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.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-conceived two-layer router with a clear routing protocol and on-demand reference discipline, but its core entry-point files (manifest.yaml and the entire static/core layer) are missing from the bundle, so the defined workflow cannot actually be executed as written. The workflow and reference fragments that do exist are well organized.

Suggestions

Add the missing manifest.yaml and static/core/tools.md + static/core/routing-and-ops.md files (or correct the paths), since step 1 of the routing protocol and the 'always_load' core depend on them.

De-duplicate the file listings across steps 1, 4 and 5 — name each file once and reference it, rather than re-enumerating the same paths repeatedly.

Consider trimming the 'Why this split' section; the static/dynamic rationale is largely inferable and adds tokens without adding actionable guidance.

DimensionReasoningScore

Conciseness

The router is mostly lean, but the same file paths are re-listed across steps 1, 4 and 5, and the 'Why this split' section explains rationale Claude could infer — efficient yet could be tightened, not the every-token-earns-its-place level.

2 / 3

Actionability

Gives concrete navigation ('Read [manifest.yaml](manifest.yaml)', explicit workflow/reference paths) for parts that exist, but the central instruction to read manifest.yaml and the static/core files points to files that are missing from the bundle, leaving key execution details broken.

2 / 3

Workflow Clarity

The five-step routing protocol is clearly sequenced with error-recovery guidance ('Report specific tool failures and continue...', 'fall back to manual generation ... if a script fails twice'), but step 1 references nonexistent manifest.yaml and static/core files, breaking the chain at the entry point rather than reaching the explicit-checkpoint level.

2 / 3

Progressive Disclosure

Structure is good where it exists — one-level-deep workflow files under references/workflows/, shared modules, and scripts are all clearly signaled and present — but the 'always_load' core layer (manifest.yaml, static/core/tools.md, static/core/routing-and-ops.md) referenced by the router is absent from the bundle, a real structural defect against the actual file listing.

2 / 3

Total

8

/

12

Passed

Description

92%

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 dense, capability-rich description that clearly states both what the skill does and when to use it, with extensive natural-language triggers (including many Chinese phrases). Its main weakness is overlap with sibling nature-* skills (notably nature-citation) and some keyword stuffing in the trigger list.

Suggestions

Trim the near-duplicate Chinese trigger permutations (e.g. the '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' set) to the most natural few, since redundancy reads as keyword stuffing.

Sharpen distinctiveness from the nature-citation sibling by foregrounding the multi-source orchestration / strict-other-citation-impact-audit scope that is unique to this skill.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'citation verification', 'article-level citation metric tables', 'influential citer profiling with citation-context extraction', 'citation file management (.nbib/.ris/.bib conversion)' — matching the multiple-specific-actions anchor, not the partial-coverage anchor below.

3 / 3

Completeness

Answers both 'what' (the long capability list) and 'when' via the explicit 'Use for coordinated literature workflows beyond one MCP call, including ...' trigger clause, matching the explicit-what-and-when anchor.

3 / 3

Trigger Term Quality

Covers natural terms users would say in both English ('literature search', 'MeSH search strategy') and a large set of natural Chinese phrases ('文献检索', '查论文', '谁引用了我的文章'), giving good coverage; the many near-duplicate permutations ('院士引用','校长引用','杰青引用') lean toward keyword stuffing but still meet the natural-term coverage bar.

3 / 3

Distinctiveness Conflict Risk

The niche (academic literature search via PubMed/CrossRef/arXiv/Scopus/ScienceDirect) is fairly specific, but the bundled reference management, BibTeX, and ID-conversion scope overlaps materially with the sibling 'nature-citation' skill referenced in the body, so it is 'somewhat specific but could overlap' rather than clearly conflict-free.

2 / 3

Total

11

/

12

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.