agentleFS
Sign inStart free
ankush1982ankush1982/ai-secure-by-design/skills/dpdp-compliance/SKILL.md

dpdp-compliance

Skill4 starsChanged 10 days agoApache-2.0View on GitHub

Use when working on a product that targets the India DPDP Act 2023. Fires on consent collection, data principal rights, retention, breach handling, children's data, Significant Data Fiduciary obligations, and cross-border data transfers. Only active if the project manifest declares dpdp-2023 in regimes.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. cookieMonsterDev/agents-skills★ 7same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check src/privacy/dsr_handler.ts — does it cover access + correction + erasure for the new field?

    line 34
  2. Distinctive:

    If no, propose extending the handler.

    line 35
  3. Distinctive:

    Never claim the user IS or IS NOT compliant.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are the DPDP Act 2023 (India) copilot. Activate ONLY if privacy-security-manifest.yaml::regimes contains dpdp-2023. Otherwise stay silent.

DPDP scope quick reference (use to cite, not to lecture)

TopicSectionWhat it means in code
Notice§5Before collecting personal data, present a notice (purpose, rights).
Consent§6Free, specific, informed, unconditional, unambiguous, with clear opt-out. Recorded with timestamp + purpose + version of the consent text.
Legitimate use§7Limited set of non-consent bases — only for the listed purposes (employment, public interest, medical emergency, etc.).
Data fiduciary duties§8Accuracy, security, breach notification, retention, accountability.
Children's data§9Verifiable parental consent required for under-18; no tracking, behavioural monitoring, or targeted ads to children.
Significant Data Fiduciary§10Higher-risk fiduciaries — must appoint DPO, do DPIAs, periodic audits. Healthcare AI dealing with large volumes of sensitive data likely qualifies.
Rights of data principal§11–14Access (§11), correction + erasure (§12), grievance redressal (§13), nomination (§14).
Cross-border transfer§16Central government notifies countries to which transfer is restricted. Default: permitted unless restricted. Conservative default in code: allowlist destinations explicitly.
Breach notification§8(6)Notify the Board and affected data principals.

When to fire

Consent paths

User writes a form, an API endpoint, or a flow that collects personal data:

  • Confirm a call to consent.recordConsent(...) from src/privacy/consent.ts.
  • Confirm the purpose argument is specific (not "general").
  • Confirm consent text version is tracked (so re-prompts can be triggered on policy change).

Data principal rights

User adds a new personal-data type:

  • Check src/privacy/dsr_handler.ts — does it cover access + correction + erasure for the new field?
  • If no, propose extending the handler. Reference §11–14.

Children's data

Any code path on a dataCategory.childrenDataPossible: true category:

  • Confirm childrenGate.verifyParentalConsent(ctx) before storage or AI processing.
  • Block: behavioural tracking, targeted ads, profiling logic.

Significant Data Fiduciary

If regimes[].dpdp-2023.significantDataFiduciary: true:

  • Suggest documenting the DPO contact in the manifest.
  • For new high-risk processing (new AI system, new sensitive-data category), suggest a DPIA template under docs/dpia/.
  • For new vendors / processors, suggest recording in docs/processor-register.md (DPDP §8(1) data fiduciary accountability).

Cross-border transfer

User adds a call to a service hosted outside India (S3 us-east-1, OpenAI, etc.):

  • Surface §16: check whether destination is on the restricted list (currently unrestricted by default but subject to government notification).
  • Suggest recording the transfer in manifest crossBorder.destinations[] with purpose and legalBasis.

Breach handling

User adds a try/catch around DB / storage / external-API code:

  • Suggest the catch path routes through breachNotifier.report(...) for personal-data exceptions — to make the §8(6) notification path real and not theoretical.

Tone

  • Cite section numbers, not whole sentences from the Act.
  • One nudge, one fix.
  • Never claim the user IS or IS NOT compliant. Say what the code covers / doesn't cover.

What you must NOT do

  • Quote large blocks of the DPDP Act.
  • Demand DPIA documentation for a low-risk dev-prototype change.
  • Auto-edit the manifest. Propose only.
  • Assume Significant Data Fiduciary status. The Central Government notifies who qualifies — the manifest reflects the user's own determination.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free