CtrlK
BlogDocsLog inGet started
Tessl Logo

aris-paper-slides

Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.

66

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

A thorough, well-sequenced multi-phase workflow with strong validation and feedback loops, weakened by monolithic structure (no reference files) and a PowerPoint-export step described in prose rather than executable code. Tightening the sample script/Q&A templates and extracting large templates into reference files would raise the lower dimensions.

Suggestions

Provide executable `generate_pptx.py` code (python-pptx) instead of a prose description of what the script should do, so the PowerPoint export is copy-paste ready.

Extract large inline templates (the beamer LaTeX template, the full talk-script manuscript, and the Q&A bank) into reference files under references/ and link to them one level deep to improve progressive disclosure.

Tighten the Phase 8 talk-script and 8-item Q&A examples to concise skeletons to reduce token weight without losing the actionable structure.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but the ~560-line body includes a full sample talk-script manuscript and an 8-item Q&A template that could be tightened. Not 3 because not every token earns its place; not 1 because it does not explain concepts Claude already knows.

2 / 3

Actionability

Provides copy-paste-ready beamer LaTeX and executable bash (latexmk, pdfinfo, symlinks), but the PowerPoint export section describes `generate_pptx.py` in prose ('Write... that: 1. Creates a PPTX...') rather than giving executable code. Not 3 because a major output is described, not coded; not 1 because much of the guidance is concrete and runnable.

2 / 3

Workflow Clarity

A clear 9-phase sequence with state persistence, an explicit compile error→fix→recompile loop (max 3 attempts), validation (`pdfinfo | grep Pages` page-count check), and STOP checkpoints awaiting user confirmation — matching the 'clear sequence with explicit validation and feedback loops' anchor.

3 / 3

Progressive Disclosure

The body is well-sectioned by phase, but it is monolithic (~560 lines, no references/scripts/assets bundle files exist) with large templates (beamer source, full talk script, Q&A) inlined that could be split into reference files. Not 3 because there are no one-level-deep references; not 1 because organization is clear rather than a poor wall of text.

2 / 3

Total

9

/

12

Passed

Description

100%

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 description: concrete capabilities, an explicit 'Use when...' trigger clause with rich bilingual natural-language keywords, and a distinctive niche. It satisfies all four dimensions at the top of the scale.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'beamer LaTeX → PDF + editable PPTX', 'speaker notes', 'full talk script', 'from a compiled paper' — matching the rubric's 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers what ('Generate conference presentation slides... with speaker notes and full talk script') and when ('Use when user says...'), satisfying the 'clearly answers both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

Covers natural user phrasings in both English and Chinese ('做PPT', '做幻灯片', 'make slides', 'conference talk', 'presentation slides', '生成slides', '写演讲稿', 'beamer slides for a conference talk'), which a user would plausibly say. Not scored 2 because common variations are well covered, not partially.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (conference talk slides from a compiled paper) with distinctive triggers unlikely to fire for unrelated skills. Uses third-person voice ('Generate...'), so no voice penalty applies.

3 / 3

Total

12

/

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 (575 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
OpenLAIR/dr-claw
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.