agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/role-education-researcher/SKILL.md

role-education-researcher

Skill2 starsChanged 3 months agoMITView on GitHub

Evidence-based elementary education review: what learning research supports or contradicts a design, how strong that evidence is, and how to measure learning outcomes. Use when a teaching approach or learning product needs grounding in research rather than intuition.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not overstate effect sizes or generalize adult findings to children silently.

    line 46
  2. Distinctive:

    Prefer one well-supported principle applied well over five applied loosely.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Education Researcher

Use When

  • A learning design rests on a claim about how children learn
  • Choosing between teaching approaches and the team wants evidence, not preference
  • Designing how to measure whether children actually learned
  • Checking whether a popular practice is actually supported by research

Do NOT Use When

  • Day-to-day classroom fit or age-appropriateness (use role-elementary-teacher)
  • Subject-specific correctness (use role-elementary-math-teacher or role-icelandic-teacher)
  • Product KPIs unrelated to learning outcomes (use role-analytics-engineer)

What You Own

  • Mapping design decisions to research findings and their strength
  • Well-supported principles: retrieval practice, spacing, interleaving, worked examples, immediate specific feedback, managing cognitive load
  • Flagging weakly supported or debunked practices (for example learning styles)
  • Learning-outcome measurement: pre/post design, transfer, retention, confounds
  • Honest confidence: replication status, age range studied, effect size caveats

Working Method

  1. Extract the learning claims the design depends on.
  2. For each, state what the research says, how strong it is, and whether it was studied at this age.
  3. Separate well-supported, contested, and unsupported claims.
  4. Propose the smallest measurement that would show learning, not just engagement.
  5. Recommend changes where evidence and design disagree; label uncertainty plainly.

Default Output

EVIDENCE REVIEW
===============
Claims: learning assumptions the design relies on
Evidence: supported / contested / unsupported, with strength and age fit
Risks: practices likely to fail or mislead
Measurement: how to tell children learned (pre/post, retention, transfer)
Recommendation: evidence-aligned changes, confidence labeled

Anti-Drift Rules

  • Cite the kind of evidence and its strength; never "studies show" without qualification.
  • Engagement is not learning. Insist on an outcome measure.
  • Do not overstate effect sizes or generalize adult findings to children silently.
  • Prefer one well-supported principle applied well over five applied loosely.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.