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

72%

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 ./skills/clinical-reports/SKILL.md

Quality

Content

78%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 content is highly actionable with executable commands and a well-structured, progressive-disclosure layout backed by real bundle files. Its main weakness is conciseness, due to repeated boundary warnings and inline time-sensitive version facts.

Suggestions

Consolidate the repeated safety-boundary warnings into the Non-Negotiable Boundary section and reference it once elsewhere instead of restating prohibitions per section.

Add an explicit feedback loop after the deterministic-checks step (e.g. "If a check fails, fix the draft and re-run; do not proceed to handoff until checks pass").

Move dense inline version/date specifics (e.g. adoption dates for ICH E6(R3), E2D(R1)) into references/sources.md and keep only the routing decision inline.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining concepts Claude already knows, but boundary warnings (DRAFT block, "never sign/submit", "do not generate findings") repeat across sections and inline time-sensitive version facts could be tightened.	3 / 5
Actionability	Each script is shown as a complete, copy-paste-ready bash command with concrete flags and output paths (e.g. "--type case-report --output ./case-report-draft.json"), covering the common cases.	5 / 5
Workflow Clarity	The five-step Safe Drafting Workflow is clearly sequenced with an Input Gate checklist and a deterministic-check validation step plus a final handoff, but it lacks an explicit "if check fails, fix and re-run" feedback loop.	4 / 5
Progressive Disclosure	The body is a clear overview with well-signaled, one-level-deep references (each references/.md and assets/.json path is listed and verified to exist), with detail appropriately split into bundle files.	5 / 5
	Total	17 / 20 Passed

Description

66%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, domain-distinctive, and uses third-person voice with good trigger-term coverage, but it lacks an explicit "Use when..." trigger clause, relying on an input guardrail instead. Completeness is the main limiter.

Suggestions

Add an explicit trigger clause such as "Use when drafting clinical case, diagnostic, trial, safety, or aggregate research report structures from verified source facts."

Lead with the when/what pairing so the trigger condition precedes the input guardrail.

Consider adding common user phrasings (e.g. "case report", "CSR", "safety table") as explicit trigger keywords.

Dimension	Reasoning	Score
Specificity	"Create safety-bounded draft structures and run local deterministic checks" names the domain plus two concrete actions and enumerates five report types, with only minor coverage gaps.	4 / 5
Completeness	The "what" is clear, but there is no explicit "Use when..." trigger clause; "Use only with synthetic, de-identified, or aggregate inputs" is a guardrail rather than usage-trigger guidance, so completeness is capped at 3.	3 / 5
Trigger Term Quality	Natural terms like "clinical case", "diagnostic", "trial", "safety", and "aggregate research reports" appear with synonyms, though a few common phrasings users might say are absent.	4 / 5
Distinctiveness Conflict Risk	The clinical-reporting niche with its enumerated report types is mostly distinct with only minor overlap risk against adjacent reporting skills.	4 / 5
	Total	15 / 20 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: 1e5eeff

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.