clinical-reports

Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory complianc...

Quality

62%

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/clinical-reports/SKILL.md

Quality

Content

42%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 well-structured with clear workflows, real bundle files, and a final checklist, but it is markedly verbose — inlining reference material that duplicates the bundle files — and its mandatory schematic step references a non-existent script. Workflows also lack embedded validation feedback loops.

Suggestions

Move the inlined reference material (full report structures, the 18 HIPAA identifiers, the ICH-E3 section list) into the corresponding references/ files and replace it with brief summaries plus "see references/..." links — those bundle files already exist and duplicate this content.

Fix the mandatory schematic step: scripts/generate_schematic.py is referenced but not present in scripts/ — either add the script or change the instruction to invoke the external scientific-schematics skill directly.

Add explicit validate→fix→retry checkpoints inside each workflow (e.g., run scripts/validate_case_report.py and only proceed on pass) instead of relying on a single end-of-document checklist.

Dimension	Reasoning	Score
Conciseness	The ~1150-line body inlines full report structures, the enumerated 18 HIPAA identifiers, and the complete ICH-E3 section list — material that duplicates the provided references/ files — making it noticeably verbose with several padded sections.	2 / 5
Actionability	Real validation scripts and templates provide concrete guidance, but the MANDATORY schematic step instructs `python scripts/generate_schematic.py` for a script that does not exist in scripts/, a broken key command that leaves the guidance incomplete.	3 / 5
Workflow Clarity	Case/diagnostic/trial workflows are clearly sequenced into phases, but validation is end-loaded into a single final checklist with no embedded validate→fix→retry feedback loops, leaving checkpoints implicit.	3 / 5
Progressive Disclosure	References and assets are well-signaled and one level deep with a clear Resources section, but large amounts of content that belong in the existing reference files are inlined in SKILL.md, and one referenced script path (generate_schematic.py) is absent.	3 / 5
	Total	11 / 20 Passed

Description

82%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 is specific and rich with natural clinical-reporting keywords and named standards, giving it strong specificity, trigger-term quality, and distinctiveness. Its weakness is the missing "Use when…" trigger clause, which caps completeness at 3.

Suggestions

Add an explicit "Use when…" trigger clause to the description (e.g., "Use when writing clinical case reports, diagnostic reports, clinical trial reports, or patient documentation") so trigger guidance surfaces at the description level and lifts completeness above 3.

Restore the truncated tail — the description cuts off mid-word at "regulatory complianc..."; complete the sentence so the full capability set is stated.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete report types with named standards — "case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries)" — matching the anchor for comprehensive coverage of specific actions.	5 / 5
Completeness	It clearly states the "what" but contains no "Use when…" clause or equivalent trigger guidance (that lives in the body, not the description), so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	It packs in natural clinical-documentation terms and their synonyms/abbreviations a user would actually say (case reports, radiology, pathology, SAE, CSR, SOAP, H&P, discharge summaries), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	The clinical-reporting niche anchored to specific regulatory standards (CARE, ICH-E3, HIPAA) is distinct with minimal overlap risk against other skills.	5 / 5
	Total	18 / 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
skill_md_line_count	SKILL.md is long (1157 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

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

Reviewed: ~14 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.