Check an ISO readiness pack before the assessor does

Drop the JSON records of an ISO 13485, ISO 14971, ISO/IEC 17025 or ISO 15189 readiness pack. Your browser runs the iso-standards-readiness skill's own structural checks on them, with the same report and exit status as its Python scripts, free. Nothing is uploaded. A paid run writes a draft evidence review for authorized human assessment, or drafts a missing controlled procedure and checks its register row.

The examples replay saved model runs - the whole page, free. Fictional organizations.

1. The pack (one JSON record per slot)

Standard profile

Scope intakevalidate_scope_intake.py

Drop one or more .json records here (each goes to its slot), or

A pasted whole pack ({"records": {"capa": ...}}) is split into its slots.

Add a record or load an example.

Check (free, in your browser, no AI)

profile

assurance lane

findings

page checks

Structural evidence check only. A zero-finding result does not establish applicability, compliance, conformity, certification, accreditation or inspection readiness, and the checks never open your evidence files.

Record	Script	Result

Blockers and page checks (numbered for the review)

Gap findings (grouped by record and code)

Domain gap view

Domain	Status	Entries

The scripts' JSON reports

The same checks with the skill's scripts

Free: no account, no run.

2. For the paid run

About the organization (optional, sent as written: roles, systems, what you are preparing for)

Anything to ask (optional)

Add a record first to price the run.

Raw model reply

The reply did not parse as the structured result, so it is shown as it arrived.

Your recent runs

What this does, and what it does not

The iso-standards-readiness agent skill ships standard-library Python checks for the records a readiness pack is built from: validate_scope_intake.py, audit_document_records.py, check_capa.py, check_traceability.py, check_supplier_controls.py, check_qmsr_transition.py, validate_evidence_manifest.py and gap_analyzer.py. They fail closed on placeholders, missing owners, evidence, sources and approvals, closed CAPAs without an effective result, critical suppliers without controls, undetermined applicability and uncovered process domains. This page runs a JavaScript port of them with the same JSON report and exit status, checked byte for byte against the Python on tens of thousands of generated records (see the notice). The manifest's optional SHA-256 file verification needs your local evidence files, so it runs only with the skill's own script.

The page's own checks, labelled "page", quote the skill's rules: laboratories are accredited, not certified; there is no ISO 14971 certificate; a design traceability matrix is the wrong tool for laboratory work; superseded editions and retired programmes. Everything written by the model is draft evidence-preparation material for authorized human review. Derived from the agent skills @k-dense-ai/iso-standards-readiness and @k-dense-ai/iso-13485-certification (k-dense-ai/scientific-agent-skills, MIT). Contains no ISO or IEC clause text. Not affiliated with ISO, IEC, FDA or any certification or accreditation body.