CtrlK
BlogDocsLog inGet started
Tessl Logo

nature-academic-search

Multi-source literature search, citation verification, strict independent other-citation audits, article-level citation metric tables, influential citer profiling with citation-context extraction, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion) via MCP tools (PubMed, CrossRef, arXiv, Scopus, ScienceDirect). Use for coordinated literature workflows beyond one MCP call, including 文献检索、 查文献、找文献、文献综述检索、查论文、引文核对、参考文献管理、文献去重、 严格他引、他引判定、排除自引、谁引用了我的文章、引用我的文章的人有没有大牛、 院士引用、校长引用、院长引用、杰青引用、长江学者引用、Fellow引用、文章引用表、 指定文章引用数、严格他引数、整理成表格.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/nature-academic-search/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

The router is well-structured and concise with a clear sequenced protocol and explicit error-recovery feedback, but its progressive-disclosure design is undermined by missing bundle files: the manifest.yaml and static/core/*.md files it instructs Claude to load first do not exist, so the primary executable step cannot be followed as written.

Suggestions

Add the missing manifest.yaml and static/core/tools.md, static/core/routing-and-ops.md files referenced as always_load in Step 1, or correct the paths to point at files that actually exist — currently the first executable step cannot be followed.

Link the workflow files explicitly (e.g., [references/workflows/wf1-multi-source-search.md]) and clarify how workflow values like multi-source-search map to the wf1–wf6 filenames, since the manifest that is supposed to declare this mapping is absent.

Trim the 'Why this split' rationale section or relocate it to a maintenance note to tighten the router further.

DimensionReasoningScore

Conciseness

A lean router that explicitly defers logic to fragments ('Do not try to apply the search logic from memory or from this router'). Not 5: the 'Why this split' section is minor over-explanation of design rationale that could be trimmed. Not 3: the body is otherwise efficient and assumes Claude's competence.

4 / 5

Actionability

Concrete file paths and a specific 5-step protocol with explicit fallbacks ('fall back to manual generation from MCP-fetched metadata if a script fails twice'), but the primary Step 1 targets (manifest.yaml, static/core/tools.md, static/core/routing-and-ops.md) do not exist in the bundle, leaving the first executable load step un-followable. Not 4 due to this key gap.

3 / 5

Workflow Clarity

Clear 5-step sequenced routing protocol with an explicit detection checkpoint ('State the detected workflow(s) in one short line before proceeding') and error-recovery feedback. Not 5: validation is fallback-oriented rather than output-verification, and there is no checklist.

4 / 5

Progressive Disclosure

Sound router concept with many real, well-signaled one-level references (references/source-tiers.md, references/dedup-engine.md, scripts/academic_search.py), but the central manifest.yaml and the always-load static/core/*.md files referenced in Step 1 are absent from the bundle, breaking navigation. Not 4 due to these missing critical references; not 2 because many references are real and the structure is genuinely a router, not a monolith.

3 / 5

Total

14

/

20

Passed

Description

96%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, specific description that clearly states both capabilities and trigger conditions, with rich natural-language trigger terms in both English and Chinese. The only weakness is moderate overlap risk with closely related sibling skills given the very broad scope.

DimensionReasoningScore

Specificity

Lists 'literature search, citation verification, strict independent other-citation audits, article-level citation metric tables, influential citer profiling with citation-context extraction, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion)' — multiple specific concrete actions with comprehensive coverage. Not below 5: the actions are concrete and the coverage is broad rather than minimal.

5 / 5

Completeness

Explicit 'what' via the full capability list and explicit 'when' via 'Use for coordinated literature workflows beyond one MCP call, including [trigger phrases]' — clearly answers both what and when with concrete triggers.

5 / 5

Trigger Term Quality

Includes natural user phrasings and synonyms (文献检索、查文献、找文献、查论文、谁引用了我的文章) plus file extensions (.nbib/.ris/.bib) and English domain terms. Not 4: both synonyms and file extensions are present, matching comprehensive natural-term coverage.

5 / 5

Distinctiveness Conflict Risk

Clear academic-literature niche with named MCP tools (PubMed, CrossRef, arXiv, Scopus, ScienceDirect), but the broad scope spanning search, citation audit, file management, and reference management risks overlap with sibling nature-* skills such as nature-citation. Not 5 due to that overlap risk.

4 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
Yuan1z0825/nature-skills
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.