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

audit-study-validity

Skill504 starsChanged 48 days agoApache-2.0View on GitHub

Audit a study against an appropriate methodological-quality and risk-of-bias rubric; return domain-level judgments, evidence, and overall confidence.

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, 2 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the validity-screened corpus may already support a stopping decision, consider assess-evidence-saturation as the next tactic.

    line 27
  2. Very specific:

    If validity differs materially across designs, populations, or conditions, consider analyze-heterogeneity as the next tactic.

    line 28
  3. Very specific:

    If the conclusion depends on study exclusions or uncertain validity judgments, consider assess-sensitivity as the next tactic.

    line 29
  4. Distinctive:

    No overall label is emitted without domain-level evidence.

    line 40
  5. Distinctive:

    Do not average incompatible domains into a false precision score or treat unreported methods as low risk.

    line 45

≈ “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

audit-study-validity

Purpose

Audit a study against an appropriate methodological-quality and risk-of-bias rubric and return domain judgments with evidence and confidence.

Input contract

required: [study_record, validity_rubric]
optional: [protocol, analysis_plan, supplementary_materials]
constraints: [rubric applicability and judgment rationale must be explicit]

Procedure

  1. Select and scope the rubric for the study design.
  2. Judge each domain from reported methods and supporting material.
  3. Record signaling evidence, uncertainty, and direction of likely bias.
  4. Aggregate domain judgments without hiding critical domain failures.

If the validity-screened corpus may already support a stopping decision, consider assess-evidence-saturation as the next tactic. If validity differs materially across designs, populations, or conditions, consider analyze-heterogeneity as the next tactic. If the conclusion depends on study exclusions or uncertain validity judgments, consider assess-sensitivity as the next tactic.

Output contract

produces: [domain_judgments, risk_of_bias_profile, evidence_basis, overall_confidence, applicability_notes]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]

Quality gates

  • No overall label is emitted without domain-level evidence.
  • Rubric choice and missing-data handling are recorded.

Failure and counterexamples

Do not average incompatible domains into a false precision score or treat unreported methods as low risk.

Provenance map

  • resolved: knowledge-acquisition-quality-assessment
  • resolved: knowledge-acquisition-risk-of-bias-assessment
  • resolved: knowledge-acquisition-quality-assessment-protocol
  • intermediate: Pass3/assess-study-quality
  • intermediate: Pass3/assess-risk-of-bias

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