literature-extensive-read

Rapidly skim and summarize academic papers (default:PDF-to-Markdown full text with `## Page XX` pagination and image references) and output a structured extensive-reading summary in Markdown when you need to quickly understand research questions, methods, key results, conclusions, and decide whether intensive reading is worthwhile.

Quality

64%

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/literature-extensive-read/SKILL.md

Quality

Content

72%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, actionable, and uses progressive disclosure effectively with real one-level-deep bundle references. The main weakness is workflow clarity: validation/quality-check is referenced rather than surfaced as an explicit checkpoint step in a batch-oriented workflow.

Suggestions

Add an explicit validation step to the numbered Steps, e.g. "5. Run the quality check: confirm every template field is filled or marked 'Not specified' before saving" — important because "reviewing many papers" is a batch use case.

Inline a brief filled example of the rapid_summary_template output so the common case is copy-paste ready and actionability reaches 5.

Consolidate the skim-then-summarize workflow (currently restated across When to Use, Key Features, and Implementation Details → Reading strategy) into one authoritative description to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is efficient and well-sectioned with no over-explanation of concepts Claude already knows; only minor redundancy between "When to Use", "Key Features", and the reading-strategy algorithm could be trimmed.	4 / 5
Actionability	It gives a concrete executable command ("pdf-extract paper.pdf > paper.md"), real pointers to bundle files (references/guide.md, assets/rapid_summary_template.md), and concrete output paths; minor gap is the lack of a filled example of the completed template.	4 / 5
Workflow Clarity	The numbered Steps give a clear sequence, but validation/quality-checking is only implicit (referenced via guide.md rather than an explicit checkpoint step), and "reviewing many papers" is a batch use case where the rubric caps clarity at 3 when checkpoints are missing.	3 / 5
Progressive Disclosure	SKILL.md is a concise overview with well-signaled, one-level-deep references to real bundle files (references/guide.md for quality checks, assets/rapid_summary_template.md for structure); content is appropriately split and easy to navigate.	5 / 5
	Total	16 / 20 Passed

Description

57%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 conveys a specific niche and includes a when-clause, but it loses points for second-person voice, missing synonyms/file extensions, and a when-clause that isn't framed as concrete user trigger phrases.

Suggestions

Rewrite in third person to avoid the voice penalty, e.g. "Skims and summarizes academic papers... and outputs a structured extensive-reading summary in Markdown."

Add natural trigger phrases and synonyms: "Use when the user asks to skim, summarize, or triage research papers, articles, literature, or .pdf files."

Reframe the when-clause as a concrete 'Use when...' trigger ("Use when triaging many papers before deciding which to read in depth") so completeness can reach 5.

Dimension	Reasoning	Score
Specificity	Names the domain and 1-2 concrete actions ("Rapidly skim and summarize academic papers", "output a structured extensive-reading summary in Markdown"), but it is not a comprehensive list of distinct actions. The second-person phrasing ("when you need to quickly understand...") triggers the rubric's voice penalty, reducing the score by 1 from a base of 3.	2 / 5
Completeness	It clearly states what the skill does and includes an explicit "when you need to..." clause, but the when is phrased as an internal need rather than concrete user-facing trigger phrases ("Use when the user asks to...").	4 / 5
Trigger Term Quality	Relevant keywords appear ("academic papers", "summarize", "research questions, methods, key results, conclusions") but common variations/synonyms users say ("research paper", "article", "literature") and the .pdf extension are missing.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (academic-paper extensive reading / literature triage with intensive-reading judgment), with only minor overlap risk against general document-summarization skills.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/literature-extensive-read/SKILL.md
Commit: 63c61d3

Reviewed: 12 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.