ISO Standards Readiness Evidence Prep
Structures scope, controlled documents, traceability, CAPA and supplier evidence into a reviewable draft package for ISO 13485, 14971, 17025 and 15189.
Docs & OfficeAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026
What it does
- Runs an 8-step workflow: declare standard/lane/owners → freeze source and edition baseline → inventory controlled documents and records → review process implementation with sampled records → run lane-specific checks → handle regulator evidence (US FDA QMSR) separately → assemble a bounded evidence manifest → controlled human handoff.
- Ships deterministic, stdlib-only Python CLIs (
validate_scope_intake.py,audit_document_records.py,check_traceability.py,check_capa.py,check_supplier_controls.py,check_qmsr_transition.py,validate_evidence_manifest.py,gap_analyzer.py) that read bounded local JSON, make no network calls, and reject symlinks, unsafe paths and unlisted standards. - Enforces assurance-lane hygiene: organizations are certified, laboratories are accredited; ISO certification never displaces FDA inspection or CLIA.
- Reproduces no ISO clause text (copyright-safe) and labels every output as draft material for authorized human review.
Who it's for
- RA/QA and quality managers at medical device manufacturers
- Testing, calibration and medical laboratories preparing for ISO/IEC 17025 or ISO 15189 accreditation
- Consultants and internal auditors assembling pre-assessment evidence packages
Examples
- ISO 13485 pre-assessment: fill the scope-intake template, run
validate_scope_intake.py --standard iso-13485, and surface unresolved applicability items as explicit blockers for management review. - CAPA and supplier sweep: run
check_capa.pyandcheck_supplier_controls.pyto flag CAPAs lacking effectiveness evidence and critical suppliers without risk-based controls or approvals. - ISO 17025 accreditation prep: build an evidence manifest, validate it with
--standard iso-17025 --verify-files, then rungap_analyzer.pyfor a domain-level gap report that marks unlisted domainsnot-assessedrather than compliant.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/iso-standards-readiness/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/iso-standards-readiness folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/iso-standards-readiness/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/iso-standards-readiness ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal in your working directory.
- Clone the repository:
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git - Create the skills directory:
mkdir -p ~/.claude/skills - Copy this skill only:
cp -r scientific-agent-skills/skills/iso-standards-readiness ~/.claude/skills/ - Verify Python 3.11 or newer:
python3 --version - Restart Claude Code and ask something like "help me prepare ISO 13485 readiness evidence" to trigger the skill.
- Copy any template out of the skill folder into your controlled workspace before filling it in — never edit a distributed template into a purported approved record.
View source on GitHub ↗License: MIT