symptom-checker-triage

Suggest triage levels (Emergency, Urgent, Outpatient) based on red flag symptoms using a rule-based engine. For AI-assisted decision support only — not a substitute for professional medical diagnosis.

Quality

69%

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/symptom-checker-triage/SKILL.md

Quality

Content

77%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 highly actionable with a clear, validated workflow and concrete examples, but it is held back by repeated disclaimers/commands and a broken reference to a missing `references/red_flags.md`. Fixing the broken link and deduplicating would materially raise the score.

Suggestions

Create the referenced `references/red_flags.md` (or inline the red-flag detail) so the "Full red flags reference" link resolves instead of 404-ing.

Remove the standalone "Quick Check" section (its command already appears in "Audit-Ready Commands") and consolidate the medical disclaimer to a single "Disclaimer" section to cut repetition.

Merge the overlapping "Stress-Case Output Checklist" and "Output Requirements" sections so the required output sections are stated once.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient operational content, but the medical disclaimer is repeated in four places and the "Quick Check" `python -m py_compile` command duplicates the first line of "Audit-Ready Commands" — redundancy that could be tightened rather than minor trimming.	3 / 5
Actionability	Copy-paste-ready CLI commands with real symptom-string examples cover the common cases (direct input, --interactive, --verbose, --json) and a concrete JSON output format plus a fallback template give fully executable guidance.	5 / 5
Workflow Clarity	The five-step Workflow has an explicit validation step ("Validate that the request is a symptom triage task; stop early if not"), an error-recovery feedback loop (step 5 → Fallback Template), and supporting checklists (Stress-Case Output Checklist, Output Requirements).	5 / 5
Progressive Disclosure	Sections are well-organized with a one-level-deep, clearly signaled reference, but the referenced `references/red_flags.md` does not exist in the bundle, leaving the promised red-flag detail neither inline nor accessible — a real structural gap beyond minor organization issues.	3 / 5
	Total	16 / 20 Passed

Description

61%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 states a clear, specific purpose with good natural trigger terms and a distinct niche, but it lacks an explicit "Use when..." trigger clause and leans on a disclaimer in its place. Adding concrete trigger guidance would lift the completeness score.

Suggestions

Add an explicit trigger clause such as "Use when a user describes symptoms and asks how urgent they are, what triage level applies, or whether to seek emergency care."

Move the medical disclaimer out of the description (it is repeated in the body) and replace it with a synonym-rich trigger phrase set so the "when" is unambiguous.

Dimension	Reasoning	Score
Specificity	"Suggest triage levels (Emergency, Urgent, Outpatient) based on red flag symptoms using a rule-based engine" names the domain plus one to two concrete actions (suggest level, identify red flags) with named levels and mechanism, but offers a single core action rather than comprehensive coverage.	3 / 5
Completeness	The "what" is clear, but there is no "Use when..." clause or equivalent trigger guidance; the second sentence ("For AI-assisted decision support only — not a substitute for professional medical diagnosis") is a disclaimer, not a trigger, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Natural user-facing keywords are present ("triage levels", "red flag symptoms", "Emergency/Urgent/Outpatient") that a user would plausibly say, though a few common synonyms (e.g. "should I go to the ER", "medical advice") are missing.	4 / 5
Distinctiveness Conflict Risk	The symptom-triage / red-flag niche is mostly distinct with specific triggers, but as part of a medical-research-skills family it has minor overlap risk with closely related diagnostic or medical-advice skills.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/symptom-checker-triage/SKILL.md
Commit: 63c61d3

Reviewed: 4 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.