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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

77%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 content is highly actionable and exceptionally well-sequenced with strong validation checkpoints and state persistence. Its weaknesses are token efficiency (verbose illustrative scaffolding) and progressive disclosure (large inline templates that would benefit from separate reference files, with no bundle files present).

Suggestions

Move the full TALK_SCRIPT.md and 8-question Q&A templates into a references/ file and link to it, keeping only the structure in SKILL.md to improve progressive_disclosure and conciseness.

Trim the verbose checkpoint ASCII blocks and example talk-script prose to assume Claude's competence, reducing token cost while preserving the rules.

Extract the venue color-scheme and talk-type/slide-count tables into a shared reference file referenced one level deep, since they duplicate /paper-poster-html content.

Dimension	Reasoning	Score
Conciseness	The body is comprehensive but noticeably long (~580 lines) with padded illustrative material (full talk-script markdown template, 8-question Q&A scaffolds, verbose checkpoint blocks) that assumes little of Claude's competence; could be tightened without losing clarity.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: concrete bash commands ("which pdflatex && which latexmk", "latexmk -$ENGINE -interaction=nonstopmode main.tex"), a complete beamer LaTeX template, and a python-pptx generation step with specific dimensions.	5 / 5
Workflow Clarity	Clearly sequenced Phases 0-8 with explicit state persistence (SLIDES_STATE.json), validation checkpoints (compile error loop max 3 attempts, pdfinfo page-count verification), and STOP-and-wait confirmation gates with defined options.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent), yet inline content that would benefit from separate files (venue color tables, full talk-script template, Q&A scaffolds) is inlined; shared-references are linked one level deep but bulk detail is not split out.	3 / 5
	Total	16 / 20 Passed

Description

100%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 is concrete, action-oriented, and explicitly answers both what the skill does and when to use it, with a rich set of natural bilingual trigger phrases. It is one of the strongest possible descriptions and matches the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: "Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX)", "with speaker notes and full talk script", covering compilation, dual-format export, notes, and script generation.	5 / 5
Completeness	Clearly answers both what ("Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script") and when ("Use when user says...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage in both English and Chinese: "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", plus "beamer slides for a conference talk".	5 / 5
Distinctiveness Conflict Risk	Clear niche (conference talk slides from a compiled paper via beamer) with distinct multilingual triggers; minimal overlap risk with general document or poster skills.	5 / 5
	Total	20 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (583 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
relative_links	Relative link issues: 3 suspicious	Warning

	Total	12 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/skills-codex-gemini-review/paper-slides/SKILL.md
Commit: f4f20f9

Reviewed: 1 day 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.