CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

88%

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

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.

A thorough, well-sequenced workflow with strong validation and feedback loops, anchored by executable LaTeX and bash. Its main weaknesses are monolithic inlining of template material that belongs in reference files and some redundant rule restatements.

Suggestions

Move the full talk-script template, anticipated Q&A bank, and venue color-scheme tables into separate reference files (e.g. references/TALK_SCRIPT_TEMPLATE.md, references/QA_BANK.md, references/venue_colors.md) and link to them one level deep from SKILL.md to improve progressive disclosure.

Remove the 'Key Rules' duplicates of Phase 2 presentation rules (one-message-per-slide, ≥60% figure area, progressive disclosure, bullet-only, font minimums) and the 'Parameter Pass-Through' restatement of the Constants block to recover tokens.

Provide a concrete generate_pptx.py skeleton (python-pptx imports, slide-layout loop, notes transfer) instead of prose steps so the PowerPoint export phase is fully executable.

DimensionReasoningScore

Conciseness

Mostly efficient, actionable content without explaining concepts Claude already knows, but the 'Key Rules' section duplicates Phase 2 presentation rules and 'Parameter Pass-Through' re-lists the Constants block, adding avoidable tokens.

4 / 5

Actionability

Concrete bash commands, a complete copy-paste beamer template, and a full Codex review prompt, but the PPTX export is described as prose steps for generate_pptx.py rather than executable code, leaving a minor gap.

4 / 5

Workflow Clarity

Eight clearly sequenced phases with SLIDES_STATE.json persistence, an explicit STOP checkpoint after the outline, a max-3-attempt compile error loop, and pdfinfo page-count verification provide explicit validation and feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist and the 630-line body is monolithic; section structure is good, but the talk-script template, Q&A bank, venue color tables, and per-talk-type slide templates are all inlined rather than split into one-level-deep reference files.

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.

A strong, third-person description that concretely states capabilities and provides rich bilingual trigger phrases covering both what and when. It is comprehensive, distinct, and free of vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — beamer LaTeX generation, PDF compile, editable PPTX export, speaker notes, and full talk script — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly 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 including bilingual synonyms users actually say ('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 generated from a compiled paper — with distinct triggers that minimize overlap risk with adjacent skills like poster generation.

5 / 5

Total

20

/

20

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 (636 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
wanshuiyin/Auto-claude-code-research-in-sleep
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.