CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sexual-health-analyzer

Sexual Health Analyzer

Quality

45%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/sexual-health-analyzer/SKILL.md

The canonical home for this skill is sexual-health-analyzer in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

38%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 a well-organized but monolithic 1,100-line medical reference dumped into SKILL.md, with no bundle files, no executable mechanics for the data it claims to analyze, and substantial duplication of medical knowledge Claude already has. Scoring tables and scenario walkthroughs give it real domain value, but structure and token efficiency are far below skill best practices.

Suggestions

Split the SKILL.md into reference files (e.g., references/iief5.md, references/std-screening.md, references/contraception.md, references/cross-module.md) and keep the main file to an overview plus one-line pointers.

Trim knowledge Claude already has (general lifestyle guidance, nutrient food sources, drug-class side effects) down to the app-specific values: scoring weights, cutoffs, and interval tables.

Add concrete mechanics for the claimed workflows: where module data lives, its format, how to compute the risk scores step by step, and how to render the listed visualizations — plus an explicit validation checkpoint before reporting (e.g., refuse analysis when records are incomplete).

DimensionReasoningScore

Conciseness

The body is a ~1,100-line / 26 KB monolithic catalog inlined in SKILL.md. Much of it restates general medical knowledge Claude already has (lifestyle guidance like "150 minutes of moderate aerobic exercise per week", Mediterranean diet composition, zinc food sources, drug-class effects like "SSRIs can cause sexual dysfunction"), matching anchor 2 ('noticeably verbose; several unnecessary explanations or padded sections'). It avoids anchor 1 only because substantial portions are skill-specific data (the app's risk-scoring weights, IIEF-5 severity cutoffs, screening-interval tables) rather than pure padding.

2 / 5

Actionability

Concrete elements exist — specific scoring tables (ED risk weights by factor, STD behavioral scoring), severity cutoffs, and five numbered scenario workflows — but execution mechanics are missing: no data paths or formats for the referenced modules ("medication module data", "chronic illness module data"), no code or commands, and visualization outputs are named but never specified. This matches anchor 3 ('Some concrete guidance but incomplete; missing key details') and not anchor 4, whose examples include executable code.

3 / 5

Workflow Clarity

The five usage scenarios list coherent numbered analysis flows (e.g., Scenario 2: retrieve IIEF-5 history → analyze medications → assess chronic disease control → ... → generate plan), and a quality-assurance section names data validation. However, checkpoints are implicit and never wired into the steps (no 'verify data completeness before interpreting', no error handling for missing records), matching anchor 3 ('sequence present but checkpoints missing or implicit'). Not anchor 2, because sequences are well-defined and consistent across scenarios.

3 / 5

Progressive Disclosure

The skill bundle contains no references/, scripts/, or assets/ directories — everything is inlined in SKILL.md. Content that clearly belongs in separate reference files (the full STD disease reference, the eight-method contraception catalog, the nutrition and medication cross-analysis) is inlined, exactly matching anchor 2 ('Minimal structure; content that clearly belongs in separate files is inlined'). It avoids anchor 1 because the body does have real structure (numbered sections, tables, headers), but cannot reach 3+ since there is no file-level disclosure at all.

2 / 5

Total

10

/

20

Passed

Description

28%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 a bare title ("Sexual Health Analyzer") that fails at nearly every job a description must do: no capabilities listed, no use-when guidance, and no natural trigger terms. It would rarely be selected for a user request because nothing in it matches what users actually ask for.

Suggestions

State concrete capabilities in third person, e.g., "Analyzes IIEF-5 scores for ED severity, manages STD screening schedules, evaluates contraceptive methods, and tracks sexual activity logs."

Add an explicit trigger clause: "Use when the user mentions erectile dysfunction, IIEF-5, STD/STI screening, contraception, or sexual health tracking."

Include natural synonyms users would say (ED, 勃起功能障碍, 避孕, 性病筛查) so the skill matches real phrasing.

DimensionReasoningScore

Specificity

The description is only the phrase "Sexual Health Analyzer" — it names the domain (sexual health) but contains no concrete actions whatsoever. It matches the anchor 'Names the domain but actions are minimal or generic' ("Processes PDF files") rather than anchor 1, because the domain label is specific, not generic like "Helps with documents"; but it cannot score 3 since not even one concrete action (analyze, assess, track) is stated.

2 / 5

Completeness

The 'what' is extremely vague — a bare label with no described capabilities — and the 'when' is entirely absent, matching anchor 2 ('Has a vague what and no when'). It is not anchor 1 only because the domain is named at all; the guideline capping completeness at 3 for a missing 'Use when...' clause is satisfied, and it falls further to 2 because the 'what' is also nearly empty.

2 / 5

Trigger Term Quality

"Sexual health" is one relevant domain keyword, but the description offers no natural trigger phrases a user would say (e.g., "IIEF-5", "STD screening", "contraception", "erectile dysfunction"). It sits between anchor 1 (no natural keywords) and anchor 3 (some relevant keywords with missing variations), fitting anchor 2's 'one or two generic keywords; missing the natural phrases users say'.

2 / 5

Distinctiveness Conflict Risk

The sexual-health domain is a niche that would not conflict with unrelated skills, but the description has no distinct triggers and could overlap with general health-analysis or medical-analysis skills, matching anchor 3 ('Somewhat specific but could still overlap with similar skills'). It cannot score 4 because anchor 4's minor-overlap profile assumes actual capability/trigger signals, which are absent here.

3 / 5

Total

9

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1121 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/sexual-health-analyzer/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.