What do I need to use MLPS 2.0 Checklist (等保 2.0)?

The system; Impact if compromised; Architecture; Existing controls and policies; Deadline.

Is MLPS 2.0 Checklist (等保 2.0) free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

MLPS 2.0 Checklist (等保 2.0)

Q: How do I know the MLPS 2.0 Checklist (等保 2.0) output is good?

The skill verifies itself against its own quality checks: The recommended level states the object harmed and the degree of harm for both security aspects; Filing applies to level two and above and is shown with its timing marked to confirm; The gap checklist covers all ten control areas; Every gap has a fix, an owner and a date.

🔵 Stable🕐 updated 2026-10-04⚖️ rules checked 2026-10-04 🔷 SkillSpec L3 pm-china-compliance

Use when asked 等保怎么做, 等保 2.0 定级, 等保备案和测评流程, 等保三级要求, 我们的系统需要过等保吗, or prepare an information system for China's Multi-Level Protection Scheme (MLPS 2.0, 网络安全等级保护). Produces a grading recommendation (定级) with the reasoning for the expert review, the filing (备案) and assessment (测评) steps and their usual timing, a gap checklist across the ten control areas of GB/T 22239-2019, and a remediation plan, marked as preparation for a licensed assessor.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

🗣 Say this to your agent

“我们的 SaaS 系统要过等保三级，帮我梳理差距。”“等保定级怎么写理由？二级还是三级？”“等保备案和测评的流程是什么？”“Prepare our system for China's MLPS 2.0 assessment.”

What to give it

▸The system — what it does, users, data it holds (including personal and important data), and whether it serves the public

▸Impact if compromised — on individuals, organisations, social order or national security, and how severe

▸Architecture — hosting (own data centre or cloud, and the cloud's own MLPS level), network zones, key components

▸Existing controls and policies — , and any previous assessment reports

▸Deadline — driving the work (a tender, a regulator, a customer)

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓The recommended level states the object harmed and the degree of harm for both security aspects

✓Filing applies to level two and above and is shown with its timing marked to confirm

✓The gap checklist covers all ten control areas

✓Every gap has a fix, an owner and a date

✓Cloud-hosted systems separate the provider's controls from the operator's

✓The output states that only a licensed assessor can assess

⚠️ What it refuses to do

**Grading low to save cost.** Expert review and the bureau can raise it, late.

**Policies on paper only.** Assessors check evidence of operation, such as logs and records.

**Assuming the cloud covers everything.** The operator still owns its own layer.

**Starting remediation after the assessment begins.** Close the obvious gaps first.

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="cn-mlps-checklist"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

MLPS 2.0 Checklist (等保 2.0) is one of 1297 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog