CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

privacy

Review PsychSift sensitive-data collection, ownership, retention, logging, caching, export, deletion, telemetry, and client exposure. Use for privacy changes, clinical queries, user data, logs, analytics, or data-subject operations.

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

An extremely concise, well-sequenced review checklist with a clear safety guardrail. Its main gap is actionability: the steps tell Claude what to examine but not how, lacking concrete commands, repo-specific locations, or an example of the 'local proofs' it requests.

Suggestions

Add one or two concrete examples of a 'focused local proof' (e.g., a test command or assertion pattern for redaction or non-persistence) so step 4 is executable rather than aspirational.

Name the specific places in the PsychSift repo to inspect (e.g., telemetry initialization, query-log module, client bundle entry point) so steps 1-3 point at real locations instead of generic categories.

Include a brief verification checkpoint for the report step, such as confirming each identified data flow has a corresponding control or documented gap before finishing.

DimensionReasoningScore

Conciseness

Six lean numbered lines with zero padding and no explanation of concepts Claude already knows; every token earns its place, matching the 'lean and efficient' anchor.

5 / 5

Actionability

It names concrete artifact categories to inspect ("client bundles, errors, telemetry, query logs, temporary files, and generated artifacts") but provides no commands, file paths, or examples of what a 'focused local proof' concretely looks like, fitting 'some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

The inventory, trace, check, prove, guardrail, report sequence is clearly ordered, and step 4 ('Add focused local proofs') plus step 5's approval gate act as checkpoints, but there is no explicit validate-and-retry feedback loop, so it sits at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and no need for external references; the single well-organized numbered list satisfies the rubric's simple-skill exception for a top progressive-disclosure score.

5 / 5

Total

17

/

20

Passed

Description

83%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 strong description that explicitly states both capabilities and usage triggers with domain-specific scoping. Its main weaknesses are reliance on a single action verb and a few missing common privacy synonyms (PII, GDPR, right-to-delete) in the trigger list.

DimensionReasoningScore

Specificity

Enumerates nine concrete privacy-lifecycle areas ("collection, ownership, retention, logging, caching, export, deletion, telemetry, and client exposure"), but they all hang on the single verb "Review" rather than multiple distinct actions, so it falls just below the comprehensive multi-action anchor 5.

4 / 5

Completeness

Clearly answers 'what' ("Review PsychSift sensitive-data collection, ownership, retention, logging, caching, export, deletion, telemetry, and client exposure") and 'when' with an explicit "Use for..." clause listing concrete trigger phrases, exactly matching the top anchor.

5 / 5

Trigger Term Quality

"privacy changes, clinical queries, user data, logs, analytics, or data-subject operations" are natural phrases users would say, but common synonyms such as PII, PHI, GDPR/CCPA, or right-to-delete are missing, matching 'good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

The PsychSift scoping and clinical/data-subject framing carve a clear niche with minimal conflict risk, but the generic trigger terms "logs" and "analytics" create minor overlap risk with logging or analytics skills, fitting anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

BigSimmo/PsychSift

Path

.agents/skills/privacy/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.