work backward)
What long-term outcomes must happen to achieve that impact?
What medium-term outcomes lead to long-term outcomes?
What short-term outcomes lead to medium-term outcomes?
What activities produce those short-term outcomes?
What inputs do those activities require?
Test the logic: Does each arrow make sense? Is there evidence for the connections?
Logic model: Shows what you do and what results you expect (the "what")
Theory of change: Explains WHY your activities lead to outcomes (the "how" and "why")
Theory of change includes assumptions, evidence base, and external factors
Long-term goal: The ultimate change you seek
Preconditions: What must be true for the goal to be achieved
Interventions: Your specific programs and activities
Assumptions: Beliefs about why your approach will work
Evidence: Research or experience supporting your assumptions
External factors: Things outside your control that affect outcomes
Indicators: How you will know if change is happening
Template: "IF we [intervention/activities], THEN [outcomes] will result, BECAUSE [evidence/rationale], ASSUMING [assumptions]."
Example: "IF we provide weekly one-on-one tutoring to struggling readers in grades 2-4, THEN their reading scores will improve by at least one grade level within one school year, BECAUSE research shows that individualized instruction at early ages has the highest impact on literacy development (National Reading Panel), ASSUMING students attend at least 80% of sessions and receive family support for homework."
Specific: Clearly defined, everyone understands what is being measured
Measurable: Can be quantified or categorized
Achievable: Realistic target given resources and context
Relevant: Directly connected to the outcome you are measuring
Time-bound: Measured within a defined timeframe
Quantitative Indicators (Numbers):
Percentage of participants who achieve a benchmark
Average change in score from pre-test to post-test
Number of days employed in 6 months after program
Reduction in emergency room visits
Qualitative Indicators (Descriptions):
Participant descriptions of changed behavior
Case studies documenting transformation
Expert assessment of skill development
Community member perceptions of change
Knowledge (Do they know more?):
Pre/post test scores
Correct identification of concepts
Ability to explain key information
Attitude (Do they think differently?):
Survey responses on confidence, self-efficacy, motivation
Likert scale ratings of beliefs and perspectives
Expressed intentions and goals
Behavior (Do they act differently?):
Observable behavior changes (attendance, participation)
Self-reported behavior changes (eating habits, exercise)
Verified behavior changes (employment records, academic transcripts)
Condition (Has their situation changed?):
Income level, housing status, health outcomes
Test scores, graduation rates, employment rates
Measured environmental conditions (water quality, air quality)
Use baseline data (where are participants starting?)
Research comparable programs for benchmarks
Set realistic but ambitious targets
Distinguish between aspirational and expected targets
Adjust based on actual results and learning
Pre/post surveys: Measure change over time (same questions, beginning and end)
Satisfaction surveys: How did participants experience the program?
Follow-up surveys: Long-term outcomes after program completion
Tips: Keep surveys short (10-15 minutes max), use validated instruments when available, pilot test before full deployment
Individual interviews: Deep understanding of one person's experience (30-60 minutes)
Focus groups: Group discussion revealing shared experiences (6-10 participants, 60-90 minutes)
Semi-structured: Prepared questions with flexibility to follow interesting threads
Tips: Record and transcribe (with consent), use open-ended questions, avoid leading
Direct observation: Watch and record behavior in program settings
Structured observation: Use checklist of specific behaviors to look for
Tips: Multiple observers increase reliability, document what you see, not what you interpret
Attendance records
Academic transcripts
Employment records
Health records (with consent/authorization)
Case management notes
Financial records
Most Significant Change: Collect stories of change, community selects most significant
Photovoice: Participants photograph their experience, discuss in group
Community mapping: Visual representation of community assets and challenges
For each indicator, document:
What data will be collected
How (survey, interview, observation, records)
When (baseline, midpoint, endpoint, follow-up)
By whom (staff, external evaluator, participants)
From whom (all participants, sample, comparison group)
Where data will be stored
How privacy will be protected
Executive summary: Key findings in one page
Program description: Brief overview of activities and participants
Methodology: How you collected and analyzed data
Findings: Results organized by outcome area
Stories: 2-3 participant narratives illustrating impact
Challenges and lessons learned: Honest reflection
Recommendations: What you will do differently based on findings
Data appendix: Detailed tables and charts
Lead with outcomes, not just outputs (changed lives, not just numbers served)
Compare to targets: Did you meet, exceed, or fall short of goals?
Explain context: External factors that affected results
Be honest about challenges: Funders respect transparency
Use visuals: Charts, infographics, photos increase engagement
Tell stories alongside data: Numbers inform, stories inspire
Keep it concise: Busy readers appreciate brevity
Bar charts: Compare categories or time periods
Line charts: Show trends over time
Pie charts: Show parts of a whole (use sparingly, only for 3-5 categories)
Infographics: Combine numbers, icons, and brief text for at-a-glance understanding
Dashboards: Real-time or periodic visual summary of key metrics
Tools: Canva (free infographics), Google Data Studio (dashboards), Excel/Google Sheets (charts)
Data answers "how much?" Stories answer "what does it feel like?" You need both.
Ask participants: "What is different in your life because of this program?"
Capture stories regularly, not just at reporting time
Get written consent for using stories publicly
Include context: Where they started, what happened, where they are now
Protect privacy: Use first names only, change identifying details if needed
The challenge: What was the person facing before the program?
The turning point: How did the program make a difference?
The outcome: What changed in their life?
The future: What is possible now that was not before?
"Of the 200 participants in our job training program, 78% secured employment within 90 days. Maria was one of them. After 18 months of unemployment following a layoff, she completed our 12-week program and landed a position as a medical office coordinator, increasing her family's income by 40%."
Formative: Conducted during program to improve it (Are we doing this well? What should we change?)
Summative: Conducted at conclusion to assess overall impact (Did it work? Was it worth the investment?)
Was the program implemented as planned?
Were target populations reached?
Was the dosage sufficient? (Number of sessions, hours, intensity)
What adjustments were made and why?
What are participants' experiences of the program?
Did participants experience the expected changes?
How much change occurred? (Effect size)
Were changes sustained over time?
Were there unintended outcomes (positive or negative)?
RE-AIM: Reach, Effectiveness, Adoption, Implementation, Maintenance
Kirkpatrick Model: Reaction, Learning, Behavior, Results (training programs)
Developmental Evaluation: For innovative programs in complex environments
Collective Impact: Shared measurement across multiple organizations
Empowerment Evaluation: Community members lead their own evaluation
Funder requires external evaluation
Need rigorous design (comparison groups, statistical analysis)
Want objective perspective on sensitive findings
Organization lacks evaluation expertise
Stakes are high (large program, significant funding decisions)
Comparing your results to similar programs provides context:
Is a 60% success rate good or poor? Depends on what comparable programs achieve
Benchmarks help set realistic targets
Funders expect you to know how you compare
Published research on similar interventions
National program networks that aggregate data (United Way, YMCA, Boys & Girls Club)
Clearinghouses of evidence-based programs (SAMHSA, What Works Clearinghouse)
State and federal agency reports
Peer organizations willing to share data
SurveyMonkey / Google Forms: Survey creation and analysis
Qualtrics: Advanced survey and research platform
Salesforce NPSP: Client tracking with outcome measurement
Apricot by Social Solutions: Outcomes management for nonprofits
Efforts to Outcomes (ETO): Case management with outcomes tracking
Tableau Public (free): Data visualization
SPSS / R (free): Statistical analysis for rigorous evaluation
NVivo / Dedoose: Qualitative data analysis
Phase 1: Build logic model, define 3-5 key indicators, start collecting basic data
Phase 2: Implement pre/post surveys, establish baseline, first impact report
Phase 3: Add qualitative methods (interviews, stories), compare to benchmarks
Phase 4: Develop data dashboards, integrate measurement into program management
Phase 5: External evaluation, publish findings, contribute to evidence base
Phase 6: Lead evaluation capacity building, develop theory of change, systems-level impact
Innovation Network (innonet.org): Free logic model builder and evaluation tools
Better Evaluation (betterevaluation.org): Comprehensive evaluation guidance
American Evaluation Association (evaluate.org): Professional community, training
Books: "Measuring the Networked Nonprofit" by Kanter and Paine
Books: "Outcome Frameworks" by Robert Penna
W.K. Kellogg Foundation Logic Model Guide: Free, comprehensive (online PDF)
Nonprofit Quarterly: Regular articles on impact measurement trends
Deliver the response as a structured document with clear headings and actionable content. Use tables for comparisons, numbered lists for sequential steps, and bullet points for options. Include specific examples where applicable.
[Social Impact Measurer deliverable]
1. Context and objectives
2. Analysis or framework
3. Specific recommendations with rationale
4. Action items with timelineInput: "Help me with social impact measurer for a mid-size project."
Output: A complete social impact measurer framework tailored to the specific context, with actionable steps, relevant considerations, and measurable outcomes.
Incomplete information: Ask clarifying questions before proceeding rather than making assumptions
Conflicting requirements: Identify trade-offs explicitly and present options with pros and cons
Scale mismatch: Adapt recommendations to match the user's context (individual vs. team vs. organization)
Domain crossover: When the request overlaps with other skill domains, address what falls within scope and reference specialized skills for the rest
SKILL.md
403 lines · 2,567 words
The text of SKILL.md is shown as it downloads, under the Apache-2.0 license, by Ferrox Labs. The license is the one in the file's own frontmatter.
Your new bot
Social Impact Measurer bot
Waiting in your sidebar once you say go.
No account needed · Runs on the AI plan you already pay for