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

68%

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

71%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 verified executable commands, a clear validated workflow, and strong scope/error handling for a safety-sensitive skill. Its main weaknesses are notable redundancy across three overlapping command sections plus repeated disclaimers, and a broken reference to a missing references/red_flags.md file.

Suggestions

Create the missing references/red_flags.md with the full red-flag categories, or remove the "Full red flags reference" link — a dead reference undermines trust in the whole skill.

Consolidate the Quick Check, Audit-Ready Commands, and CLI Usage sections into a single command section; each currently repeats the same python scripts/main.py invocations.

State the disclaimer once (e.g., in the Disclaimer section) and reference it elsewhere instead of repeating it in the intro, Fallback Template, output warning, and Output Requirements.

Dimension	Reasoning	Score
Conciseness	The body never explains concepts Claude already knows, but it is structurally redundant: the Quick Check duplicates the first Audit-Ready command, CLI Usage repeats the same commands a third time, and the medical disclaimer appears in four-plus places (intro, Fallback Template, output warning, Disclaimer, Output Requirements). This fits "mostly efficient but could be tightened"; not 2 because no section is padded filler and each carries some unique content.	3 / 5
Actionability	Commands are copy-paste ready and verified executable (py_compile, real symptom-string invocations, --interactive, --verbose, --json all match scripts/main.py's argparse), with a concrete JSON output format and a fully specified fallback template covering the common cases. Minor absence of a non-JSON default-output example is not a gap severe enough to drop below anchor 5.	5 / 5
Workflow Clarity	The 5-step workflow has a clear sequence with an explicit validation checkpoint (step 2 scope validation, elaborated in Input Validation) and an error-recovery path (step 5 fallback template, plus Error Handling and the Stress-Case checklist). It sits between anchors 4 and 5: recovery is "switch to the fallback template" rather than a fix-and-retry feedback loop, so the even score applies.	4 / 5
Progressive Disclosure	Section structure is good and the bulk rule content is appropriately externalized to scripts/main.py, but the single advertised external reference, "references/red_flags.md", does not exist in the bundle — the link is broken, so navigation fails exactly where the skill promises detail. This matches "references present but not clearly signaled/effective"; not 4 because a dead reference is a real navigation failure, and not 2 because nothing that belongs in a separate file is wrongly inlined.	3 / 5
	Total	15 / 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 clearly states what the skill does and stays appropriately scoped with a safety disclaimer, but it omits any "Use when..." trigger guidance and underuses natural trigger terms. Adding an explicit use-when clause with user-facing phrases would substantially improve it.

Suggestions

Add an explicit trigger clause, e.g., "Use when a user provides a symptom description and needs a triage level, asks how urgent symptoms are, or mentions red flags or emergency vs. routine care."

Include natural trigger terms users would actually say, such as "symptom check", "how serious", "should I go to the ER", and "urgent care".

Optionally mention the concrete outputs (red flags identified, rationale, recommended next steps) to broaden the specificity of the action list.

Dimension	Reasoning	Score
Specificity	"Suggest triage levels (Emergency, Urgent, Outpatient) based on red flag symptoms using a rule-based engine" names the domain and one concrete action with the levels enumerated, matching the anchor for 1-2 concrete actions. It is not 4 because it does not list several specific actions (e.g., identifying red flags, generating structured output appear only implicitly).	3 / 5
Completeness	The "what" is clearly stated (suggest triage levels from red flag symptoms via a rule-based engine) but there is no "Use when..." clause or equivalent explicit trigger guidance, which per judging guidelines caps completeness at 3. Not 4 because "when" is entirely absent rather than merely imprecise.	3 / 5
Trigger Term Quality	Relevant keywords are present ("triage levels", "red flag symptoms", "Emergency, Urgent, Outpatient") but common natural variations users would say are missing ("symptom check", "how urgent", "should I go to the ER", "medical emergency"). Not 4 because keyword coverage has clear gaps beyond just a few missing synonyms.	3 / 5
Distinctiveness Conflict Risk	"Suggest triage levels (Emergency, Urgent, Outpatient) based on red flag symptoms using a rule-based engine" carves a clear niche with the explicit scope disclaimer "not a substitute for professional medical diagnosis" reducing overlap with general medical Q&A skills. Not 5 because it lacks explicit distinct trigger phrases that would fully separate it from closely related clinical decision-support skills.	4 / 5
	Total	13 / 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: 686e09d

Reviewed: 12 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.