CtrlK
BlogDocsLog inGet started
Tessl Logo

nature-downloader

Use when a user needs lawful academic full text, CNKI institutional access, English OA retrieval, publisher API access, institutional browser fallback, or supporting information downloads.

63

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

77%

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

The body is highly actionable with clear sequenced workflows, validation checkpoints, and feedback loops, but it is verbose with repeated guidance and keeps detailed reference material inline rather than splitting it into separate progressive-disclosure files.

Suggestions

Consolidate the repeated SI-gate, API-fallback, and no-credentials-in-chat rules into single canonical sections and reference them instead of restating.

Move the status-code catalog, TSV headers, and triage/domain classification tables into a separate reference file (e.g. references/status_codes.md) linked from the overview.

Fix or remove the dangling src/wizard.py reference, since no src/ directory exists in the bundle.

DimensionReasoningScore

Conciseness

The ~615-line body avoids explaining basic concepts Claude knows, but restates the same rules repeatedly (SI gate, API-fallback, no-credentials-in-chat appear in several sections) and could be tightened substantially, so it is mostly efficient but not lean.

2 / 3

Actionability

It provides copy-paste-ready commands with real flags (e.g. 'node scripts/batch_download.mjs --dois ... --no-si --out', 'python3 scripts/configure_credentials.py set elsevier --stdin'), concrete status codes, and exact TSV headers, giving fully executable guidance.

3 / 3

Workflow Clarity

Routing is shown as a decision tree, Preconditions are a numbered checklist, the WoS route is a sequenced 10-step list, and failure handling has explicit feedback loops (auto-verify -> fail -> user handoff -> retry once -> do_not_auto_retry) with verification checkpoints (%PDF, manifest, extract_pdf_text.py).

3 / 3

Progressive Disclosure

Bundle scripts are referenced by real one-level paths and the body is well-sectioned, but all reference material (status-code catalog, triage tables, TSV formats, domain lists) is inline in one monolithic SKILL.md with no separate reference docs, and src/wizard.py is referenced but absent.

2 / 3

Total

10

/

12

Passed

Description

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description has an explicit trigger clause and a clear, distinctive niche, but its capability phrasing leans on access-route nouns rather than concrete actions and includes some technical jargon over natural user terms.

Suggestions

Lead with concrete verbs ('Download academic full text and supporting information via CNKI, publisher APIs, open access, or institutional browser access') before the 'Use when' clause.

Replace jargon like 'institutional browser fallback' and 'OA retrieval' with user-natural phrasing such as 'institutional library login' and 'open-access copies'.

Ensure the 'what' is stated as an action, not only implied by the list of access scenarios.

DimensionReasoningScore

Specificity

It names the domain and routes ('CNKI institutional access', 'English OA retrieval', 'publisher API access', 'supporting information downloads') but the concrete verb-actions are limited to 'downloads'/'access'; it is largely a list of access paths rather than comprehensive specific actions, so it is not a 3.

2 / 3

Completeness

An explicit 'Use when a user needs ...' clause answers when, and the enumerated routes convey what the skill does (obtain academic full text / SI), matching the both-what-and-when anchor with explicit triggers.

3 / 3

Trigger Term Quality

Natural terms like 'full text', 'CNKI', and 'supporting information' appear, but 'OA retrieval', 'publisher API access', and 'institutional browser fallback' are technical phrasings a user would rarely say, so coverage is partial rather than strong.

2 / 3

Distinctiveness Conflict Risk

The niche is narrow and specific (academic literature via CNKI, publisher APIs, OA, institutional browser access), with triggers unlikely to fire for unrelated skills.

3 / 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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (624 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 2 deeper-than-1-level

Warning

Total

13

/

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.