paper-analyzer

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

Quality

66%

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

72%

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

The skill is concise and well-structured with executable commands for fetching and script invocation, and its bundle references are real and one level deep. Its weaknesses are the vague central analysis step and the complete absence of validation/verification checkpoints across the workflow. Adding concrete analysis guidance and failure-handling loops would raise both actionability and workflow clarity.

Suggestions

Make Step 3 actionable: specify concrete analysis steps or a checklist (e.g. extract claims, map methodology to figures, score evidence) rather than a bare topic list.

Add validation checkpoints — verify the curl download succeeded and the generated note file exists before proceeding to the graph update.

Add an error-recovery loop for the knowledge-graph update (confirm the graph was modified, retry or abort on failure), since it mutates persistent state.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it does not explain what a PDF or library is, and uses compact code blocks for the mechanical steps, matching the lean/efficient anchor.	3 / 3
Actionability	Fetching (curl) and note/graph generation (python scripts) are concrete and executable, but the core Step 3 "Analyze: abstract, methodology, experiments..." is a vague comma list that describes rather than instructs how to perform the analysis — missing key details.	2 / 3
Workflow Clarity	Five steps are clearly sequenced, but there are no validation checkpoints (e.g. confirm the PDF downloaded, verify note output) and the knowledge-graph update is a persistent/batch mutation with no feedback loop — per the guidelines this caps workflow clarity at 2.	2 / 3
Progressive Disclosure	SKILL.md is an overview with well-signaled, one-level-deep references to real bundle scripts ("scripts/generate_note.py", "scripts/update_graph.py", both confirmed present); sections are organized and navigation is easy, matching the clear-overview anchor.	3 / 3
	Total	10 / 12 Passed

Description

60%

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 is specific about capabilities and outputs but omits any explicit "Use when..." trigger guidance, leaving the activation conditions implied. Trigger-term coverage is partial, missing the natural terms (arXiv, PDF, research paper) a user would actually say. Adding an explicit trigger clause would lift both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to analyze, summarize, or take notes on a paper (arXiv ID, PDF, or title)."

Add natural trigger terms users actually say — "arXiv", "PDF", "research paper", "literature", "summarize this paper" — alongside "paper".

Tie the knowledge-graph update to a concrete trigger so the skill is distinguishable from plain summarization skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "generate structured notes with figures, evaluation, and knowledge graph updates" — naming the domain (single paper) plus several distinct outputs, matching the multiple-specific-actions anchor.	3 / 3
Completeness	It clearly states what the skill does, but there is no "Use when..." clause or equivalent trigger, so the "when" is absent — per the guidelines this caps completeness at 2.	2 / 3
Trigger Term Quality	"paper" and "structured notes" are natural terms, but common variations a user would actually say ("arXiv", "PDF", "research paper", "literature review", "summarize") are missing, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The "single paper" + "knowledge graph updates" niche is somewhat specific, yet without explicit triggers it could still overlap with general note/summarization skills.	2 / 3
	Total	9 / 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
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: 6da7f7c

Reviewed: about 7 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.