medical-case-interpreter

Generates compliant medical case report articles for WeChat.

Quality

51%

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 ./scientific-skills/Other/medical-case-interpreter/SKILL.md

Quality

Content

50%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 medical generation rules are concrete and actionable, but the skill is padded with generic boilerplate that adds little and even contradicts the actual workflow (script validation referenced at top, denied at bottom). Trimming the boilerplate and integrating validation into the generation steps would improve clarity and token efficiency.

Suggestions

Remove the generic boilerplate sections ("When to Use", "Dependencies", "Recommended Workflow", "Output Contract", "Failure Handling", "Completion Checklist") that duplicate or dilute the medical-specific instructions.

Resolve the validation contradiction: either treat scripts/validate_skill.py as the verification path or drop the script reference rather than stating "No local script validation step is required."

Integrate validation/safety checkpoints directly into Step 1 and Step 2 (e.g. confirm anonymization before generating the body) so the workflow has explicit checkpoints instead of separate generic rules.

Dimension	Reasoning	Score
Conciseness	The body includes large amounts of generic boilerplate ("When to Use", "Dependencies", "Recommended Workflow", "Output Contract", "Failure Handling", "Completion Checklist") alongside the real medical content, and even contradicts itself on validation, matching the "noticeably verbose; several unnecessary padded sections" anchor.	2 / 5
Actionability	The medical section gives concrete, executable rules (anonymize to "Patient (Gender, Age)", convert dates to "Day 1", foreword under 200 words, exact headers like "## Case Report" and "### Treatment Process"), which is mostly executable instruction-style guidance with only minor gaps.	4 / 5
Workflow Clarity	Steps 1 (privacy/cleaning) and 2 (content generation) are sequenced, but validation checkpoints live in disconnected generic sections rather than being integrated into the generation flow, matching the "steps listed but checkpoints missing or implicit" anchor.	3 / 5
Progressive Disclosure	The body has section headers and one real referenced bundle file (scripts/validate_skill.py), but it monolithically inlines generic boilerplate with the skill-specific content and signals the script inconsistently, fitting the "some structure but could be better organized" anchor.	3 / 5
	Total	12 / 20 Passed

Description

53%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 domain-specific and clear about what it does, but it lacks explicit "when to use" trigger guidance and offers only one concrete action with limited keyword variation. Adding a Use-when clause with natural trigger phrases would raise completeness and trigger-term quality.

Suggestions

Append a "Use when..." clause naming concrete triggers, e.g. "Use when the user asks to draft a medical case report or clinical case article for WeChat."

Add natural synonyms and variations (e.g. "clinical case report", "case study article", "WeChat medical post") to broaden trigger-term coverage.

List 1-2 more concrete actions (e.g. anonymize patient data, enforce a fixed article structure) to move specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Generates compliant medical case report articles for WeChat" names a specific domain and one concrete action (generating articles), matching the anchor for naming the domain plus 1-2 concrete actions, though it is not comprehensive.	3 / 5
Completeness	The description clearly states what the skill does but includes no "Use when..." clause or equivalent trigger guidance, so per the rubric completeness is capped at 3 for a clear "what" with missing "when".	3 / 5
Trigger Term Quality	Terms like "medical case report", "articles", and "WeChat" are natural phrases a user might say, but coverage of synonyms and variations is limited, matching the "some relevant keywords but missing common variations" anchor.	3 / 5
Distinctiveness Conflict Risk	The medical-case-report-for-WeChat niche is a distinct, narrow domain with minor overlap risk against closely related writing skills, fitting the "mostly distinct" anchor better than the more generic level 3.	4 / 5
	Total	13 / 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: aipoch/medical-research-skills
Path: scientific-skills/Other/medical-case-interpreter/SKILL.md
Commit: f5ef65b

Reviewed: ~18 hours 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.