C15t
c15t/c15t
Work with c15t consent management docs, APIs, and integrations for Next.js, React, and JavaScript.
Implements profiling restrictions for children under GDPR Recital 71, Article 22, UK AADC Standard 12, and COPPA.
Install Children Profiling Limits
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill children-profiling-limits -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills children-profiling-limits --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/privacy/children-profiling-limits .claude/skills/children-profiling-limits && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "children-profiling-limits" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/children-profiling-limits into .claude/skills/children-profiling-limits/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "children-profiling-limits", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/children-profiling-limitsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill children-profiling-limits -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills children-profiling-limits --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/privacy/children-profiling-limits .agents/skills/children-profiling-limits && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "children-profiling-limits" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/children-profiling-limits into .agents/skills/children-profiling-limits/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "children-profiling-limits", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill children-profiling-limits -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills children-profiling-limits --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/privacy/children-profiling-limits .cursor/skills/children-profiling-limits && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "children-profiling-limits" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/children-profiling-limits into .cursor/skills/children-profiling-limits/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "children-profiling-limits", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mukul975/Privacy-Data-Protection-Skills.git --path skills/privacy/children-profiling-limits--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill children-profiling-limits -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills children-profiling-limits --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/privacy/children-profiling-limits .gemini/skills/children-profiling-limits && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "children-profiling-limits" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/children-profiling-limits into .gemini/skills/children-profiling-limits/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "children-profiling-limits", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mukul975/Privacy-Data-Protection-Skills children-profiling-limitsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill children-profiling-limits -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/privacy/children-profiling-limits .github/skills/children-profiling-limits && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "children-profiling-limits" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/children-profiling-limits into .github/skills/children-profiling-limits/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "children-profiling-limits", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill children-profiling-limits -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills children-profiling-limits --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/privacy/children-profiling-limits .opencode/skills/children-profiling-limits && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "children-profiling-limits" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/children-profiling-limits into .opencode/skills/children-profiling-limits/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "children-profiling-limits", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
children-profiling-limits- GitHub stars
- 295
- Token cost
- ~4.3k tokens
- SKILL.md length
- 2,108 words
- Files
- 5 (incl. scripts, references, assets)
- Skills in repo
- 278
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Implements profiling restrictions for children under GDPR Recital 71, Article 22, UK AADC Standard 12, and COPPA.
- Works in 3 steps: Stop recommending similar content → Interject wellbeing resources or… → Alert the parent through the parental…
- Tasks that involve Privacy and GDPR
- SKILL.md covers Overview, Legal Framework, Types of Profiling and Their… and Recommendation Algorithm…, plus 5 more sections
- Runs Python scripts from its folder
What it does
Children Profiling Limits is an agent skill from mukul975/Privacy-Data-Protection-Skills. Implements profiling restrictions for children under GDPR Recital 71, Article 22, UK AADC Standard 12, and COPPA. Covers prohibition of behavioural advertising to children, recommendation algorithm limitations, nudge technique prohibition, and automated decision-making safeguards. Keywords: profiling, children, behavioural advertising, recommendation algorithm, AADC, automated decision.
Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts, reference files and assets (for example `assets/template.md`, `references/standards.md` and `references/workflows.md`).
It sits in Legal & Compliance, covering Privacy and GDPR. The repository describes itself as: 282+ structured privacy & data protection skills for AI agents. GDPR, CCPA, EU AI Act, HIPAA, LGPD, PIPL, DPDP Act. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Privacy and GDPR
Example prompts
- “Use the children-profiling-limits skill to implement profiling restrictions for children under GDPR Recital 71, Article 22, UK AADC Standard 12, and…”
- “/children-profiling-limits”
Requirements
- Python 3
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Stop recommending similar content
- Interject wellbeing resources or helpline information
- Alert the parent through the parental dashboard (without disclosing specific content details that might violate the child's confidence)
What it can do on your machine
Read from SKILL.md and the folder at commit 9b2ef9e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Children Profiling Limits loads about 4.3k tokens when it runs, and up to ~8.5k if it reads all its reference files. Until then it costs about 104 tokens; SKILL.md has 2,108 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from mukul975/Privacy-Data-Protection-Skills at commit 9b2ef9e, republished under its Apache-2.0 licence (© mukul975). 2,108 words, ~4,279 tokens.
Download SKILL.mdSave it as
.claude/skills/children-profiling-limits/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- children-profiling-limits
- description
- Implements profiling restrictions for children under GDPR Recital 71, Article 22, UK AADC Standard 12, and COPPA. Covers prohibition of behavioural advertising to children, recommendation algorithm limitations, nudge technique prohibition, and automated decision-making safeguards. Keywords: profiling, children, behavioural advertising, recommendation algorithm, AADC, automated decision.
- license
- Apache-2.0
- metadata.author
- mukul975
- metadata.version
- 1.0
- metadata.domain
- privacy
- metadata.subdomain
- children-data-protection
- metadata.tags
- profiling, children, behavioural-advertising, recommendation-algorithm, aadc, automated-decision
Children's Profiling Restrictions
Overview
Profiling of children is subject to heightened restrictions under multiple regulatory frameworks. GDPR Recital 71 states that automated decision-making including profiling "should not concern a child." The UK AADC Standard 12 requires profiling to be switched off by default for child users, with exceptions only where the controller can demonstrate a compelling reason and appropriate protective measures. The EU Digital Services Act (DSA) Article 28(2) explicitly prohibits online platforms from presenting targeted advertising based on profiling using the personal data of minors. COPPA prohibits the collection of persistent identifiers from children for behavioural advertising without verifiable parental consent. This skill establishes a comprehensive framework for lawful and ethical data processing that avoids prohibited profiling of children.
Legal Framework
GDPR Recital 71 — Children and Automated Decisions
"In any case, such processing should be subject to suitable safeguards, which should include specific information to the data subject and the right to obtain human intervention, to express his or her point of view, to obtain an explanation of the decision reached after such assessment and to challenge the decision. Such measure should not concern a child."
The EDPB interprets "should not concern a child" as a strong presumption against subjecting children to automated decision-making based on profiling that produces legal or similarly significant effects. While "should not" is weaker than "shall not," the EDPB guidance and DPA enforcement practice treat this as an effective prohibition unless exceptional circumstances apply.
GDPR Article 22 — Automated Individual Decision-Making
Art. 22(1): "The data subject shall have the right not to be subject to a decision based solely on automated processing, including profiling, which produces legal effects concerning him or her or similarly significantly affects him or her."
For children, this prohibition is reinforced by Recital 71. Exceptions under Art. 22(2) (contract necessity, law, explicit consent) are interpreted narrowly for children:
- Contract necessity (Art. 22(2)(a)): Rarely applicable to children; children's contracts are often voidable
- Law (Art. 22(2)(b)): May apply for age verification or child safety obligations
- Explicit consent (Art. 22(2)(c)): Must be parental consent under Art. 8 for children below the threshold; the child's explicit consent alone is insufficient
GDPR Article 4(4) — Definition of Profiling
"Profiling means any form of automated processing of personal data consisting of the use of personal data to evaluate certain personal aspects relating to a natural person, in particular to analyse or predict aspects concerning that natural person's performance at work, economic situation, health, personal preferences, interests, reliability, behaviour, location or movements."
UK AADC Standard 12 — Profiling
"Switch options which use profiling off by default (unless you can demonstrate a compelling reason for profiling to be on by default, taking account of the best interests of the child). Only allow profiling if you have appropriate measures in place to protect the child from any harmful effects (including but not limited to feeding the child content that is detrimental to their health or wellbeing)."
UK AADC Standard 13 — Nudge Techniques
"Do not use nudge techniques to lead or encourage children to provide unnecessary personal data or weaken or turn off their privacy protections."
EU Digital Services Act — Article 28(2)
"Providers of online platforms shall not present advertisements on their interface based on profiling as defined in Article 4, point (4), of Regulation (EU) 2016/679, using personal data of the recipient of the service when they are aware with reasonable certainty that the recipient of the service is a minor."
COPPA — Persistent Identifiers
COPPA defines persistent identifiers as personal information when used for purposes other than support for internal operations. Using persistent identifiers to serve behavioural advertising to children requires verifiable parental consent.
Types of Profiling and Their Status for Children
Prohibited Profiling
| Profiling Type | Description | Regulatory Basis | Status |
|---|---|---|---|
| Behavioural advertising | Using browsing history, interaction patterns, or inferred interests to serve targeted advertisements | DSA Art. 28(2), AADC Std 12, COPPA | Prohibited for children — no exceptions under DSA |
| Social scoring | Evaluating a child's social standing, popularity, or reputation based on interactions | AADC Std 5, Recital 71 | Prohibited — detrimental to wellbeing |
| Emotional profiling | Inferring emotional state from behavioural signals (typing speed, cursor movement, facial expressions) to adapt content or marketing | AADC Std 5, Art. 9 (if inferring mental health) | Prohibited — exploits developmental vulnerability |
| Predictive analytics for commercial targeting | Predicting future purchasing behaviour, susceptibility to marketing, or price sensitivity | AADC Std 5, Recital 71 | Prohibited — commercial exploitation of children |
| Cross-service behavioural tracking | Combining data from multiple services or websites to build comprehensive behavioural profiles | AADC Std 9, COPPA, DSA Art. 28(2) | Prohibited — exceeds any legitimate purpose for children |
Restricted Profiling (Permitted with Safeguards)
| Profiling Type | Description | Conditions for Lawfulness |
|---|---|---|
| Content-based recommendations | Recommending content based on the characteristics of content the child has engaged with (not the child's personal profile) | Default: OFF. May be enabled with parental consent. Content diversity safeguards required. |
| Educational adaptive learning | Adjusting educational content difficulty based on learning progress | Permitted where necessary for the educational purpose. Must not extend to non-educational features. DPO review required. |
| Safety and moderation profiling | Detecting grooming, bullying, or abuse patterns in communications | Permitted under legitimate interest (safeguarding). Must be proportionate and subject to DPIA. Must not be used for commercial purposes. |
| Age-appropriate content filtering | Using age data to filter inappropriate content | Permitted as necessary for child protection. Must not be used to serve advertising. |
Permitted Processing (Not Profiling)
| Processing Type | Description | Why It Is Not Profiling |
|---|---|---|
| Contextual advertising | Serving advertisements based on the current page content, not the user's profile | No personal data used for ad selection; based on content context only |
| Aggregate analytics | Analysing anonymised, aggregate user patterns to improve the service | No evaluation of individual personal aspects; data is not linked to individual users |
| A/B testing | Randomly assigning users to feature variants to test service improvements | Random assignment, not based on personal characteristics |
Recommendation Algorithm Safeguards
For services that implement content recommendation algorithms for children (where permitted), the following safeguards must be in place:
Content Diversity Injection
- Recommendation algorithms must include a minimum diversity ratio (e.g., at least 30% of recommended content must be from categories the child has NOT previously engaged with)
- This prevents filter bubbles and content rabbit holes that can be particularly harmful to children's development
- The diversity injection must be documented and periodically reviewed
Time-Limitation Mechanisms
- Recommendation-driven feeds must include natural stopping points (e.g., "You've been browsing for 20 minutes — time for a break!")
- Autoplay must be disabled by default for children per UK AADC guidance (YouTube implemented this following ICO engagement)
- Infinite scroll must be replaced with paginated content with clear endpoints
Content Safety Filters
- All recommended content must pass through content safety filters before being presented to children
- Filters must be age-tiered: stricter for younger children, proportionate for teenagers
- Human review for edge cases where automated filtering confidence is low
Mental Health Circuit Breakers
- If the recommendation algorithm detects engagement patterns associated with harmful content cycles (e.g., repeated engagement with content about self-harm, eating disorders, or extreme body image), the algorithm must:
- Stop recommending similar content
- Interject wellbeing resources or helpline information
- Alert the parent through the parental dashboard (without disclosing specific content details that might violate the child's confidence)
Nudge Technique Prohibition
Prohibited Nudge Techniques for Children
| Technique | Description | Why Prohibited |
|---|---|---|
| Confirmshaming | "Are you sure you want to miss out?" when declining data collection | Exploits social anxiety and fear of missing out |
| Reward-for-data | Offering in-game currency, badges, or rewards in exchange for personal data or weakened privacy settings | Bribes children to surrender privacy; exploits reward-seeking behaviour |
| Asymmetric choice | Making the privacy-reducing option larger, brighter, or more prominent than the privacy-protecting option | Manipulates choice architecture to exploit limited decision-making capacity |
| Hidden opt-out | Burying the option to decline data collection in sub-menus or requiring multiple clicks | Exploits limited navigation skills and attention span |
| Social proof | "95% of users allow notifications!" to pressure acceptance | Exploits conformity bias, which is stronger in children |
| Urgency/scarcity | "Enable location sharing now or you'll lose your streak!" | Exploits impulsivity and loss aversion |
| Default-to-share | Pre-selecting sharing or public options and requiring the child to actively opt out | Exploits status quo bias and inertia |
Show full SKILL.md (768 more words)Show less
Required Design Patterns
| Pattern | Description | Implementation |
|---|---|---|
| Equal-weight choices | Accept and reject options must be equally prominent in size, colour, and placement | Both buttons same size, same visual weight, no colour hierarchy |
| Neutral language | Choice labels must not favour one option over the other | "Turn on" / "Keep off" — not "Yes, personalise!" / "No, I want a boring experience" |
| Privacy-first defaults | The default state must be the most privacy-protective option | All toggles default to OFF for data-intensive features |
| Friction parity | The number of clicks to enhance privacy must equal or be fewer than the number to reduce privacy | If enabling a feature takes 1 tap, disabling must take 1 tap or fewer |
| No dark patterns | Interface must not use visual tricks, misdirection, or confusing language to influence the child's choice | Regular UX audits with children in the target age group |
BrightPath Learning Inc. — Profiling Compliance Implementation
Profiling Status Matrix
| Feature | Profiling Type | Status | Justification |
|---|---|---|---|
| Learning content difficulty adjustment | Educational adaptive learning | ACTIVE (default) | Necessary for educational service delivery; adjusts maths and reading levels based on assessment scores |
| Game recommendations | Content-based | OFF by default | Recommends games based on subject area, not child's behavioural profile; parent can enable |
| Progress reports | Aggregate scoring | ACTIVE (with consent) | Summarises learning outcomes for parent dashboard; no behavioural profiling |
| Advertising | None | NOT PRESENT | BrightPath does not serve advertisements to children |
| Social features | None | NOT PRESENT | No social scoring, popularity metrics, or peer comparison features |
| Communication moderation | Safety profiling | ACTIVE | Automated detection of inappropriate content in pre-approved message templates; DPIA completed |
Algorithmic Impact Assessment
BrightPath conducts an annual Algorithmic Impact Assessment for its learning content recommendation system:
- Purpose test: Does the algorithm serve the child's educational interests? YES — adjusts content to appropriate difficulty level
- Necessity test: Could the educational purpose be achieved without profiling? NO — adaptive learning requires assessment of current skill level
- Proportionality test: Is the profiling limited to what is necessary? YES — only learning assessment scores are used; no behavioural data, no demographic data beyond age
- Harm assessment: Could the algorithm produce harmful effects? ASSESSED — risk of discouragement if difficulty increases too rapidly; mitigated by gradual progression and positive reinforcement design
- Bias audit: Does the algorithm produce different outcomes based on protected characteristics? TESTED — annual bias audit across age, gender, and language groups; no statistically significant disparities found
- Human oversight: Can a human override the algorithm? YES — parents can manually set content difficulty levels; teachers (in school deployments) can override
Enforcement Precedents
- TikTok (DPC Ireland, 2023): EUR 345 million fine included findings that TikTok's "For You" algorithmic feed profiled children to serve content, with inadequate safeguards against harmful content amplification, violating GDPR Art. 5(1)(a), 5(1)(c), and 25.
- Instagram (Meta, DPC Ireland, 2022): EUR 405 million fine for failing to restrict profiling and public exposure of children's data, including default public profiles for business accounts used by children aged 13-17.
- YouTube (FTC, 2019): USD 170 million settlement for using persistent identifiers (cookies) to track children's viewing behaviour on child-directed channels and serve behaviourally targeted advertising.
- TikTok (CNIL France, 2022): EUR 5 million fine for making it difficult for users, including children, to refuse tracking cookies — constituting a nudge technique that weakened privacy protections.
- Fortnite/Epic Games (FTC, 2022): USD 275 million for design choices that exposed children to harmful interactions, with dark patterns facilitating in-app purchases by children.
Common Compliance Failures
- Profiling on by default: Activating recommendation algorithms, personalisation features, or content curation based on behavioural profiling without requiring explicit opt-in
- Behavioural advertising to known children: Serving targeted advertisements based on personal data profiles despite DSA Art. 28(2) prohibition
- No algorithmic impact assessment: Deploying algorithms that affect children without assessing their impact on children's rights, wellbeing, and development
- Nudge techniques in consent flows: Using dark patterns, confirmshaming, or asymmetric choice design to obtain consent for profiling features
- Cross-service tracking: Using persistent identifiers to track children across websites or services for profiling purposes
- No content diversity safeguards: Allowing recommendation algorithms to create filter bubbles or content rabbit holes without diversity injection or time limits
Integration Points
- Children's Data Minimisation: Data minimisation directly limits the data available for profiling — less data collected means less material for profile construction
- UK AADC Implementation: AADC Standards 5, 7, 12, and 13 collectively govern profiling, defaults, nudge techniques, and detrimental use
- Children's Privacy Notice: The privacy notice must clearly explain what profiling occurs, its effects, and how the child/parent can object
- GDPR Parental Consent: Parental consent is required for any profiling of children below the Art. 8 threshold
- Age-Gating Services: The age gate result determines which profiling restrictions apply to the user account
© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts, references, assets) in skills/privacy/children-profiling-limits of mukul975/Privacy-Data-Protection-Skills.
- SKILL.md
- assets/template.md
- references/standards.md
- references/workflows.md
- scripts/process.py
Open the folder on GitHubat commit 9b2ef9e
Compare with similar skills
Children Profiling Limits next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Children Profiling Limits this skillmukul975/Privacy-Data-Protection-Skills | 295 | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | |
| C15tc15t/c15t | 1.9k | 1 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| HIPAA Safe Harbor Coverage Auditmaziyarpanahi/openmed | 5.5k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Korean Privacy Termskimlawtech/korean-privacy-terms | 586 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Gdpr ComplianceSushegaad/Claude-Skills-Governance-Risk-and-Compliance | 942 | 1 repos | ~3.9k | Automated safety check: Pass | MIT | |
| Hipaa ComplianceSushegaad/Claude-Skills-Governance-Risk-and-Compliance | 942 | 1 repos | ~2.3k | Automated safety check: Pass | MIT |
Similar skills
HIPAA Safe Harbor Coverage Audit
maziyarpanahi/openmed
Checks OpenMed de-identified clinical text against the 18 HIPAA Safe Harbor identifier categories and reports gaps and residual re-identification risk.
Korean Privacy Terms
kimlawtech/korean-privacy-terms
처리방침·이용약관 자동 생성 스킬 패키지 (v4.0). An agent skill from kimlawtech/korean-privacy-terms.
Gdpr Compliance
Sushegaad/Claude-Skills-Governance-Risk-and-Compliance
Expert GDPR compliance assistant covering all four core workflows: (1) auditing code and systems for GDPR violations, (2) drafting GDPR-compliant documents such as privacy policies, Data Processing…
Hipaa Compliance
Sushegaad/Claude-Skills-Governance-Risk-and-Compliance
Expert HIPAA compliance assistant for healthcare and software contexts.
Pii Contract Analyze
gregmos/PII-Shield
Universal legal document processor with PII anonymization. An agent skill from gregmos/PII-Shield.
More from mukul975/Privacy-Data-Protection-Skills
All 278 skills in this repoAge Gating Services
mukul975/Privacy-Data-Protection-Skills
Implements age-gating mechanisms for online services to restrict access based on user age.
AI Data Retention
mukul975/Privacy-Data-Protection-Skills
Manages AI model retention and machine unlearning requirements.
Dpia Mitigation Plan
mukul975/Privacy-Data-Protection-Skills
Structures risk mitigation planning and residual risk tracking for Data Protection Impact Assessments under GDPR Article 35(7)(d).
Gdpr Accountability
mukul975/Privacy-Data-Protection-Skills
Guides implementation of the GDPR accountability principle under Articles 5(2) and 24, including documentation requirements for policies, DPIAs, RoPA, training records, and breach logs.
Pia Threshold Screening
mukul975/Privacy-Data-Protection-Skills
Conducts pre-DPIA threshold screening to determine whether a full Data Protection Impact Assessment is required under GDPR Article 35.
Retention Schedule
mukul975/Privacy-Data-Protection-Skills
Designs and implements data retention schedules compliant with GDPR Article 5(1)(e) storage limitation principle.
Related
Categories
Questions about Children Profiling Limits
What does Children Profiling Limits do?
Implements profiling restrictions for children under GDPR Recital 71, Article 22, UK AADC Standard 12, and COPPA. Children Profiling Limits is an agent skill from mukul975/Privacy-Data-Protection-Skills. Implements profiling restrictions for children under GDPR Recital 71, Article 22, UK AADC Standard 12, and COPPA.
When should I use Children Profiling Limits?
Children Profiling Limits fits situations like: tasks that involve Privacy and GDPR.
How do I install Children Profiling Limits in Claude Code?
Run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill children-profiling-limits -a claude-code`. Or copy the skill folder (skills/privacy/children-profiling-limits in mukul975/Privacy-Data-Protection-Skills) into .claude/skills/children-profiling-limits in your project. Claude Code loads it when a task matches its description.
How do I install Children Profiling Limits in Codex?
Run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill children-profiling-limits -a codex`. Or copy the skill folder (skills/privacy/children-profiling-limits in mukul975/Privacy-Data-Protection-Skills) into .agents/skills/children-profiling-limits in your project. Codex loads it when a task matches its description.
Can I use Children Profiling Limits in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill children-profiling-limits -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/children-profiling-limits, .gemini/skills/children-profiling-limits, .github/skills/children-profiling-limits and .opencode/skills/children-profiling-limits in your project.
What does Children Profiling Limits need to run?
Going by SKILL.md and its folder, Children Profiling Limits needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Children Profiling Limits access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Children Profiling Limits safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Children Profiling Limits use?
Children Profiling Limits is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Children Profiling Limits use?
About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.2k tokens, read only when the agent opens those files.
What are the alternatives to Children Profiling Limits?
Skills that share tags, products or a category with Children Profiling Limits: C15t (c15t/c15t, 1.9k stars), HIPAA Safe Harbor Coverage Audit (maziyarpanahi/openmed, 5.5k stars), Korean Privacy Terms (kimlawtech/korean-privacy-terms, 586 stars) and Gdpr Compliance (Sushegaad/Claude-Skills-Governance-Risk-and-Compliance, 942 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Children Profiling Limits?
mukul975 (a GitHub user) maintains it in mukul975/Privacy-Data-Protection-Skills, which has 295 GitHub stars. The repository holds 278 skills in this directory. The repository was last updated on March 16, 2026.
Source: mukul975/Privacy-Data-Protection-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.