data-minimisation

Use when reviewing form components, API payloads, or client-side storage to identify fields that are collected but not consumed by a stated feature.

Quality

70%

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 ./skills/data-minimisation/SKILL.md

Quality

Content

65%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 content is well-structured with a clean overview and an appropriate single-level reference, plus concrete actionable audit guidance. It is held back by motivational padding in the intro and the absence of explicit validation checkpoints in the workflow.

Suggestions

Trim or remove the opening paragraph on breach blast radius and GDPR fines; Claude already knows this context and it competes with the token budget.

Add an explicit validation/verification checkpoint, e.g. 'After fixes, re-scan payloads to confirm no raw PII remains', to lift workflow clarity above a 3.

Inline one short executable example (e.g. a pseudonymisation helper or a retention-clear snippet) so the body is self-sufficient for the common case.

Dimension	Reasoning	Score
Conciseness	Mostly efficient sections, but the opening paragraph restates breach/regulatory motivation (GDPR Article 5(1)(c), blast radius, fines, trust) that Claude already knows, matching the 'mostly efficient but includes some unnecessary explanation' anchor; not a 4 because that motivational padding is clearly trimmable.	3 / 5
Actionability	Concrete, specific guidance names exact surfaces (form fields, API request bodies, storage keys, analytics/logging payloads) and exact PII types (email, names, phone numbers, full query strings) plus concrete remediation (pseudonymous IDs, retention windows); held below 5 because executable code examples are delegated to the reference rather than shown inline.	4 / 5
Workflow Clarity	Check/Fix/Explain/Code Review sections give an implicit audit-then-remediate sequence, but there are no explicit validation checkpoints or feedback loops; the review nature avoids the destructive-cap, yet it still fits the 'steps listed but validation gaps' anchor better than anchor 4.	3 / 5
Progressive Disclosure	The body is a concise overview with well-organized sections and a single, clearly signaled one-level-deep pointer to references/rule.md (a real file) for full details, matching the 'clear overview with well-signaled one-level-deep references' anchor.	5 / 5
	Total	15 / 20 Passed

Description

75%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 is specific and complete, clearly answering both what the skill does and when to invoke it with concrete review surfaces. It is held below top marks by a single core action and the absence of common synonyms (PII, personal data, privacy).

Suggestions

Add natural trigger synonyms users say, e.g. 'PII', 'personal data', or 'privacy review', to broaden trigger coverage.

Expand the 'what' beyond the single identify-unused-fields action to mention remediation (anonymise/remove) for more comprehensive capability coverage.

Dimension	Reasoning	Score
Specificity	Names concrete surfaces (form components, API payloads, client-side storage) and a specific action (identify fields collected but not consumed by a stated feature), matching the 'several specific actions; minor gaps' anchor; not a 5 because it hinges on a single core action across surfaces rather than multiple distinct operations.	4 / 5
Completeness	Explicitly states both what (identify fields collected but not consumed) and when ('Use when reviewing form components, API payloads, or client-side storage'); the 'when' is condition-based on surfaces rather than concrete user-utterance triggers, keeping it just below anchor 5.	4 / 5
Trigger Term Quality	Includes natural review-oriented terms a user would say (form components, API payloads, client-side storage) but omits common synonyms like PII, personal data, or privacy, so it falls short of comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The 'collected but not consumed by a stated feature' framing carves a clear privacy niche with distinct triggers; minor overlap risk with general code-review skills prevents a 5.	4 / 5
	Total	16 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: thedaviddias/Front-End-Checklist
Path: skills/data-minimisation/SKILL.md
Commit: 30756a7

Reviewed: 8 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.