dentist-agent

Emergency dental assistant (Dr. Molar) for triage, first aid, and severity classification of broken/chipped/cracked teeth, delivered over web, Slack, or Telegram. Use for non-diagnostic dental guidance only.

Quality

71%

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 ./modules/skills/src/main/resources/META-INF/skills/dentist-agent/SKILL.md

Quality

Content

65%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.

A well-structured, concise persona skill whose assessment questions and guardrails are genuinely usable, but it stops short of being actionable where it matters: the first-aid instructions and severity-classification criteria it promises are referenced, never specified. Adding those details (or pointing to a reference file containing them) would lift the mid-tier scores.

Suggestions

Provide the actual first-aid guidance (e.g., how to store a knocked-out tooth, cold compress for swelling, bleeding control) instead of only listing 'Provide first-aid instructions' as a skill.

Define explicit severity thresholds mapping symptom combinations to 'go to ER now' vs 'see a dentist within 24h' vs 'next-day appointment', so the urgency recommendation is deterministic.

Remove the duplicated AI-disclosure statement (it appears in both the intro and the Guardrails section) to tighten the token budget.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is lean and assumes Claude's competence, with no padding or explanation of known concepts. Not 5 because the AI-disclosure is stated twice (intro and Guardrails) and a few persona lines restate the description.	4 / 5
Actionability	The assessment questions are concrete ("Pain level (1-10)", "Is the broken piece still available?"), but the skill names its core deliverables without providing them: no actual first-aid instructions and no severity criteria behind "Classify the severity". This matches 'some concrete guidance but incomplete; missing key details', not 4, which requires mostly executable guidance.	3 / 5
Workflow Clarity	An assessment flow is implied (ask questions, then assess, then recommend) and an escalation rule exists ("direct to ER immediately"), but there is no explicit sequence, no decision thresholds for ER vs next-day dentist, and checkpoints are implicit — matching anchor 3 rather than 4.	3 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into clearly labeled sections (Skills, Tools, Channels, Guardrails); per the rubric's simple-skill guidance this earns a 5 with well-organized sections alone.	5 / 5
	Total	15 / 20 Passed

Description

78%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.

A strong description: concrete actions, natural trigger terms, and a distinct niche. The main weakness is the 'when' clause, which limits scope ('non-diagnostic dental guidance only') rather than positively stating when to invoke the skill.

Suggestions

Replace the limiting 'Use for non-diagnostic dental guidance only' with a positive trigger clause such as 'Use when the user reports a broken, chipped, cracked, or knocked-out tooth or any dental emergency'.

Fold one or two more natural user phrasings (e.g., 'dental emergency', 'toothache') into the description to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ("triage, first aid, and severity classification of broken/chipped/cracked teeth") plus delivery channels, matching the 'several specific actions with minor gaps' anchor. It falls short of 5 because body-detailed capabilities like pain management and ER-vs-dentist urgency determination are absent from the description.	4 / 5
Completeness	The 'what' is clear and a 'Use for non-diagnostic dental guidance only' clause provides explicit trigger guidance, so it is not capped at 3. It is not 5 because the 'when' is a negative scope limiter rather than a concrete positive trigger (e.g., 'Use when the user reports a broken or chipped tooth').	4 / 5
Trigger Term Quality	Good natural keyword coverage ("broken/chipped/cracked teeth", "triage", "first aid", "Emergency dental") that mirrors how users would describe the problem. Not 5 because common user phrasings like "dental emergency", "knocked-out tooth", and "toothache" are missing.	4 / 5
Distinctiveness Conflict Risk	A clear dental-emergency niche with distinct triggers (specific tooth injuries, named channels) and minimal overlap with other skills; the non-diagnostic scoping further reduces mis-trigger risk.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Atmosphere/atmosphere
Path: modules/skills/src/main/resources/META-INF/skills/dentist-agent/SKILL.md
Commit: 1c968d5

Reviewed: 2 days 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.