CtrlK
BlogDocsLog inGet started
Tessl Logo

huggingface-paper-publisher

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

57

Quality

66%

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/huggingface-paper-publisher/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

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 concrete executable commands, but it is verbose and repetitive, lacks validation checkpoints in its batch and repository-modifying workflows, and fails to leverage its reference file for progressive disclosure.

Suggestions

Collapse the redundant 'Commands Reference', 'Integration Examples', and 'Common Patterns' sections (which restate the Methods commands) and move the detailed command catalog into references/quick_reference.md, linking to it from a concise overview.

Add explicit validation checkpoints to the workflows — e.g., run `check` before `link`, and run `validate` after batch linking — with a fix-and-retry loop, since batch and README-modifying operations require feedback loops.

Signal references/quick_reference.md from the body and remove or create the missing templates/ and examples/ paths that quick_reference.md points to, so references are one level deep and actually resolve.

DimensionReasoningScore

Conciseness

The ~600-line body is mostly actionable but heavily redundant — 'Commands Reference', 'Integration Examples', and 'Common Patterns' each restate the same `uv run` commands already shown in Methods 1-5 — so it could be tightened considerably, fitting the score-2 anchor.

2 / 3

Actionability

It provides fully executable, copy-paste-ready `uv run scripts/paper_manager.py` commands with specific flags, concrete YAML metadata examples, and a Python API example, matching the score-3 anchor.

3 / 3

Workflow Clarity

Workflows (Workflow 1-3, Common Patterns) are sequenced, but batch linking and README-modifying operations lack any validation checkpoints or validate-fix-retry feedback loops, so per the guidelines workflow clarity is capped at 2.

2 / 3

Progressive Disclosure

A references/quick_reference.md file exists but is never signaled or linked from the body, the monolithic body duplicates nearly all of it inline, and quick_reference.md itself points to non-existent templates/ and examples/ directories — fitting the score-2 anchor of references present but not clearly signaled with content that should be separate kept inline.

2 / 3

Total

9

/

12

Passed

Description

67%Weight 40%Scale 1-3

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 is specific and distinctively niched to Hugging Face paper publishing, but it omits any explicit 'Use when...' trigger guidance and lacks common trigger terms like 'arXiv', which weakens completeness and trigger coverage.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when publishing or indexing research papers on the Hugging Face Hub, linking arXiv papers to models/datasets, or claiming paper authorship').

Include the primary trigger term 'arXiv' and common variations ('HF', 'paper page', 'model card citation') so the description matches natural user phrasing.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles' — matching the score-3 anchor for naming several specific actions.

3 / 3

Completeness

It clearly answers 'what' the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance for when to use it, so per the judging guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

It includes some natural terms users would say ('research papers', 'Hugging Face Hub', 'paper pages', 'models/datasets'), but misses common variations and the primary trigger 'arXiv', fitting the score-2 anchor of relevant keywords without full coverage.

2 / 3

Distinctiveness Conflict Risk

'Publish and manage research papers on Hugging Face Hub' carves out a clear niche with distinct triggers that are unlikely to conflict with other skills, matching the score-3 anchor.

3 / 3

Total

10

/

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

skill_md_line_count

SKILL.md is long (625 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
huggingface/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.