Name: privacy-by-design
Rating: 54.400000000000006 (1 reviews)
Author: administrakt0r

privacy-by-design

Use when building apps that collect user data. Ensures privacy protections are built in from the start—data minimization, consent, encryption.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/privacy-by-design/SKILL.md

The canonical home for this skill is privacy-by-design in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and supplies concrete, actionable code across the core privacy patterns, but it is noticeably padded with rationale Claude already knows and redundant checklists, and it lacks validation checkpoints for the destructive deletion/purge operations it recommends.

Suggestions

Trim the 'Deep Dive: Why It Matters' section and the CCPA/LGPD definitional summaries — Claude knows these; keep only the actionable consequence (e.g. 'define retention_days per data type and automate cleanup').

Consolidate the four overlapping lists (Common Pitfalls, Implementation Checklist, Best Practices, Third-Party Audit) into a single sequenced checklist to cut redundancy.

Add explicit validation steps around destructive flows — e.g. after account deletion: verify user row purged, verify backups covered by retention, verify third-party data deletion requested/confirmed.

Dimension	Reasoning	Score
Conciseness	Concrete code examples earn their place, but the body pads with rationale Claude already knows (the 'Deep Dive: Why It Matters' explanations, summaries of what CCPA/LGPD are) and runs four overlapping lists (When to Use, Common Pitfalls, Implementation Checklist, Best Practices, Third-Party Audit) — efficient in parts but with clear trimmable material, matching the 'mostly efficient but some unnecessary explanation' anchor rather than the noticeably padded anchor 2.	3 / 5
Actionability	Multiple concrete, mostly-executable examples (minimal user model, consent-gated tracking, redacted logging, SQL schema with purpose/retention, API allowlist) plus actionable checklists give strong guidance; it stops short of 5 because several snippets use placeholder functions (hash_user_id, userConsent.analytics) and BAD/GOOD pattern illustrations rather than copy-paste-ready implementations.	4 / 5
Workflow Clarity	The skill offers checklists rather than a sequenced multi-step workflow, and the destructive operations it endorses (data purge, retention deletion, account deletion including backups) carry no validation/verification steps, which caps workflow clarity at 3 per the destructive-operations rule; there is no real sequence to push it higher.	3 / 5
Progressive Disclosure	The single-file skill is well-organized with clear, navigable section headers and no need for external references; it is not a 5 because the ~200-line body inlines rationale (Deep Dive, Legal Frameworks detail) and repeats 'When to Use' guidance that a tighter overview or a split reference could offload.	4 / 5
	Total	14 / 20 Passed

Description

62%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description cleanly states both what the skill does and when to use it, with a recognizable privacy niche. It is held back by a single generic action verb and a trigger list that misses common regulatory synonyms (GDPR, PII, compliance) and offers only one trigger phrase.

Suggestions

Lead with concrete verbs instead of 'Ensures ... are built in' — e.g., 'Minimizes collected data, captures consent, encrypts data at rest and in transit, and defines retention/deletion policies.'

Broaden trigger keywords to include natural regulatory terms users say: 'personal data', 'PII', 'GDPR', 'CCPA', 'compliance', 'user accounts'.

Add a second concrete trigger phrase, e.g. 'Use when designing database schemas, APIs, or auth flows that handle personal data.'

Dimension	Reasoning	Score
Specificity	The description names the domain ('building apps that collect user data') and lists three concrete protections ('data minimization, consent, encryption'), but the only action verb is the generic 'Ensures ... are built in'; the named items are concepts/controls rather than actions, so it sits at the 'domain + a few concrete elements' anchor rather than the action-rich anchor 4.	3 / 5
Completeness	Both halves are present and explicit: 'Use when building apps that collect user data' answers when, and 'Ensures privacy protections are built in from the start—data minimization, consent, encryption' answers what; it falls short of a 5 because the trigger guidance offers a single phrase rather than the multiple concrete triggers shown in the anchor-5 example.	4 / 5
Trigger Term Quality	It includes natural terms a user might say ('apps that collect user data', 'privacy protections', 'consent', 'encryption') but omits common variations and regulatory synonyms users frequently invoke in this domain ('personal data', 'PII', 'GDPR', 'CCPA', 'compliance'), leaving it below the 'good coverage, a few missing' anchor.	3 / 5
Distinctiveness Conflict Risk	The privacy-by-design framing (data minimization, consent, encryption) carves a recognizable niche distinct from most skills, with only minor overlap risk against general security or compliance skills; it is not a 5 because the trigger 'apps that collect user data' is broad enough to potentially fire for general data-handling work.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/privacy-by-design/SKILL.md
Commit: 57c135b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.