paper-analyzer

Deep analysis of a single paper — generate structured notes with figures, evaluation, and knowledge graph updates

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/paper-analyzer/SKILL.md

Quality

Content

61%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 concise and well-organized with concrete commands and real script references, but the workflow uses unresolved placeholders/variables and lacks validation checkpoints for the batch knowledge-graph write. Defining the variables and adding verification steps would raise actionability and workflow_clarity.

Suggestions

Define the placeholder variables before use — show how PAPER_ID, TITLE, AUTHORS, DOMAIN, and SCORE are obtained (e.g. from the arXiv HTML page) so the curl/python blocks are copy-paste ready.

Add validation checkpoints: verify the PDF downloaded (file size / HTTP status), confirm parsing before generate_note.py, and validate the note before update_graph.py runs.

Make the script references more explicit, e.g. 'See scripts/generate_note.py' as signaled links, to push progressive_disclosure toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean — short headers, curl/python commands, and no over-explanation of concepts Claude already knows — with only minor prose (the Note Structure sentence) that could be trimmed, fitting the 'efficient; minor over-explanation' anchor.	4 / 5
Actionability	Concrete curl and python commands are given, but they use unresolved placeholders ([PAPER_ID]) and unset variables ($TITLE, $AUTHORS, $DOMAIN, $SCORE) with no setup, so the guidance is incomplete rather than copy-paste ready, matching the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	Five clearly sequenced steps with real commands are present, but there are no validation checkpoints (e.g. verify the PDF downloaded, confirm parsing succeeded) before batch graph writes, so the rubric's missing-validation cap holds this at 3.	3 / 5
Progressive Disclosure	A compact overview with a dedicated # Scripts section pointing to real bundle files (generate_note.py, update_graph.py) is well-structured and one level deep, matching the 'good structure; references mostly clear' anchor rather than the fully-signaled 5.	4 / 5
	Total	14 / 20 Passed

Description

58%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 conveys a clear, fairly specific purpose with several concrete deliverables but lacks any 'when to use' trigger guidance. Adding an explicit 'Use when...' clause with natural user phrases would lift completeness and trigger_term_quality.

Suggestions

Append a 'Use when...' clause, e.g. 'Use when the user wants a deep read of a specific arXiv paper, asks to summarize or evaluate a paper, or needs structured notes from a PDF.'

Add natural trigger terms users actually say — 'read this paper', 'summarize the paper', 'arXiv', 'PDF' — to improve trigger_term_quality.

Tighten the deliverable list into the most concrete verbs (extract, evaluate, score, link) to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Deep analysis of a single paper') and lists several concrete outputs — 'generate structured notes with figures, evaluation, and knowledge graph updates' — with only minor coverage gaps, matching the 'several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	The description gives a clear 'what' but contains no 'Use when...' trigger clause, so per the rubric cap completeness cannot exceed 3 even though the what-side is strong.	3 / 5
Trigger Term Quality	Includes 'paper' and 'analysis' but misses the natural phrases users say ('read this paper', 'summarize a paper', 'arXiv', '.pdf') and common synonyms, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The single-paper deep-analysis niche with knowledge-graph updates is mostly distinct from generic skills with only minor overlap risk against broader research tools, matching the 'mostly distinct' anchor rather than the fully distinct 5.	4 / 5
	Total	14 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/paper-analyzer/SKILL.md
Commit: 4b35756

Reviewed: 1 day 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.