nature-shared

Internal shared-reference support package for installed Nature Skills, including nature-writing, nature-polishing, nature-response, nature-reader, and nature-paper2ppt. Do not invoke it as a standalone user workflow. Load only the specific core or journal-format file requested by another Nature skill.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/nature-shared/SKILL.md

Quality

Content

67%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 body is a concise, actionable routing guide that clearly maps each reference file to its use scope and ends with a QA return step. Its major weakness is progressive disclosure: the package's entire purpose is to supply referenced core/ and journal-formats/ files, but those files are absent from the bundle, leaving all references dangling.

Suggestions

Add the missing core/ and journal-formats/ reference files (or correct the paths) so every referenced file resolves in the bundle.

Reference scripts/check_consistency.py from the body since it is the one bundle file actually present, or remove it if it does not belong to this package.

Collapse the repeated 'do not present it as official journal policy' caveat into a single shared note to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude knows what Nature journals and journal formats are, and maps each file to its scope without padding; the only trim opportunity is the repeated 'do not present it as official journal policy' caveat which appears four times.	4 / 5
Actionability	It gives concrete file-to-scope directives (e.g., 'Use journal-formats/nature.md only for the flagship journal Nature', 'Use core/research-compliance.md only when its specialist applicability gate is triggered'), which are specific and actionable for an instruction-only skill, with only minor gaps.	4 / 5
Workflow Clarity	The dispatch flow is clear (load the exact referenced file, apply it within its defined scope, return to the requesting skill for task logic and final QA), and the QA return acts as a checkpoint; no destructive/batch validation cap applies.	4 / 5
Progressive Disclosure	The overview is well-structured with clearly signaled one-level-deep references, but the actual bundle is broken: none of the seven referenced files (core/.md, journal-formats/.md) exist, and the one present bundle file (scripts/check_consistency.py) is never referenced, so in practice navigation is impossible.	2 / 5
	Total	14 / 20 Passed

Description

62%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.

The description clearly identifies the package as an internal Nature-skills dependency and gives explicit standalone-inversion guardrails, scoring well on completeness and distinctiveness. It is weaker on trigger-term quality and specificity because the action set is essentially 'load referenced files' and the keywords are internal skill names rather than natural user phrases.

Suggestions

Lead with a sharper capability verb (e.g., 'Provides shared core and journal-format reference definitions for...') to lift specificity beyond a single load action.

Add at least one natural user/trigger-adjacent phrase so the skill is discoverable beyond internal skill names.

Dimension	Reasoning	Score
Specificity	Names the domain ('shared-reference support package for installed Nature Skills') and lists the five supported skills plus the load-file action, but the actionable verb set is thin (mainly 'load only the specific core or journal-format file'), so coverage is not comprehensive.	3 / 5
Completeness	It clearly states what the package does and gives explicit 'when' guidance ('Do not invoke it as a standalone user workflow. Load only the specific core or journal-format file requested by another Nature skill.'), though the trigger is dependency-based rather than a concrete user trigger phrase.	4 / 5
Trigger Term Quality	It includes relevant domain keywords (the five named Nature skills, 'core or journal-format file'), but these are skill-internal technical names rather than natural phrases a user would say, and there is no user-facing trigger wording since it is explicitly not for standalone invocation.	3 / 5
Distinctiveness Conflict Risk	The 'Internal shared-reference support package' framing plus 'Do not invoke it as a standalone user workflow' carves a clear niche with minimal conflict risk, with only minor overlap potential against the individual Nature skills it supports.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Yuan1z0825/nature-skills
Path: skills/nature-shared/SKILL.md
Commit: 3817cd1

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

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.