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.
63
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/novelty-check/SKILL.mdQuality
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 well-crafted 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, such as searching specific databases, comparing approaches, or generating summary reports.
Suggestions
Expand the capability description with more concrete actions, e.g., 'Searches recent papers, compares methodologies, and summarizes overlapping work to verify research idea novelty against recent literature.'
| 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 concrete actions like searching databases, comparing methodologies, summarizing related work, 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 the scenario of wanting to verify novelty before implementing). | 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 natural phrasing '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 conflict with general literature review, code review, or other research skills. The Chinese trigger terms and specific 'novelty check' phrasing further reduce conflict risk. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured multi-phase workflow for research novelty checking with clear sequencing and a useful output template. Its main weaknesses are the lack of concrete executable examples (e.g., actual MCP call syntax, example search queries) and references to bundle files that don't exist, undermining the progressive disclosure strategy. The anti-hallucination safeguards are thorough but verbose.
Suggestions
Add a concrete, complete MCP invocation example showing the exact tool call with all parameters, rather than just a config snippet.
Provide 2-3 example search query formulations for a sample research claim to make Phase B more actionable.
Either include the referenced bundle files (verify_papers.py, shared-references/*.md, save_trace.sh) or remove/inline the critical parts of those references so the skill is self-contained.
Condense the anti-hallucination paragraph and review tracing section — move detailed protocols to referenced files and keep only the key rules inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some unnecessary verbosity, such as explaining what novelty means in obvious ways ('Applying X to Y is NOT novel unless...') and the lengthy anti-hallucination paragraph. The constants section and phase structure are efficient, but the overall content could be tightened. | 2 / 3 |
Actionability | The skill provides a clear multi-phase workflow with specific search targets and output format, but lacks executable code examples. The MCP call syntax is shown only as a config snippet, not a complete invocation. Query formulation examples and concrete search strings are missing, making it harder to follow precisely. | 2 / 3 |
Workflow Clarity | The four-phase workflow (Extract Claims → Literature Search → Cross-Model Verification → Report) is clearly sequenced with explicit steps within each phase. The cross-model verification serves as a validation checkpoint, and the anti-hallucination rules with verify_papers.py provide error-checking feedback loops for the citation pipeline. | 3 / 3 |
Progressive Disclosure | The skill references external files (shared-references/integration-contract.md, shared-references/citation-discipline.md, shared-references/review-tracing.md, verify_papers.py, save_trace.sh) which is good progressive disclosure in principle, but no bundle files are provided, making these references unverifiable dead links. The main content is well-sectioned but the anti-hallucination and review tracing sections are dense inline blocks that could benefit from being in separate referenced files. | 2 / 3 |
Total | 9 / 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
a425a71
- 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.