CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/data-minimisation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

A clean, well-structured overview that delegates implementation detail to a real, clearly-signaled reference file. The body itself is weakened by redundancy (Check vs Code Review), a motivational intro Claude does not need, and the absence of any concrete technique for its central task — deciding when a collected field is truly unconsumed.

Suggestions

Merge the near-duplicate "Check" and "Code Review" sections into one, and drop or compress the "why it matters" intro — the Explain section already covers the rationale for the user.

Add one concrete inline heuristic or command for the core verification step, e.g. "grep the codebase for reads of the field/key before flagging it as unconsumed", so the audit is executable without opening the reference.

Reorder sections into a single check-then-fix flow with an explicit validation point (confirm unused, then remove/anonymise, then re-check the payload) to give the workflow checkpoints.

DimensionReasoningScore

Conciseness

The body is mostly tight, but the motivational intro paragraph ("increases the blast radius of a breach, exposes your organisation to regulatory fines, and erodes user trust") explains context Claude already knows, and the "Check" and "Code Review" sections are near-duplicates of each other (both audit form fields/fetch calls/storage keys plus analytics payloads for raw PII). Mostly efficient but could be meaningfully tightened, matching anchor 3.

3 / 5

Actionability

Concrete audit targets are named ("form components, fetch/axios calls, and storage utilities"; "raw email addresses, names, phone numbers, or full query strings"), but the body contains no executable method for its core step — no commands or heuristics for verifying a field is truly unused, and all code examples are deferred to references/rule.md. Some concrete guidance but incomplete, matching anchor 3.

3 / 5

Workflow Clarity

The sections (Quick Reference, Check, Fix, Explain, Code Review) form a recognizable check-then-fix sequence, but there are no validation checkpoints (e.g. confirming a field is unread by grepping for consumers before flagging it), and "Code Review" sits oddly after "Fix" as a restatement of "Check". Steps listed with validation gaps, matching anchor 3.

3 / 5

Progressive Disclosure

The body is a lean under-50-line overview with a clearly signaled, one-level-deep pointer ("For full implementation details, code examples, and framework-specific guidance, see references/rule.md") to a real file that carries the code examples and detailed guidance. Overview and detail are appropriately split with easy navigation, matching anchor 5.

5 / 5

Total

14

/

20

Passed

Description

71%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.

A well-structured description with an explicit Use-when clause and a clear, precise statement of what the skill does. Its main weakness is trigger vocabulary: the privacy-domain terms users would naturally say (PII, personal data, privacy, GDPR, data minimisation) are entirely absent, limiting discoverability and distinctiveness.

Suggestions

Add the skill's core natural trigger terms to the description — e.g. "personal data", "PII", "data minimisation", or "privacy" — so users asking in privacy vocabulary can find it.

Mention one or two more of the skill's actual capabilities (e.g. auditing analytics/logging payloads for raw PII, or suggesting removal/anonymisation) to raise specificity from one action to several.

Include common artifact names users would say, such as "cookies" or "localStorage", alongside the more abstract "client-side storage".

DimensionReasoningScore

Specificity

The description names the domain ("form components, API payloads, or client-side storage") and one precisely-defined action ("identify fields that are collected but not consumed by a stated feature"), but does not list the several other actions the skill covers (remediation, analytics/log auditing, retention definition). This matches anchor 3: domain plus 1-2 concrete actions without comprehensive coverage.

3 / 5

Completeness

It explicitly answers both questions: the "what" ("identify fields that are collected but not consumed by a stated feature") and the "when" ("Use when reviewing form components, API payloads, or client-side storage") with three concrete trigger contexts. This matches anchor 5: both what and when clearly and explicitly stated with concrete trigger phrases.

5 / 5

Trigger Term Quality

Relevant keywords like "form components", "API payloads", and "client-side storage" are present, but central natural phrases a user would say are missing: "PII", "personal data", "privacy", "data minimisation", "GDPR", "cookies", "localStorage". The skill's own domain vocabulary is absent from the description, matching anchor 3 (some relevant keywords but missing common variations or synonyms).

3 / 5

Distinctiveness Conflict Risk

"Fields collected but not consumed by a stated feature" carves out a distinct audit niche with concrete triggers, but the lack of privacy/PII vocabulary means a generic request like "review my form" could plausibly trigger form-validation or unused-code skills instead. Mostly distinct with minor overlap risk against closely related skills, matching anchor 4.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

thedaviddias/Front-End-Checklist

Path

skills/data-minimisation/SKILL.md

Reviewed

Table of Contents

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.