Pipl Impact Assessment logo

Pipl Impact Assessment

Organization
open-legal-products
pipl-impact-assessment

Run the personal-information protection impact assessment required by PIPL Articles 55-56: test the five mandatory triggers, then draft the three-part assessment (lawfulness, necessity and legitimacy of purpose and method; impact and security risk to individual rights; whether protective measures are lawful, effective, and matched to the risk) and the three-year record. Use before processing sensitive personal information, automated decision-making, entrusted processing, provision to another processor, public disclosure, or outbound transfer. The workflow drafts; the processor accepts residual risk and keeps the file.

Overview

Publisheropen-legal-products
Repositorymike-workflows
Skill namepipl-impact-assessment
Stars
91
Forks
43
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by open-legal-products on GitHub. Read the source before you install it.

Installation

Install the Pipl Impact Assessment AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/open-legal-products/mike-workflows/tree/main/assistant-workflows/china-pipl-pack/pipl-impact-assessment
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/open-legal-products/mike-workflows.git /tmp/mike-workflows
mkdir -p .claude/skills
cp -r /tmp/mike-workflows/assistant-workflows/china-pipl-pack/pipl-impact-assessment .claude/skills/pipl-impact-assessment
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pipl Impact Assessment in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pipl Impact Assessment on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pipl Impact Assessment is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PIPL Impact Assessment

PIPL calls this a personal-information protection impact assessment, not a GDPR DPIA. This workflow tests whether Article 55 requires one and drafts the Article 56 content. Residual-risk acceptance and the decision to proceed stay with the processor. Confirm every cited article in the official Chinese text. Unconfirmed citations stay tagged [TO VERIFY] and cannot support "not required".

Step 1 - Is an assessment required (Article 55)

A prior assessment and a processing record are mandatory in any of these cases:

  1. processing sensitive personal information (Article 28 definition; children's information under fourteen is sensitive);
  2. using personal information for automated decision-making;
  3. entrusted processing, providing personal information to another personal-information processor, or disclosing personal information;
  4. providing personal information abroad;
  5. other processing activities that have a major impact on individual rights and interests.

Record required or not required with a per-limb justification. "Other major impact" is not a clearance: if the facts are thin, mark recommended and list the missing facts. Article 54 compliance audits are a separate periodic duty; do not treat this assessment as satisfying Article 54.

Step 2 - Draft the Article 56 content

Draft all three elements. Missing facts become gaps, not invented findings.

  • (1) Whether the purpose and method of processing are lawful, legitimate, and necessary. Tie this to a PIPL Article 13 legal basis and to the principles in Article 5 (lawfulness, legitimacy, necessity, good faith; purpose limitation; minimisation; openness and transparency). For sensitive personal information also walk Article 29 (specific purpose, sufficient necessity, strict measures, separate consent unless a law provides otherwise) and Article 30 (notice of necessity and impact).
  • (2) Impact on individual rights and interests, and security risk: confidentiality, integrity, and availability scenarios; likelihood and severity; groups such as children or employees.
  • (3) Whether protective measures are lawful, effective, and matched to the risk, against the Article 51 catalogue (internal management rules, classification, encryption or de-identification, access control, training, incident plans) so far as the facts support.

Article 56, second paragraph: keep the assessment report and the processing record for at least three years.

Step 3 - Entrusted processing and outbound overlays

  • Entrusted processing (Article 21): the commission agreement must state purpose, period, method, categories, protection measures, and the rights and duties of both sides. The trustee must process as agreed, return or delete on completion, and not further subcontract without consent. If the user is assessing a vendor deal, list these contract points as open items rather than rewriting the commercial terms.
  • Outbound transfer (Article 55(4)): this assessment is required even when the 2024 Cross-border Data Flow Provisions exempt the three filing mechanisms. Do not treat an Article 5 exemption as skipping Article 55.

Output

A draft assessment: trigger table, Article 56 narrative with gaps marked, three-year retention note, and a residual-risk line for the processor to accept or reject. Do not declare the processing "compliant".

Governance boundary

The workflow screens the trigger and drafts the file. A human accepts residual risk, signs, and keeps the record. Nothing is filed automatically.

Frequently asked questions

What does the Pipl Impact Assessment AI skill do?

Run the personal-information protection impact assessment required by PIPL Articles 55-56: test the five mandatory triggers, then draft the three-part assessment (lawfulness, necessity and legitimacy of purpose and method; impact and security risk to individual rights; whether protective measures are lawful, effective, and matched to the risk) and the three-year record. Use before processing sensitive personal information, automated decision-making, entrusted processing, provision to another processor, public disclosure, or outbound transfer. The workflow drafts; the processor accepts resid...

Why use Pipl Impact Assessment on TypingMind?

Because you install it once and use it with any model. Pipl Impact Assessment is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pipl Impact Assessment in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/open-legal-products/mike-workflows/tree/main/assistant-workflows/china-pipl-pack/pipl-impact-assessment. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pipl Impact Assessment?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pipl Impact Assessment?

As many as you like. As long as a model supports skills, you can use Pipl Impact Assessment with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pipl Impact Assessment AI skill free?

Yes. It is published on GitHub by open-legal-products under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇