AGENT SKILL

ra-qm-skills

Router/index for the 15 regulatory & quality-management skills bundled in this plugin (ISO 13485 QMS, EU MDR 2017/745, FDA submissions under QMSR, ISO 14971 risk, CAPA, document control, ISO 27001/ISMS, ISO 42001 AIMS, EU AI Act, GDPR/DSGVO, SOC 2, auditing). Use when a compliance request doesn't obviously match one skill and you need to pick the right one (e.g., 'prepare us for an ISO 13485 audit', 'is my AI system high-risk under the AI Act').

License 许可
MIT
最近更新
2026-08-25
Stars
★ 0
Forks
0

01 前言 Front Matter

name
ra-qm-skills
tags
[ "regulatory", "quality-management", "iso-13485", "mdr", "fda", "iso-27001", "gdpr" ]
agents
[ "claude-code", "codex-cli", "openclaw" ]
author
Alireza Rezvani
license
MIT
version
2.9.0
description
Router/index for the 15 regulatory & quality-management skills bundled in this plugin (ISO 13485 QMS, EU MDR 2017/745, FDA submissions under QMSR, ISO 14971 risk, CAPA, document control, ISO 27001/ISMS, ISO 42001 AIMS, EU AI Act, GDPR/DSGVO, SOC 2, auditing). Use when a compliance request doesn't obviously match one skill and you need to pick the right one (e.g., 'prepare us for an ISO 13485 audit', 'is my AI system high-risk under the AI Act').

03 SKILL.md 正文

Regulatory Affairs & Quality Management Skills — Router

This plugin bundles 15 compliance skills for HealthTech/MedTech organizations (this router is the 16th folder under ra-qm-team/skills/). Each skill is self-contained.

Routing table

Match the request, then load ra-qm-team/skills/<skill>/SKILL.md. If multiple rows match, ask one clarifying question first.

Request signals Skill Path
Regulatory strategy, pathway selection, submissions planning regulatory-affairs-head skills/regulatory-affairs-head/
Management review, quality KPIs, QMR governance quality-manager-qmr skills/quality-manager-qmr/
ISO 13485 QMS implementation, process control quality-manager-qms-iso13485 skills/quality-manager-qms-iso13485/
ISO 14971 risk analysis, FMEA, risk files risk-management-specialist skills/risk-management-specialist/
Root cause analysis, corrective/preventive actions capa-officer skills/capa-officer/
Document control, 21 CFR Part 11, DHF/DMR/DHR quality-documentation-manager skills/quality-documentation-manager/
ISO 13485 internal audits, NC classification qms-audit-expert skills/qms-audit-expert/
ISO 27001 audit planning and execution isms-audit-expert skills/isms-audit-expert/
ISMS design, security risk assessment information-security-manager-iso27001 skills/information-security-manager-iso27001/
EU MDR classification, technical files, PSUR mdr-745-specialist skills/mdr-745-specialist/
FDA 510(k)/PMA/De Novo, QMSR fda-consultant-specialist skills/fda-consultant-specialist/
GDPR/DSGVO, DPIA, data subject rights gdpr-dsgvo-expert skills/gdpr-dsgvo-expert/
EU AI Act risk classification, obligations eu-ai-act-specialist skills/eu-ai-act-specialist/
ISO/IEC 42001 AI management system iso42001-specialist skills/iso42001-specialist/
SOC 2 Type I/II readiness, trust criteria soc2-compliance skills/soc2-compliance/

Quick start

# Example: route a risk-analysis request
cat ra-qm-team/skills/risk-management-specialist/SKILL.md
python3 ra-qm-team/skills/risk-management-specialist/scripts/risk_matrix_calculator.py --help

Rules

  • Route to exactly one skill, then follow that skill's workflow. This router ships no tools of its own.
  • All outputs are decision support: final compliance determinations route to the named human owner (QMR, DPO, regulatory counsel) — never auto-decide.
  • Verify regulatory citations against the current text (e.g., FDA QMSR effective 2026-02-02 replaced the legacy QSR subsections).

04 同仓库更多 Skills

JiayiV
JiayiV/question_mixing

webmcpify

Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for "webmcpify", "add WebMCP", or "expose app actions to AI agents".

★ 0
JiayiV
JiayiV/question_mixing

vardoger-analyze

Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~/.copilot/session-state/`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~/.copilot/copilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.

★ 0
JiayiV
JiayiV/question_mixing

transloadit-media-processing

Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS/MP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.

图像与多媒体Skill与智能体开发
★ 0
JiayiV
JiayiV/question_mixing

terraform-azurerm-set-diff-analyzer

Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.

运维与部署
★ 0
JiayiV
JiayiV/question_mixing

technical-job-search

Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV/resume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.

内容创作者人力资源写作与文案
★ 0
JiayiV
JiayiV/question_mixing

steno-mode

Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says "steno mode", "shorthand mode", "compressed responses", "token reduction", "brief structured output", or invokes /steno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding/tutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.

★ 0