discharge-summary-writer

Generate hospital discharge summaries from admission data, hospital course, diagnoses, procedures, and follow-up plans; use when a structured discharge document is required from clinical notes.

Quality

86%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is genuinely actionable with real commands and well-organized references, but it is inflated with generic template boilerplate that is unrelated to — and sometimes contradictory with — the medical discharge-summary purpose. The workflow is present but generic rather than task-specific.

Suggestions

Remove or rewrite the off-domain boilerplate: the "When to Use" academic-writing bullet and the Required Inputs table referencing research questions, PMIDs, PDFs, and CSVs do not fit a hospital discharge-summary skill.

Replace the generic 5-step Workflow with a discharge-specific sequence (ingest patient JSON → map sections per template → render via scripts/main.py → verify required sections present), with explicit validation checkpoints.

Tighten the body by collapsing the many overlapping meta-sections (Output Requirements, Output Contract, Response Template, Failure Handling, Error Handling) into one concise guidance block to reduce token load.

Dimension	Reasoning	Score
Conciseness	Useful efficient content exists (parameters table, input JSON, executable commands), but the body is padded with large generic boilerplate sections irrelevant to the medical domain — e.g. "Use this skill for academic writing tasks" and a Required Inputs table listing "Research question... PMID, PDF, CSV, DOCX, keywords".	2 / 3
Actionability	Concrete executable commands ("python scripts/main.py --input patient_data.json --output discharge_summary.md --format standard", "python -m py_compile scripts/main.py"), a real bundled script, a parameters table, and a full input JSON schema give copy-paste-ready guidance.	3 / 3
Workflow Clarity	A 5-step Workflow and a Quick Check are present, but the steps are generic template language ("Confirm the user objective", "Validate that the request matches the documented scope") rather than a task-specific sequence, and validation checkpoints for the actual generation are only implicit.	2 / 3
Progressive Disclosure	References are clearly signaled and one level deep ("references/discharge_template.md", "references/medical_terms.json", "references/section_guidelines.md"), and all three are real bundle files, giving clean navigation.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 is specific, uses third person, names concrete actions and inputs, and includes an explicit "use when" trigger tied to natural clinical terms. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	"Generate hospital discharge summaries from admission data, hospital course, diagnoses, procedures, and follow-up plans" lists multiple specific concrete actions and inputs, matching the top anchor.	3 / 3
Completeness	It states both what ("Generate hospital discharge summaries...") and when ("use when a structured discharge document is required from clinical notes") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Natural clinical terms a user would say appear — "hospital discharge summaries", "clinical notes", "structured discharge document", "admission data" — giving good coverage rather than jargon.	3 / 3
Distinctiveness Conflict Risk	The hospital-discharge niche with clinical-note triggers is clearly distinct and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
Commit: 7cc5680

Reviewed: 3 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.