Develops data classification policies with tiered handling (public, internal, confidential, restricted), labeling requirements, enforcement mechanisms, and procedures per tier.
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill classification-policy -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills classification-policy --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/classification-policy .claude/skills/classification-policy && 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 "classification-policy" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/classification-policy into .claude/skills/classification-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classification-policy", 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/classification-policyType 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 classification-policy -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills classification-policy --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/classification-policy .agents/skills/classification-policy && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "classification-policy" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/classification-policy into .agents/skills/classification-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classification-policy", 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 classification-policy -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills classification-policy --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/classification-policy .cursor/skills/classification-policy && 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 "classification-policy" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/classification-policy into .cursor/skills/classification-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classification-policy", 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/classification-policy--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 classification-policy -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills classification-policy --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/classification-policy .gemini/skills/classification-policy && 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 "classification-policy" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/classification-policy into .gemini/skills/classification-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classification-policy", 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 classification-policyInstalls 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 classification-policy -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/classification-policy .github/skills/classification-policy && 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 "classification-policy" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/classification-policy into .github/skills/classification-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classification-policy", 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 classification-policy -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 classification-policy --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/classification-policy .opencode/skills/classification-policy && 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 "classification-policy" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/classification-policy into .opencode/skills/classification-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classification-policy", 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.
classification-policyDevelops data classification policies with tiered handling (public, internal, confidential, restricted), labeling requirements, enforcement mechanisms, and procedures per tier.
Classification Policy is an agent skill from mukul975/Privacy-Data-Protection-Skills. Develops data classification policies with tiered handling (public, internal, confidential, restricted), labeling requirements, enforcement mechanisms, and procedures per tier. Covers policy governance, exception handling, and compliance monitoring. Keywords: classification policy, data tiers, handling procedures, labeling, enforcement, data governance, information security.
Its SKILL.md is about 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, Data governance and Error handling. 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.
Read from SKILL.md and the folder at commit 9b2ef9e. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Classification Policy loads about 3k tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 100 tokens; SKILL.md has 1,196 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.
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.
The full file from mukul975/Privacy-Data-Protection-Skills at commit 9b2ef9e, republished under its Apache-2.0 licence (© mukul975). 1,196 words, ~3,033 tokens.
.claude/skills/classification-policy/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.A data classification policy establishes the enterprise-wide framework for categorising data by sensitivity level and prescribing handling requirements per tier. The policy translates GDPR classification obligations (personal, special category, criminal) and information security requirements (confidentiality, integrity, availability) into practical, enforceable rules that govern how data is stored, transmitted, accessed, and disposed of throughout its lifecycle. This skill covers the design, implementation, and enforcement of a four-tier classification scheme aligned with GDPR requirements and ISO 27001 Annex A controls.
| Tier | Label | Description | GDPR Mapping | ISO 27001 Mapping |
|---|---|---|---|---|
| Tier 1: Public | PUBLIC | Information approved for public release. Disclosure carries no risk to the organisation or individuals. | Anonymised data (Recital 26), published reports, public filings | A.8.2 — Unclassified/Public |
| Tier 2: Internal | INTERNAL | Information for internal use only. Disclosure would cause minor inconvenience but no significant harm. | Pseudonymised aggregate data, internal procedures, organisational charts | A.8.2 — Internal |
| Tier 3: Confidential | CONFIDENTIAL | Information whose disclosure would cause significant harm to individuals or the organisation. | Personal data (Art. 4(1)), financial data, customer records, employee records | A.8.2 — Confidential |
| Tier 4: Restricted | RESTRICTED | Information whose disclosure would cause severe harm, regulatory sanction, or irreversible damage. | Art. 9 special category data, Art. 10 criminal data, trade secrets, regulatory investigation data | A.8.2 — Restricted/Secret |
| Data Type | Tier | Rationale |
|---|---|---|
| Published annual report | PUBLIC | Approved for public disclosure |
| Internal org chart | INTERNAL | No individual harm from disclosure, but not intended for external distribution |
| Customer name and email | CONFIDENTIAL | Personal data — disclosure would breach GDPR obligations |
| Customer account number and transactions | CONFIDENTIAL | Personal data with financial sensitivity |
| Employee National Insurance Number | CONFIDENTIAL (borderline RESTRICTED) | High-sensitivity direct identifier |
| Employee health records | RESTRICTED | Art. 9 special category data |
| Biometric access templates | RESTRICTED | Art. 9 biometric data |
| Criminal background check results | RESTRICTED | Art. 10 criminal data |
| AML investigation files | RESTRICTED | Criminal data + legal privilege |
| Board strategic plans | RESTRICTED | Commercial sensitivity |
| Encryption keys and credentials | RESTRICTED | Security-critical |
| Control | Requirement |
|---|---|
| Storage | No restrictions; any approved platform |
| Transmission | No restrictions; may be sent via any channel |
| Access control | No restrictions; accessible to all |
| Encryption | Not required (but recommended for integrity) |
| Retention | Per document retention schedule |
| Disposal | Standard deletion |
| Labelling | Label: "Public" or no label required |
| Control | Requirement |
|---|---|
| Storage | Vanguard-managed systems only (no personal devices, no personal cloud) |
| Transmission | Vanguard email or approved collaboration tools; not via personal email |
| Access control | All Vanguard employees and approved contractors with valid account |
| Encryption | Required in transit (TLS 1.2+); recommended at rest |
| Retention | Per document retention schedule |
| Disposal | Standard secure deletion (file system delete) |
| Labelling | Label: "Internal" applied via header/footer or metadata |
| Control | Requirement |
|---|---|
| Storage | Vanguard-managed systems with access controls; encrypted at rest (AES-256) |
| Transmission | Encrypted email (TLS 1.3 or S/MIME); approved SFTP; no unencrypted channels |
| Access control | Role-based access control (RBAC); business need-to-know; MFA required |
| Encryption | Required at rest (AES-256) and in transit (TLS 1.3); field-level encryption for high-sensitivity fields |
| Printing | Permitted with secure print release; printed copies secured in locked cabinets |
| External sharing | Permitted only with approved third parties under DPA/NDA; DPO approval for new recipients |
| Retention | Per data-specific retention schedule; automated enforcement |
| Disposal | Secure overwrite (NIST 800-88 Clear); shredding for physical media |
| Labelling | Label: "Confidential" in document header/footer, email subject tag, and metadata |
| Audit | Access logged; quarterly review of access permissions |
| DLP | DLP policies active: warn on external sharing, block sharing to personal email |
| Control | Requirement |
|---|---|
| Storage | Designated restricted-access systems only; encrypted at rest with customer-managed keys; separate network segment or HSM where applicable |
| Transmission | End-to-end encrypted channels only; no email without encryption; approved secure file transfer only |
| Access control | Named individual access lists (not role-based); dual-person authorisation for bulk access; MFA required; privileged access management (PAM) |
| Encryption | AES-256 at rest with customer-managed keys; TLS 1.3 in transit; field-level encryption mandatory |
| Printing | Prohibited unless specifically authorised by DPO; watermarked with user identity |
| External sharing | Prohibited unless DPO and Chief Privacy Officer jointly approve; encrypted transfer only |
| Retention | Strict retention with automated deletion; no extensions without DPO approval |
| Disposal | NIST 800-88 Purge (cryptographic erasure or physical destruction); disposal certificate required |
| Labelling | Label: "Restricted" in document header/footer (red), email banner, and metadata; visual marking on screens |
| Audit | All access logged with user identity, timestamp, and purpose; monthly audit review by DPO |
| DLP | DLP policies active: block all external sharing, block USB copy, block print, block screenshot; alert DPO on policy trigger |
| Incident response | Any unauthorised access or disclosure treated as data breach; immediate DPO notification |
| Section | Content |
|---|---|
| 1. Purpose and Scope | Defines why classification is required and what data is covered |
| 2. Classification Tiers | Four-tier definitions with examples |
| 3. Roles and Responsibilities | Data owner, data steward, DPO, IT Security, all employees |
| 4. Classification Procedures | How to classify new data, reclassification triggers |
| 5. Handling Requirements | Per-tier controls matrix |
| 6. Labelling Requirements | How to apply labels (manual and automated) |
| 7. Exception Process | How to request exceptions with risk acceptance |
| 8. Enforcement | Monitoring, audit, and consequences for violations |
| 9. Training | Classification awareness training requirements |
| 10. Review Schedule | Annual review; interim reviews on regulatory change |
| Role | Responsibility |
|---|---|
| Data Owner (business unit head) | Classify data for their business function; approve access requests; review classifications annually |
| Data Steward (departmental) | Maintain classification labels; ensure handling compliance in their area; report classification issues |
| DPO | Oversee policy compliance; approve Restricted tier exceptions; conduct classification audits |
| IT Security | Implement technical controls per tier; manage DLP policies; configure encryption; monitor audit logs |
| All Employees | Apply classification labels to data they create; handle data per tier requirements; report suspected misclassification |
| Privacy Engineering | Configure automated classification tools; manage discovery platforms; tune detection accuracy |
Exception Request
│
├─► Step 1: Requestor documents the exception
│ - What data? What tier? What control cannot be met?
│ - Why is the exception needed?
│ - What alternative controls are proposed?
│ - Duration of exception requested
│
├─► Step 2: Risk Assessment
│ - Data Steward assesses the risk of the exception
│ - For Confidential tier: Data Owner approves
│ - For Restricted tier: DPO and CISO jointly approve
│
├─► Step 3: Approval and Documentation
│ - Exception recorded in exception register
│ - Alternative controls documented and implemented
│ - Expiry date set (maximum 12 months, renewable)
│
└─► Step 4: Review
- Exception reviewed at expiry
- Renewed only if original justification remains valid
- Chronic exceptions trigger process improvement| Mechanism | Implementation |
|---|---|
| Automated labelling | Microsoft Purview auto-labelling applies Confidential/Restricted labels based on detected PII |
| DLP policies | Microsoft Purview DLP blocks or warns on policy violations (external sharing, USB copy) |
| Access reviews | Quarterly certification of access permissions for Confidential; monthly for Restricted |
| Audit logging | All access to Confidential and Restricted data logged and retained for 2 years |
| Classification audits | DPO conducts semi-annual audits sampling 100 items per tier for classification accuracy |
| Training compliance | Annual classification training required for all employees; completion tracked in LMS |
| Disciplinary policy | Violations escalated per employee handbook: warning → formal warning → disciplinary action |
© 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
SKILL.md and 4 other files (scripts, references, assets) in skills/privacy/classification-policy of mukul975/Privacy-Data-Protection-Skills.
Open the folder on GitHubat commit 9b2ef9e
Classification Policy 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 |
|---|---|---|---|---|---|---|
| Classification Policy this skillmukul975/Privacy-Data-Protection-Skills | 295 | — | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Implementing Cloud Dlp For Data Protectionmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Cometchat Compliancecometchat/cometchat-skills | 129 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Data Policyericrisco/rsc-harness | 156 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Nw Security And GovernancenWave-ai/nWave | 617 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Data Security Officertheneoai/awesome-skills | 183 | — | ~2.4k | Automated safety check: Pass | MIT |
mukul975/Anthropic-Cybersecurity-Skills
Implement cloud DLP using Amazon Macie, Google Cloud DLP API, Microsoft Purview, Azure Information Protection, and Nightfall AI to discover, classify, label, de-identify, and protect sensitive data…
cometchat/cometchat-skills
Data governance & compliance for CometChat — pick the data-residency region, satisfy GDPR/CCPA (right-to-erasure and data export), plan message retention & purge, and produce audit / eDiscovery…
ericrisco/rsc-harness
A skill your agent uses when building internal data-governance machinery: a retention schedule (period, lawful basis, expiry action, system where deletion runs), an Art.
nWave-ai/nWave
Database security (encryption, access control, injection prevention), data governance (lineage, quality, MDM), and compliance frameworks (GDPR, CCPA, HIPAA)
theneoai/awesome-skills
Expert-level Data Security Officer with deep knowledge of data classification, DLP strategy, encryption at rest and in transit, data governance frameworks, regulatory compliance (GDPR, CCPA, PIPL…
glebis/claude-skills
Runs a human-first workflow for labeling PII spans in a transcript, then scores inter-annotator agreement and drafts an adjudicated gold set.
mukul975/Privacy-Data-Protection-Skills
Implements age-gating mechanisms for online services to restrict access based on user age.
mukul975/Privacy-Data-Protection-Skills
Manages AI model retention and machine unlearning requirements.
mukul975/Privacy-Data-Protection-Skills
Structures risk mitigation planning and residual risk tracking for Data Protection Impact Assessments under GDPR Article 35(7)(d).
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.
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.
mukul975/Privacy-Data-Protection-Skills
Designs and implements data retention schedules compliant with GDPR Article 5(1)(e) storage limitation principle.
Categories
Develops data classification policies with tiered handling (public, internal, confidential, restricted), labeling requirements, enforcement mechanisms, and procedures per tier. Classification Policy is an agent skill from mukul975/Privacy-Data-Protection-Skills. Develops data classification policies with tiered handling (public, internal, confidential, restricted), labeling requirements, enforcement mechanisms, and procedures per tier.
Classification Policy fits situations like: tasks that involve Privacy and GDPR; tasks that involve Data governance; tasks that involve Error handling.
Run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill classification-policy -a claude-code`. Or copy the skill folder (skills/privacy/classification-policy in mukul975/Privacy-Data-Protection-Skills) into .claude/skills/classification-policy in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill classification-policy -a codex`. Or copy the skill folder (skills/privacy/classification-policy in mukul975/Privacy-Data-Protection-Skills) into .agents/skills/classification-policy in your project. Codex loads it when a task matches its description.
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 classification-policy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/classification-policy, .gemini/skills/classification-policy, .github/skills/classification-policy and .opencode/skills/classification-policy in your project.
Going by SKILL.md and its folder, Classification Policy needs Python for the scripts in its folder. Our summary lists: Python 3.
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.
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.
Classification Policy 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.
About 3k tokens (SKILL.md is roughly 12k 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 1.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Classification Policy: Implementing Cloud Dlp For Data Protection (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Cometchat Compliance (cometchat/cometchat-skills, 129 stars), Data Policy (ericrisco/rsc-harness, 156 stars) and Nw Security And Governance (nWave-ai/nWave, 617 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.
