clinical-reports

Create safety-bounded draft structures and run local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate research reports. Use only with synthetic, de-identified, or aggregate inputs and verified source-fact manifests; every output requires qualified review.

Quality

92%

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

85%

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

A well-structured, actionable body with executable commands, an explicit validated workflow, and clean one-level progressive disclosure. The only drag on conciseness is inline dated version pins that duplicate the dated sources ledger.

Suggestions

Move dated adoption/version pins (e.g. 'ICH E6(R3) ... 16 June 2026', 'E2D(R1) ... 15 September 2025') into references/sources.md and keep the body version-agnostic, leaving 'check the live official source' as the dated pointer.

The 'sources.md — checked 2026-07-23' date in the References list is time-sensitive; consider framing it as 'last reviewed' in the ledger rather than a hard date inline.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence, but inline dated version pins ('ICH E6(R3) ... adopted on 16 June 2026', 'E2D(R1), adopted 15 September 2025', 'sources.md — checked 2026-07-23') add time-sensitive detail that could live in the dated sources ledger rather than the body.	2 / 3
Actionability	Provides fully executable, copy-paste bash commands for every script (generate_report_template.py, validate_case_report.py, format_adverse_events.py, terminology_validator.py, etc.) with concrete flags and output paths.	3 / 3
Workflow Clarity	A clearly sequenced 5-step Safe Drafting Workflow (manifest → template → populate → deterministic checks → review) with an explicit validation checkpoint before review and a fail-closed generator, plus a boundary/stop rule for unsafe requests.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview that signals one-level-deep references to real files (references/.md, scripts/.py, assets/*.json), with explicit Assets and References sections listing verified paths for easy navigation.	3 / 3
	Total	11 / 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.

A precise, third-person description that states concrete capabilities, explicit use-when triggers, and strong input/review guardrails. It clearly answers what and when and is well differentiated from other skills.

Dimension	Reasoning	Score
Specificity	Lists concrete actions across multiple report types — 'Create safety-bounded draft structures', 'run local deterministic checks', for 'clinical case, diagnostic, trial, safety, and aggregate research reports'.	3 / 3
Completeness	Explicitly answers both what ('Create safety-bounded draft structures and run local deterministic checks') and when ('Use only with synthetic, de-identified, or aggregate inputs and verified source-fact manifests; every output requires qualified review').	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'clinical case', 'diagnostic', 'trial', 'safety', 'aggregate research reports' — with good variation across report categories.	3 / 3
Distinctiveness Conflict Risk	Highly niche triggers tied to clinical/safety reporting with explicit input and review constraints make it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/clinical-reports/SKILL.md
Commit: 757b63b

Reviewed: about 11 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.