agentleFS
Sign inStart free
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/assess-construct-validity/SKILL.md

assess-construct-validity

Skill504 starsChanged 48 days agoApache-2.0View on GitHub

Assess whether a benchmark measures its claimed capability using content, convergent, discriminant, and confound analysis.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check content coverage and plausible construct-irrelevant cues against the benchmark specification.

    line 23
  2. Distinctive:

    Test confound hypotheses with controlled contrasts or artifact probes and record residual uncertainty.

    line 25
  3. Very specific:

    If construct validity depends on whether the operationalization covers the intended domain, consider map-coverage-space as the next tactic.

    line 27
  4. Distinctive:

    Every validity claim cites a task, measure, contrast, or artifact observation.

    line 38
  5. Distinctive:

    Do not infer construct validity from a high score, face validity, or agreement with another measure that shares the same confound.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

assess-construct-validity

Purpose

Assess whether a benchmark or evaluation construct measures the claimed capability rather than content cues, confounds, or unrelated skill.

Input contract

required: [construct_claim, benchmark_specification, evaluation_records]
optional: [content_analysis, convergent_measures, discriminant_measures, confound_hypotheses]
constraints: [each validity judgment requires an observable indicator, comparison basis, and provenance]

Procedure

  1. State the target construct and map benchmark tasks, labels, and metrics to its intended components.
  2. Check content coverage and plausible construct-irrelevant cues against the benchmark specification.
  3. Compare convergent and discriminant evidence where available, preserving missing comparisons.
  4. Test confound hypotheses with controlled contrasts or artifact probes and record residual uncertainty.

If construct validity depends on whether the operationalization covers the intended domain, consider map-coverage-space as the next tactic.

Output contract

produces: [construct_map, content_validity_assessment, convergent_discriminant_evidence, confound_report, validity_judgment]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]

Quality gates

  • Every validity claim cites a task, measure, contrast, or artifact observation.
  • Content coverage, convergence, discrimination, and confounds are reported separately.
  • A missing diagnostic is marked unresolved rather than treated as evidence of validity.

Failure and counterexamples

Do not infer construct validity from a high score, face validity, or agreement with another measure that shares the same confound.

Provenance map

  • resolved: construct-validity-assessment

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.

Check your setup, free