table-narrative-writer

Converts biomedical table content into clear manuscript or presentation narrative by prioritizing meaningful patterns, contrasts, and interpretation boundaries rather than restating every number.

Quality

58%

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 ./awesome-med-research-skills/Academic Writing/table-narrative-writer/SKILL.md

Quality

Content

63%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 well-structured with excellent progressive disclosure and a concrete, actionable output template, but it is notably redundant across its overview, execution, and prohibition sections, which hurts token efficiency.

Suggestions

Collapse the Task, Core Function, and Execution lists into a single canonical workflow to remove triple restatement of the same steps.

Merge the overlapping prohibition lists (Scope Boundary 'not for', Hard Rules, and What This Skill Should Not Do) into one consolidated rules section.

Add one short worked example (e.g. a small regression table and the resulting narrative) to lift actionability from concrete guidance to copy-paste-ready modeling.

Dimension	Reasoning	Score
Conciseness	The body restates the same workflow three times (Task, Core Function, Execution) and the same prohibitions across Scope Boundary, Hard Rules, and What This Skill Should Not Do, making it noticeably verbose despite not teaching concepts Claude already knows.	2 / 5
Actionability	A concrete mandatory output structure (sections A–H), seven execution steps, and ten hard rules give highly actionable guidance; the gap is the absence of a worked example of actual narrative output.	4 / 5
Workflow Clarity	A clearly sequenced seven-step workflow with explicit validation checkpoints (input sufficiency check, boundary check) is present, though there is no error-recovery feedback loop as expected at a 5.	4 / 5
Progressive Disclosure	Seven reference files are each signaled one level deep with a 'Use to ...' purpose and all referenced paths resolve to real files, giving a clear overview with easy navigation.	5 / 5
	Total	15 / 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 states a clear purpose in third person and carves a specific niche, but it omits an explicit 'Use when' trigger clause and the natural phrasing users actually say, leaving completeness and trigger quality at mid-level.

Suggestions

Add an explicit 'Use when...' clause with concrete triggers, e.g. 'Use when a user asks to turn a Table 1, regression table, or subgroup table into manuscript or presentation text.'

Surface natural user phrases such as 'narrate this table', 'write the Results paragraph', or 'summarize this table for a deck' to improve trigger-term quality.

List one or two more concrete actions (e.g. 'selects prose-worthy contrasts', 'flags over-interpretation') to lift specificity beyond a single action verb.

Dimension	Reasoning	Score
Specificity	It names the domain ('biomedical table content') and one concrete action ('converts ... into clear manuscript or presentation narrative'), with the remainder describing approach rather than additional actions; not the several concrete actions needed for a 4.	3 / 5
Completeness	The 'what' is clear, but there is no explicit 'Use when...' clause; per the judging guideline a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant domain keywords ('biomedical table', 'manuscript', 'presentation narrative') appear, but common natural user phrases like 'Table 1', 'regression table', or 'summarize this table' are absent.	3 / 5
Distinctiveness Conflict Risk	The biomedical table-to-narrative niche is mostly distinct with only minor overlap risk against general manuscript-writing skills, though the lack of explicit triggers keeps it below a 5.	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: awesome-med-research-skills/Academic Writing/table-narrative-writer/SKILL.md
Commit: f5ef65b

Reviewed: ~9 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.