本文へ移動
cccskills
無料GitHub で公開

compliance-auditor

Audit feature specs against India's Digital Personal Data Protection (DPDP) Act. Use this skill when: - Writing or reviewing any feature that handles user data (especially children's data) - Auditing a spec's Personal Information section for completeness - Checking a feature against DPDP Act 2023 requirements - Preparing compliance documentation before engineering review - Verifying masking, retention, and consent policies are defined for all PII

インストール方法を見る

含まれるファイル(1)

  • SKILL.md10.2 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Compliance Auditor — DPDP Act 2023

Audit a feature specification against India's Digital Personal Data Protection Act 2023. Identifies personal data elements, maps them to DPDP sections, checks for consent/retention/security policies, and flags compliance gaps.

Workflow

  1. Read the feature spec — Focus on data elements, PII sections, compliance sections
  2. Identify data elements — Extract every data element from the spec
  3. Classify as personal data — Determine if each element is personal data under DPDP
  4. Map to DPDP sections — For each personal data element, identify applicable DPDP requirements
  5. Check policies — Verify consent, purpose limitation, retention, security, and deletion policies exist
  6. Generate audit report — Output the audit table and gap analysis

DPDP Act 2023 — Key Provisions

Definitions (Section 2)

TermDPDP Definition
Personal dataAny data about an individual who is identifiable by or in relation to such data
Data PrincipalThe individual whose personal data is being processed
Data FiduciaryThe entity that determines the purpose and means of processing
Data ProcessorThe entity that processes data on behalf of a Data Fiduciary
Significant Data FiduciaryA Data Fiduciary notified by the government based on volume/sensitivity of data
ChildIndividual below the age of 18 years

Obligations of Data Fiduciary (Section 8)

#ObligationCheck
1Lawful purpose — Process data only for a lawful purpose for which Data Principal has given consentPurpose stated in spec? Consent mechanism defined?
2Purpose limitation — Use data only for the purpose for which it was collectedEach data element has a stated purpose? No secondary use without fresh consent?
3Data minimization — Collect only data necessary for the stated purposeEach element justified by a spec requirement?
4Accuracy — Ensure personal data is complete, accurate, and not misleadingData validation rules defined?
5Retention limitation — Retain data only as long as necessary for the stated purpose, then eraseRetention period specified per data element? Erasure procedure defined?
6Reasonable security safeguards — Protect personal data with appropriate technical and organizational measuresEncryption at rest and in transit? Access control defined?

Consent Requirements (Section 6)

#RequirementCheck
1Free, specific, informed, unconditional, unambiguous consent with clear affirmative actionConsent UI/UX defined? Not bundled with T&C?
2Itemized consent — Separate consent for each purpose if multiple purposes existSeparate consent per data processing activity?
3Consent withdrawal — Data Principal can withdraw consent at any time, as easily as giving itWithdrawal mechanism defined and accessible?
4Notice before consent — Provide notice in clear, plain language describing data and purposeNotice content defined? Available in English and scheduled Indian languages?

Rights of Data Principal (Section 11-14)

#RightCheck
1Right to access — Summary of personal data being processed and processing activitiesAccess/download mechanism defined?
2Right to correction and erasure — Request correction of inaccurate/incomplete data, erasure of data no longer neededEdit and delete workflows defined?
3Right to grievance redressal — Nominate a grievance officer, respond within prescribed timeGrievance officer designated? Response SLA defined?
4Right to nominate — Nominate another person to exercise rights in case of death/incapacityNomination mechanism considered?

Children's Data (Section 9) — CRITICAL

#RequirementCheck
1Verifiable guardian consent — Before processing any child's data, obtain verifiable consent from parent/guardianGuardian consent mechanism defined? Age verification present?
2No tracking or behavioral monitoring — Must not track, monitor, or do behavioral analysis of childrenFeature does not profile children beyond stated purpose?
3No targeted advertising — Must not target advertising at childrenNo ad-related data collection or usage?
4No detrimental processing — Must not process data in a manner that causes detrimental effect to a childNo public ranking, shaming, or disadvantaging features?

Data Breach Notification (Section 8(6))

#RequirementCheck
1Notify Data Protection Board — In the event of a personal data breach, inform the Board in prescribed mannerBreach notification procedure defined?
2Notify affected Data Principals — Inform each affected individualUser notification mechanism defined?

Penalties (Section 33)

ViolationMaximum Penalty
Failure to take security safeguards (breach)Rs 250 crore
Failure to notify breachRs 200 crore
Non-compliance with children's data provisionsRs 200 crore
Non-compliance with Data Fiduciary obligationsRs 150 crore
Non-compliance with additional Significant Data Fiduciary obligationsRs 150 crore

Output Format

# DPDP Compliance Audit Report

**Spec:** {spec file}
**Feature:** {feature name}
**Audited:** {DD-MM-YYYY}
**Regulation:** Digital Personal Data Protection Act, 2023 (India)

## 1. Data Element Inventory

| # | Data Element | Category | Personal Data? | Source | Purpose | Retention |
|---|-------------|----------|---------------|--------|---------|-----------|
| 1 | User name | Identity | Yes | {spec section} | Personalization | Account lifetime |
| 2 | Usage duration | Activity | Yes (linkable) | {spec section} | Analytics | 2 years |

## 2. DPDP Compliance Check

| # | Data Element | DPDP Section | Requirement | Status | Gap |
|---|-------------|-------------|-------------|--------|-----|
| 1 | User name | S.6 | Consent — free, specific, informed | Compliant | — |
| 2 | User name | S.8(3) | Retention limitation | Gap | No retention period defined |
| 3 | User name | S.8(4) | Erasure after purpose fulfilled | Gap | No erasure workflow defined |
| 4 | Child age | S.9 | Verifiable guardian consent | Compliant | — |

## 3. Children's Data Audit (Section 9)

| # | Requirement | Status | Evidence | Gap |
|---|------------|--------|----------|-----|
| 1 | Guardian consent mechanism | Compliant/Gap | {description} | {if gap} |
| 2 | No tracking/behavioral monitoring | Compliant/Gap | {description} | {if gap} |
| 3 | No targeted advertising | Compliant/Gap | {description} | {if gap} |
| 4 | No detrimental processing | Compliant/Gap | {description} | {if gap} |

## 4. Data Principal Rights Check

| # | Right | DPDP Section | Mechanism Defined? | Status |
|---|------|-------------|-------------------|--------|
| 1 | Access | S.11 | {yes/no} | Compliant/Gap |
| 2 | Correction & Erasure | S.12 | {yes/no} | Compliant/Gap |
| 3 | Grievance Redressal | S.13 | {yes/no} | Compliant/Gap |
| 4 | Nomination | S.14 | {yes/no} | Compliant/Gap |

## 5. Masking & Security Audit

| # | Data Element | Masking Required? | Masking Method | At Rest Encryption | In Transit Encryption | Status |
|---|-------------|-------------------|----------------|--------------------|-----------------------|--------|

## 6. Summary

| Status | Count |
|--------|-------|
| Compliant | {N} |
| Needs Review | {N} |
| Gap (Must Fix) | {N} |

**Penalty Exposure:** {estimated based on gap severity}

## 7. Required Actions

### Gaps (Must Fix Before Review)
1. **{Data Element} — DPDP S.{section} — {Requirement}**
   Gap: {description}
   Fix: {specific action to add to the spec}
   Penalty risk: {relevant penalty from Section 33}

### Needs Review (Discuss with Legal)
1. **{Data Element} — DPDP S.{section}**
   Question: {what needs clarification}

Rules

  1. When in doubt, flag it — Classify uncertain data as personal data and flag for review
  2. Linkable data is personal data — Data linkable to a specific person (even via session ID) is personal data under DPDP
  3. Children = strictest requirements — Section 9 applies to all individuals under 18. No exceptions.
  4. Analytics events are data — Event tracking creates personal data about user behavior. Include in audit.
  5. Don't assume compliance — If a policy isn't explicitly stated in the spec, it's a gap
  6. Consent must be granular — Bundled consent (buried in T&C) does not satisfy Section 6
  7. Retention must be finite — "Account lifetime" is not acceptable without a defined account deletion policy

Anti-Patterns

  • Don't skip the children's data audit — Section 9 penalties are up to Rs 200 crore
  • Don't treat consent as a checkbox — DPDP requires free, specific, informed consent
  • Don't assume "anonymized" data is exempt — verify the anonymization is irreversible
  • Don't ignore Data Principal rights — access, correction, erasure, and grievance mechanisms are mandatory

Quality Checklist

  • Every data element from the spec is inventoried
  • Personal data classification applied to each element
  • DPDP sections mapped per element
  • Children's data audit completed (Section 9)
  • Data Principal rights check completed (Sections 11-14)
  • Consent mechanism verified (Section 6)
  • Retention periods specified (Section 8(3))
  • Security safeguards defined (Section 8(4))
  • Masking and encryption audit completed
  • Gaps have specific fix recommendations with penalty references

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Rate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Generate A/B copy variants grounded in Eugene Schwartz's awareness and market-sophistication stages and John Caples' tested-headline discipline. Every variant declares its angle, the awareness stage it targets, and a falsifiable hypothesis, and the skill recommends which pair to test first and what delta counts as signal. Use when the user says "A/B test this", "write variants", "give me options", "test different angles", "copy variants", "ab copy", "test this headline", "multiple versions", "which version is better", or wants to test copy before publishing. For reviewing copy that already exists, see copy-review. For sample size and stopping rules, see growth-experiment. For diagnosing a page rather than its words, see page-cro. For full paid ad sets by platform, see ad-campaign-writer.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "fit criteria", "given when then", "Gherkin scenarios", "what does done look like", "testable conditions", "how will we know this works" - even if they don't explicitly say "acceptance criteria".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Build a strategic account plan for winning, retaining, or expanding a named account. Use when the user says "build an account plan", "strategic account planning", "how do I grow this account", "account expansion strategy", "whitespace analysis", "QBR prep", "key account review", "map the stakeholders in this account", "land and expand plan", "how do I break into [company]", or wants a structured strategy for a specific account.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Write paid ad copy for LinkedIn, Google, Meta, and YouTube. Produces multiple variants per platform, each targeting a different Eugene Schwartz awareness level and Cialdini persuasion principle. Use when the user asks for ad copy, ad variants, "write LinkedIn ads", Google ads, Meta ads, paid social copy, ad headlines, or wants creative for a paid campaign. Reads brand voice, ICP, and positioning from knowledge/. For organic social posts, see linkedin-post or social-calendar. For the landing page the ad points at, see landing-page-writer. For testing variants, see ab-copy-writer.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Design clean and consistent APIs. Use when the user says "design an API", "API design review", "design these endpoints", "REST API for X", "GraphQL schema", "API contract", "how should this endpoint work", "review my API design", or wants to create or improve an API interface - even if they don't explicitly say "API design".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

qa-aman のスキルをすべて見る

このスキルの問題を報告する