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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

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-organized, actionable multi-phase workflow with concrete tooling and built-in verification policies. Weakest spot is progressive disclosure: no local bundle exists and several referenced shared-references files are external/inverifiable, while the sizable report template is inlined.

Suggestions

Move the full Novelty Check Report markdown template into a referenced file (e.g. references/report-template.md) and keep only a short pointer inline to reduce body length.

Vendor or include the referenced shared-references/*.md and helper scripts (verify_papers.py, save_trace.sh) under references/ or scripts/ so the bundle is self-contained and the references are verifiable.

Tighten the 'Important Rules' list by merging the duplicated anti-hallucination guidance and dropping rhetorical padding like 'Be BRUTALLY honest' to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The phased structure (A-D) is efficient and does not explain concepts Claude already knows, with only minor padding ('Be BRUTALLY honest', restated anti-hallucination guidance) that could be trimmed; fits 'efficient; minor over-explanation'.	4 / 5
Actionability	Provides a concrete MCP call block (model + reasoning config), a dossier-file pattern with absolute path, and a structured report template, plus named helper scripts; some search steps remain guidance rather than fully executable queries, leaving minor gaps.	4 / 5
Workflow Clarity	Phases A-D are clearly sequenced with validation checkpoints (paper pre-search verification policy with fallback tagging, mandatory review tracing); not a 5 because validation is expressed as policy rather than a strict validate→fix→retry loop embedded in the phase sequence.	4 / 5
Progressive Disclosure	References to shared-references/*.md (citation-discipline, review-tracing, integration-contract) and helper scripts are one level deep and clearly signaled inline with good section structure; no bundle files exist to verify, and the long report template is inlined rather than split out, leaving minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

95%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 strong, well-structured description that crisply states both the capability and explicit bilingual trigger conditions. The only minor gap is capability breadth (a single core action) rather than any ambiguity.

Dimension	Reasoning	Score
Specificity	Names the domain ('research idea novelty') and a concrete action ('verify...against recent literature'), but offers only a single primary action rather than a comprehensive list of capabilities; fits the 'several specific actions, minor gaps' anchor better than the single-action anchor at 3.	4 / 5
Completeness	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.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases in two languages — '查新', 'novelty check', '有没有人做过', 'check novelty' — plus the intent phrasing 'verify a research idea is novel before implementing', covering synonyms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (research novelty verification) with distinctive bilingual triggers unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/novelty-check/SKILL.md
Commit: f4f20f9

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.