aris-novelty-check

Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.

Quality

82%

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

The canonical home for this skill is novelty-check in wanshuiyin/Auto-claude-code-research-in-sleep

Quality

Content

75%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.

A well-structured, actionable research workflow with clear phased sequencing and a concrete report template. The main gaps are minor: a few padded phrases, search steps expressed as instructions rather than literal commands, and no explicit re-search feedback loop after finding overlaps.

Suggestions

Tighten conciseness by trimming filler like "systematically verify its novelty" and condensing the 'Important Rules' bullets into the phases they apply to.

Add a feedback loop to Phase B/C: if Phase C flags a high-overlap paper, re-run targeted searches for that closest-prior-work's lineage before finalizing the report.

Give 1-2 example literal WebSearch query strings per claim type so the search step is copy-paste executable rather than only descriptive.

Dimension	Reasoning	Score
Conciseness	The body is directive and assumes Claude's knowledge (it never explains what arXiv/NeurIPS are), with only minor padding such as "systematically verify its novelty" and the 'Important Rules' list that could be trimmed; efficient but not perfectly lean.	4 / 5
Actionability	Concrete guidance throughout — named sources, "at least 3 different query formulations", year filters 2024-2026, a copy-paste Codex config block, and a full report template — but search steps are instructional rather than literal executable commands, leaving minor gaps.	4 / 5
Workflow Clarity	Phases A-D are clearly sequenced with Phase C acting as a cross-model verification checkpoint; this is an analysis task (not destructive/batch), so the missing validate->fix->retry loop only costs the top level, landing at 'clear sequence with minor validation gaps'.	4 / 5
Progressive Disclosure	A single self-contained SKILL.md with no nested references and clear section headers (Constants, Phases A-D, Important Rules); well-organized but over 50 lines with the report template inlined, so it does not quite reach the 'perfectly split' top anchor.	4 / 5
	Total	16 / 20 Passed

Description

90%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.

A tightly scoped, well-triggered description that cleanly answers both what and when with natural (bilingual) trigger phrases. The only weakness is specificity: it states a single composite action rather than enumerating the discrete capabilities the skill performs.

Dimension	Reasoning	Score
Specificity	"Verify research idea novelty against recent literature" names the domain and one concrete action (verify novelty against literature), but does not enumerate multiple specific actions, so it sits at the '1-2 concrete actions' anchor rather than the 'several specific actions' level above.	3 / 5
Completeness	It explicitly answers both what ("Verify research idea novelty against recent literature") and when ("Use when user says ... or wants to verify a research idea is novel before implementing") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	"查新", "novelty check", "有没有人做过", "check novelty" give comprehensive coverage of natural phrases users would say, including bilingual synonyms and colloquial variants; no file extensions apply to this research-oriented task.	5 / 5
Distinctiveness Conflict Risk	The research-novelty niche with distinctive bilingual trigger phrases ("查新", "有没有人做过") makes it clearly distinguishable from other skills with minimal conflict risk.	5 / 5
	Total	18 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-novelty-check/SKILL.md
Commit: d51b64e

Reviewed: 6 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.