ask-openmed

Choose the first OpenMed workflow skill for an intake, privacy, extraction, exchange, or verification request using deterministic local routing. Use when a goal is broad, spans several clinical-data stages, or leaves the data-sensitivity status unclear; the privacy gate is selected before downstream work when raw clinical or personal content may be present.

Quality

88%

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

Quality

Content

88%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.

An exemplary instruction-only routing skill: a deterministic, precisely-specified procedure with exact markers, fixed ordering, explicit privacy-gate checkpoints, and worked ambiguous-case examples. It is dense and well-structured, with only minor restatement and no progressive-disclosure depth (none needed for a single-file router).

Dimension	Reasoning	Score
Conciseness	Efficient and information-dense — numbered routing rules and cue/skill tables assume Claude's competence and avoid explaining known concepts; minor trimming is possible where the privacy override is restated across the rules and the verification section.	4 / 5
Actionability	Fully actionable procedure: ordered rules, exact safe-marker strings, case-insensitive substring matching, fixed handoff order, and cue-to-skill tables let the routing be executed precisely; worked ambiguous-goal examples cover common cases.	5 / 5
Workflow Clarity	Clear sequenced workflow (rules 1-5, fixed intake→privacy→extraction→exchange→verification order) with explicit checkpoints (privacy gate before downstream, safe-marker verification with negation-window check) and an orientation fallback for no-match cases.	5 / 5
Progressive Disclosure	Well-organized into clear sections (Intake, Privacy, Extraction, Exchange, Verification, Ambiguous goals) with the routing tables appropriately inline; no bundle files exist so all content is self-contained, but it is a longer single file with no progressive-disclosure layering.	4 / 5
	Total	18 / 20 Passed

Description

87%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, specific description that clearly states what the skill does (deterministic local routing to the first OpenMed workflow skill) and when to use it (broad, multi-stage, or sensitivity-unclear goals), with explicit privacy-gate selection. Minor keyword gaps keep trigger quality and specificity at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete routing actions ("Choose the first OpenMed workflow skill...using deterministic local routing", selecting the privacy gate before downstream work) with comprehensive coverage of the five stages, though the action vocabulary is narrow (select/route) rather than transformative.	4 / 5
Completeness	Explicitly answers both what ("Choose the first OpenMed workflow skill...using deterministic local routing") and when ("Use when a goal is broad, spans several clinical-data stages, or leaves the data-sensitivity status unclear") with concrete trigger phrases; the 'Use when' clause is present.	5 / 5
Trigger Term Quality	Good keyword coverage with natural stage terms (intake, privacy, extraction, exchange, verification) and trigger conditions ("goal is broad, spans several clinical-data stages, or leaves the data-sensitivity status unclear"), though some natural synonyms users might say (de-identification, FHIR, anonymize) are absent.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche (OpenMed first-pass routing) with distinct triggers tied to clinical-data stages and sensitivity status, giving minimal conflict risk with unrelated skills.	5 / 5
	Total	18 / 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
relative_links	Relative link issues: 41 suspicious	Warning

	Total	15 / 16 Passed

Repository: maziyarpanahi/openmed
Path: skills/ask-openmed/SKILL.md
Commit: b161a18

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.