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.
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with excellent trigger term coverage (including bilingual terms), a clear 'Use when' clause, and a distinctive niche. Its main weakness is that the 'what' portion could be more specific about the concrete actions involved in the novelty verification process (e.g., searching databases, comparing approaches, summarizing findings).
Suggestions
Expand the capability description to list more concrete actions, e.g., 'Searches recent literature, compares methodologies, identifies overlapping work, and summarizes novelty gaps for research ideas.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (research novelty verification) and one core action (verify research idea novelty against recent literature), but doesn't list multiple specific concrete actions like searching databases, comparing methodologies, summarizing overlapping papers, or generating novelty reports. | 2 / 3 |
Completeness | Clearly answers both 'what' (verify research idea novelty against recent literature) and 'when' (explicit 'Use when' clause with specific trigger phrases and a conceptual trigger scenario). The when clause is explicit and well-defined. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including both Chinese ('查新', '有没有人做过') and English ('novelty check', 'check novelty') variations, plus the conceptual trigger 'verify a research idea is novel before implementing'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — research novelty checking is a very specific task unlikely to overlap with general literature review, citation management, or other research skills. The Chinese trigger terms further narrow the scope and reduce conflict risk. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill that provides clear multi-phase workflow for novelty checking with specific tools, venues, and output formats. Its main strengths are the concrete tool usage instructions, the cross-model verification step, and the detailed output template. Minor weaknesses include some slightly unnecessary explanatory text and the monolithic structure that could benefit from externalizing the report template.
Suggestions
Consider externalizing the output report template to a separate TEMPLATE.md file to reduce the main skill's token footprint
Remove the explanation of what REVIEWER_MODEL values are valid OpenAI models — Claude knows this already
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary elaboration. The 'Important Rules' section contains some advice Claude would naturally follow (like being honest), and the constants section explaining what OpenAI models are is slightly redundant. However, the overall structure is reasonably tight for the complexity of the task. | 2 / 3 |
Actionability | Provides highly concrete, step-by-step guidance with specific tool names (WebSearch, WebFetch, mcp__codex__codex), exact config parameters, specific query strategies (3 formulations per claim, year filters), specific venues to check, and a complete output template with markdown table format. The instructions are directly executable. | 3 / 3 |
Workflow Clarity | The four-phase workflow (Extract → Search → Verify → Report) is clearly sequenced with explicit dependencies between phases (Phase C uses Phase B results). The cross-model verification in Phase C serves as a validation checkpoint. For each phase, the steps are numbered and specific. The workflow is well-structured for a multi-step research process. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and phases, but everything is in a single file. The output report template is quite long and could potentially be referenced separately. For a skill of this length (~80 lines of meaningful content), the inline approach is borderline acceptable but the report template adds bulk that could be externalized. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
dc00dfb
- Reviewed
Table of Contents
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.