CtrlK
BlogDocsLog inGet started
Tessl Logo

referral-letter-generator

Generate medical referral letters with patient summary, reason for referral, key findings, and requested next steps; use when transferring care or communicating with another clinician or department.

67

Quality

81%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete executable commands and a clear, validated workflow, but it is significantly bloated with generic boilerplate and redundant sections, and it under-uses its real reference bundle by pointing generically at the folder instead of linking specific files.

Suggestions

Remove the generic boilerplate sections ('Risk Assessment', 'Security Checklist', 'Lifecycle Status', 'Evaluation Criteria', 'Output Requirements', 'Response Template') and collapse redundant scope/input/error sections to cut the body to a lean overview.

Replace 'See references/ folder for: ...' with explicit one-level-deep links to the actual files (e.g., 'See [referral_template.md](references/referral_template.md)') so navigation is well-signaled.

Move the detailed input-parameter and risk/compliance material into reference files, keeping SKILL.md as a concise overview pointing to them.

DimensionReasoningScore

Conciseness

The ~260-line body is padded with generic boilerplate ('Risk Assessment', 'Security Checklist', 'Lifecycle Status', 'Evaluation Criteria', 'Output Requirements', 'Response Template') and heavy redundancy (overlapping 'When to Use'/'Use Cases', 'Input Parameters'/'Required Inputs', 'Error Handling'/'Failure Handling'/'Input Validation'/'When Not to Use'); this matches the 'verbose; padded with unnecessary context' anchor and is not level 2 because the padding is pervasive rather than occasional.

1 / 3

Actionability

Quotes 'python scripts/main.py --input patient_data.json --output referral_letter.pdf', 'python -m py_compile scripts/main.py', 'python scripts/main.py --help', and the Python API call with a real function signature are concrete, executable guidance; matches the 'fully executable code/commands; copy-paste ready' anchor and is above the 'pseudocode instead of executable code' level.

3 / 3

Workflow Clarity

The numbered 'Workflow' (steps 1-5) plus 'Quick Check' and 'Audit-Ready Commands' provide a clear sequence with explicit validation checkpoints, and 'Error Handling'/'Failure Handling' give feedback loops for recovery, matching the top anchor; it is not level 2 because validation steps and error-recovery loops are explicit rather than implicit.

3 / 3

Progressive Disclosure

Real bundle files exist (references/referral_template.md, referral_standards.md, templates.md, etc.) but the body only says 'See references/ folder for: Sample referral letter templates...' without naming or linking specific files, and large amounts of boilerplate that belong in separate files are inline; matches the 'references present but not clearly signaled; content that should be separate is inline' anchor and is not level 3 because navigation is not well-signaled with one-level-deep links.

2 / 3

Total

9

/

12

Passed

Description

100%

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 strong: it states concrete capabilities, includes explicit natural trigger terms, answers both what and when, and occupies a clear niche. Third-person imperative voice is used correctly with no first/second-person penalty.

DimensionReasoningScore

Specificity

Quotes 'Generate medical referral letters with patient summary, reason for referral, key findings, and requested next steps' lists multiple specific concrete components of the action rather than vague language; matches the 'Lists multiple specific concrete actions' anchor and is above the 'names domain and some actions' level.

3 / 3

Completeness

It explicitly answers both what ('Generate medical referral letters with patient summary, reason for referral, key findings, and requested next steps') and when ('use when transferring care or communicating with another clinician or department') with an explicit 'Use when' trigger, matching the top anchor; it is not level 2 because the trigger is explicit rather than implied.

3 / 3

Trigger Term Quality

Quotes 'medical referral letters', 'transferring care', 'communicating with another clinician or department' are natural terms a clinician would actually say; good coverage matching the 'natural terms users would say' anchor and above the 'some relevant keywords but missing common variations' level.

3 / 3

Distinctiveness Conflict Risk

The medical referral letter niche with triggers 'transferring care or communicating with another clinician or department' is a clear, distinct domain unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor; it is above the 'somewhat specific but could still overlap' level.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
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.