agentsclimarketplace

Scar experiment validation critic

Skill KangjieShen/openscar-starter/skills/research/scar-experiment-validation-critic

AI-native scar and keloid phenotyping framework with registry schema, synthetic mock data, validation scripts, and clinician-reviewable workflow skills

Install
npx -y skills add KangjieShen/openscar-starter --skill scar-experiment-validation-critic

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Critique scar and keloid target validation plans for evidence fit, feasibility, overclaim risk, and clinician-scientist review readiness.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.8 KB, as published. Nobody here has run it

Scar Experiment Validation Critic

Description

Use this skill to critique proposed validation plans for OpenScar target candidates. It checks whether a planned tissue, spatial, qPCR, imaging, in vitro, co-culture, perturbation, or cohort-review experiment actually tests the nomination claim and whether the claim remains inside a research boundary.

This skill does not approve experiments ethically or clinically, validate targets, recommend treatment, diagnose disease, determine recurrence, or claim any candidate is a validated biomarker.

When to Use

  • A target nomination package includes a proposed validation recommendation.
  • A tissue or assay plan needs a pre-review for feasibility, comparator logic, endpoint fit, and overclaim risk.
  • A clinician-scientist wants a structured critique before IRB, collaborator discussion, or wet-lab planning.
  • A manuscript claim needs a check against the actual validation design.

Do Not Use

  • Do not use this skill as IRB approval, biosafety approval, statistical sign-off, or clinical protocol approval.
  • Do not suggest patient-specific treatment based on planned or completed target assays.
  • Do not claim an assay validates a biomarker unless a qualified study design and clinician-scientist review have established that outside this skill.
  • Do not hide missing controls, sample-size limits, endpoint immaturity, or tissue-selection bias.
  • Do not use identifiable patient samples or images in public outputs.

Required Inputs

  • Candidate target or mechanism being tested.
  • Nomination claim and phenotype anchor.
  • Proposed experiment type, such as IHC, IF, RNAscope, qPCR, bulk comparison, spatial localization, cell culture, co-culture, perturbation, or cohort review.
  • Sample source, inclusion criteria, comparator groups, timing, treatment exposure context, and available metadata.
  • Planned readouts, positive and negative controls, expected direction, and success criteria.
  • Governance status, de-identification status, and clinician-scientist reviewer role.

Workflow

  1. Confirm the plan is research-only and does not include patient-specific care recommendations.
  2. Restate the target nomination claim in testable, non-clinical language.
  3. Map each experiment component to the claim:
    • sample and comparator fit
    • assay and readout fit
    • tissue region or cell-state fit
    • endpoint and follow-up fit
    • control adequacy
    • reproducibility and batch-risk concerns
  4. Identify design gaps, confounders, missing controls, and feasibility risks.
  5. Check whether the result could support only exploratory evidence, stronger nomination, downgrade, or rejection.
  6. Rewrite overclaiming language into research-safe language.
  7. Produce a clinician-scientist review checklist and decision gate.

Output Format

  • Candidate target and nomination claim
  • Required input completeness check
  • Experiment-to-claim fit assessment
  • Control and comparator critique
  • Feasibility and governance risks
  • Overclaim and biomarker-claim audit
  • Recommended revisions to the validation plan
  • Possible interpretation boundaries
  • Clinician-scientist review requirement
  • No treatment recommendation statement
  • No validated biomarker claim statement

Safety

Safety boundary: this skill supports research plan critique and clinician-scientist review only. It does not diagnose, prescribe, determine recurrence, validate therapeutic targets, recommend treatment, approve human-subjects research, or replace licensed clinical judgment. Escalate urgent patient-specific clinical concerns to a qualified clinician.

Clinician-scientist review requirement: a qualified clinician-scientist must review the validation plan, governance status, sample logic, assay fit, and claim language before work proceeds or findings are communicated.

No treatment recommendation: do not infer treatment selection, treatment response, or patient-level care implications from a validation plan or exploratory result.

No validated biomarker claim: do not describe a target, assay, stain, expression signature, or spatial pattern as a validated biomarker, diagnostic marker, predictive marker, response marker, or clinically actionable marker.

Examples

Critique this RNAscope and IF plan for POSTN as an exploratory invasive-edge scar target, focusing on comparator logic, controls, overclaim risk, and clinician-scientist review questions.

Integration

Works well with scar-target-nomination, scar-target-evidence-review, scar-literature-review, ScarAtlas evidence tables, and OpenScar target validation planning templates.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.