lay-summary-gen

Converts complex medical abstracts into plain language summaries for.

Quality

42%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/lay-summary-gen/SKILL.md

Quality

Content

35%

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

The body pairs a genuinely executable script with a concrete I/O contract, but is weighed down by large amounts of generic template boilerplate, a stale review date, inaccurate documented commands, and mislabeled cross-references. Useful core content is buried under padding and weak navigation.

Suggestions

Remove generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) and delete or update the past "Next Review Date" to reduce padding.

Correct the usage docs: main.py takes an abstract as argv[1] with no --help/demo/CONFIG support, so drop or fix those commands and show a real invocation like `python scripts/main.py "<abstract text>"`.

Fix the mislabeled cross-references ("See ## Features/Prerequisites/Workflow above" — these sections are below) and move the boilerplate process guidance into references/ so the SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The ~190-line body is padded with generic template boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) that Claude already knows, and includes a time-sensitive "Next Review Date: 2026-03-06" that is now in the past.	1 / 3
Actionability	A complete executable script and concrete I/O contract (Input Parameters table, Output Format JSON) are provided, but documented commands are inaccurate: main.py has no --help handling, no "demo" subcommand, and no CONFIG block referenced in the run plan.	2 / 3
Workflow Clarity	A sequenced Workflow with a scope-validation step, a Quick Check (py_compile), and an error fallback exists, but validation is shallow (syntax-only) and the core generate step lacks an output-quality checkpoint; multiple overlapping workflow sections also muddle the path.	2 / 3
Progressive Disclosure	The bundle uses real one-level-deep references (references/guidelines.md, scripts/main.py), but internal navigation is broken ("See ## Features above" points to a section below) and content that could be split out is inline.	2 / 3
	Total	7 / 12 Passed

Description

50%

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 conveys a clear domain and single concrete action but is truncated (dangling "for.") and lacks any explicit "Use when..." trigger guidance, leaving every dimension at the mid-level. It is distinguishable but not strongly triggered.

Suggestions

Fix the truncated sentence and complete the "what", e.g. "Converts complex medical abstracts into plain-language lay summaries for patients and the public."

Add an explicit "Use when..." clause naming natural triggers such as "lay summary", "plain English summary", "simplify medical jargon", or "EU CTR lay summary".

List more concrete actions (e.g. jargon replacement, reading-level targeting, key-takeaway extraction) to lift specificity.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and one action ("Converts complex medical abstracts into plain language summaries"), but only lists a single action rather than multiple specific concrete actions.	2 / 3
Completeness	States the "what" (converts abstracts to plain summaries) but has no "Use when..." clause or equivalent trigger guidance, which caps completeness at 2; the trailing "for." also leaves the what partially truncated.	2 / 3
Trigger Term Quality	Contains some relevant keywords ("medical abstracts", "plain language summaries") but misses common natural variations a user would say like "lay summary", "plain English", or "simplify medical jargon".	2 / 3
Distinctiveness Conflict Risk	The medical lay-summary niche is somewhat specific, but without explicit triggers it could still overlap with general summarization or plain-language skills.	2 / 3
	Total	8 / 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.