program-evaluation
Design and implement formative, summative, and developmental evaluations using logic models and mixed methods
npx skills add a5c-ai/babysitter --skill program-evaluation --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Program Evaluation Skill Design and implement rigorous evaluations of social programs and policy interventions using established frameworks. ## Overview The Program Evaluation skill enables design and implementation of formative, summative, and developmental evaluations using logic models, theory of change frameworks, and mixed methods approaches for assessing program effectiveness and informing improvement. ## Capabilities ### Evaluation Design - Formative evaluation - Summative evaluation - Developmental evaluation - Impact evaluation - Process evaluation ### Logic Models - Theory of change development - Input-output mapping - Outcome identification - Assumption articulation - Indicator specification ### Data Collection - Multiple data sources - Quantitative measures - Qualitative methods - Mixed approaches - Participatory methods ### Analysis and Reporting - Outcome measurement - Attribution assessment - Cost-effectiveness analysis - Stakeholder reporting - Recommendation development ### Utilization Focus - Stakeholder engagement - Use identification - Findings translation - Recommendation implementation - Learning facilitation ## Usage Guidelines ### When to Use - Assessing p
- Overview
- Capabilities
- Evaluation Design
- Logic Models
- Data Collection
- Analysis and Reporting
- Utilization Focus
- Usage Guidelines
- When to Use
- Best Practices
- Integration Points
- References
What does the program-evaluation skill do?
Design and implement formative, summative, and developmental evaluations using logic models and mixed methods
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill program-evaluation --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.