ib-summarizer

Summarize core safety information from Investigator's Brochures for clinical.

Quality

56%

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/Evidence Insight/ib-summarizer/SKILL.md

Quality

Content

60%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 and actionable with concrete commands, parameters, and output templates, plus a clear workflow with validation. Its main weakness is conciseness: duplicate sections, filler cross-references, and generic boilerplate inflate the token budget without adding IB-specific value.

Suggestions

Remove duplicate install instructions (merge Prerequisites into Installation) and delete the filler 'See ## Usage/Workflow above' lines that add no information.

Cut generic process boilerplate (Implementation Details, Output Requirements, Response Template) down to IB-specific guidance only.

Consolidate the overlapping Quick Check and Audit-Ready Commands sections, which both run the same two py_compile/--help commands.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: duplicate install instructions (Installation and Prerequisites both show 'pip install -r requirements.txt'), filler cross-references ('See ## Usage above for related details', 'See ## Workflow above'), and several generic boilerplate sections (Implementation Details, Output Requirements, Response Template) that restate process truisms rather than IB-specific knowledge.	2 / 5
Actionability	Provides concrete executable commands ('python -m py_compile scripts/main.py', 'python scripts/main.py --help'), a full parameters table, and concrete markdown/JSON output templates; minor gaps are that no inline extraction code is shown (delegated to scripts/main.py).	4 / 5
Workflow Clarity	A clear 5-step Workflow sequence is present with an explicit Quick Check validation checkpoint (py_compile before deeper execution) and an Error Handling fallback path; not a 5 because the validate→fix→retry feedback loop is not strongly emphasized for error recovery.	4 / 5
Progressive Disclosure	Content is well-sectioned with clear headers, and the one-level-deep reference (references/audit-reference.md) and scripts/main.py are properly signaled and real; minor gaps because the output-structure templates and security checklist are largely inlined rather than split out.	4 / 5
	Total	14 / 20 Passed

Description

53%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 clearly states the domain and action but omits any explicit trigger ('Use when...') guidance, which limits completeness and trigger discoverability. It is specific and distinct but not comprehensive in coverage or natural-language triggers.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when summarizing safety data from an Investigator's Brochure (IB) for clinical research, drug safety review, or trial preparation.'

Include common synonyms and file extensions (IB, drug safety, .pdf, .docx) to improve trigger-term coverage.

Specify the concrete safety sections extracted (ADRs, contraindications, warnings) to lift specificity toward a 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Investigator's Brochures', 'core safety information') and one concrete action ('Summarize'), matching the anchor for naming a domain with 1-2 actions but lacking comprehensive coverage.	3 / 5
Completeness	The 'what' is clearly stated ('Summarize core safety information from Investigator's Brochures'), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Relevant domain keywords ('Investigator's Brochures', 'safety information', 'clinical') are present, but common synonyms (IB, drug safety) and file extensions are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Investigator's Brochure safety summarization is a narrow, distinct niche with minimal conflict risk, though it could overlap slightly with other clinical/medical summarizer skills.	4 / 5
	Total	13 / 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/Evidence Insight/ib-summarizer/SKILL.md
Commit: 63c61d3

Reviewed: 10 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.