medication-reconciliation

Compare patient pre-admission medication lists with inpatient orders to automatically identify omitted or duplicated medications and improve medication safety.

Quality

70%

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/medication-reconciliation/SKILL.md

Quality

Content

75%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 executable commands and concrete examples, and the workflow is clearly sequenced with validation checkpoints. Main weakness is noticeable internal duplication across Workflow, Error Handling, Stress-Case Rules, and Response Template sections that could be consolidated.

Suggestions

De-duplicate the "state exactly which fields are missing" guidance and the dose-change warning, keeping each in one canonical location and cross-referencing from the other.

Consolidate the overlapping Stress-Case Rules and Response Template sections into a single response-structure block to tighten conciseness.

Add an explicit one-level-deep pointer such as "See scripts/main.py for matching logic and edge-case handling" to strengthen progressive disclosure signaling.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with no basic-concept padding, but noticeable duplication — "state exactly which fields are missing" appears in both Workflow step 8 and Error Handling, the dose-change warning is repeated, and Stress-Case Rules overlaps the Response Template — pushes it to the "could be tightened" anchor rather than the minor-trims anchor.	3 / 5
Actionability	Copy-paste-ready commands ("python scripts/main.py --pre-admission pre_meds.json --inpatient orders.json --output report.json", "--example", "--verbose"), a full parameters table, and concrete JSON output/dose-change examples cover the common cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The 8-step workflow has explicit checkpoints (PHI check step 1, input validation step 3, physician-verification on dose change step 6) plus an Error Handling fallback, matching the clear-sequence-with-most-checkpoints anchor; not a 5 because error recovery is a manual fallback rather than a tight validate→fix→retry loop.	4 / 5
Progressive Disclosure	The single bundle file scripts/main.py holds the implementation while SKILL.md serves as a well-sectioned one-level-deep overview (verified scripts/main.py exists), matching the good-structure anchor; not a 5 because the reference to the script is implicit in usage examples rather than a clearly signaled "See scripts/main.py" pointer, and Stress-Case Rules/Response Template are somewhat heavy for an overview.	4 / 5
	Total	16 / 20 Passed

Description

65%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 concrete, distinctive clinical purpose but omits any explicit "Use when..." trigger guidance, capping completeness at 3. It is written in correct third-person voice with no over-claims.

Suggestions

Append a "Use when..." clause naming concrete triggers, e.g. "Use when reconciling pre-admission and inpatient medication lists for admission, transfer, or discharge."

Add the natural synonym "medication reconciliation" and terms like "admission meds" / "discharge reconciliation" to broaden trigger coverage.

Replace the abstract tail "and improve medication safety" with another concrete capability (e.g. generating structured reconciliation reports) to lift specificity.

Dimension	Reasoning	Score
Specificity	Quotes "Compare patient pre-admission medication lists with inpatient orders" and "automatically identify omitted or duplicated medications" name the domain with two concrete actions (compare, identify omissions/duplicates), but "improve medication safety" is abstract padding and report generation is absent, matching the 1-2-concrete-actions anchor rather than the several-actions anchor.	3 / 5
Completeness	The description gives a clear "what" but no explicit "Use when..." trigger clause, so per the missing-trigger cap it cannot exceed 3 — matching the anchor "Has a clear 'what' but 'when' is missing or only weakly implied."	3 / 5
Trigger Term Quality	Terms "pre-admission medication lists", "inpatient orders", and "omitted or duplicated medications" are natural clinical phrases a user would say, giving good keyword coverage; not a 5 because synonyms ("med rec", "reconciliation") and common variations are missing.	4 / 5
Distinctiveness Conflict Risk	The narrow clinical niche of comparing pre-admission meds against inpatient orders to flag omissions/duplicates has distinct triggers and minimal overlap with other skills, matching the clear-niche anchor.	5 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/medication-reconciliation/SKILL.md
Commit: f5ef65b

Reviewed: ~18 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.