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.

67

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

70%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 well-sequenced, highly actionable multi-phase workflow with strong validation checkpoints, but it is long and redundant with everything inlined into one file rather than split into reference bundles.

Suggestions

Deduplicate the slide-density rules — keep them in one place (the Phase 2 table or Key Rules) and cross-reference, rather than restating verbatim in both.

Move the beamer template and the talk-script/Q&A template into separate reference files under references/ and link to them, to reduce the inline length and improve progressive disclosure.

Provide the full generate_pptx.py source (or a reference script in scripts/) rather than only describing its steps, to close the main actionability gap.

DimensionReasoningScore

Conciseness

Mostly efficient and actionable, but noticeably redundant — the slide-density rules (one message/slide, max 6 lines, figure ≥60%, bullet fragments) are stated in both the Phase 2 table and the Key Rules section, and the full talk-script/Q&A template is long.

3 / 5

Actionability

Provides concrete bash commands, a complete copy-paste beamer template, and per-phase executable steps; the main gap is generate_pptx.py, which is described in steps but not fully written out.

4 / 5

Workflow Clarity

A clearly sequenced 9-phase (Phase 0–8) workflow with explicit STOP checkpoints, SLIDES_STATE.json persistence, a compile error-recovery loop (max 3 attempts), and pdfinfo page-count verification.

5 / 5

Progressive Disclosure

No bundle files exist and the SKILL.md is a ~540-line monolith; content that could be split out (the beamer template, the talk-script/Q&A template, venue color tables) is inlined, though sections are reasonably organized.

3 / 5

Total

15

/

20

Passed

Description

96%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 excellent: third-person, concrete, and explicit about both capability and trigger conditions, with rich bilingual natural-language triggers. The only soft spot is minor overlap with generic pptx skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX)... with speaker notes and full talk script' — covering the full output pipeline comprehensively.

5 / 5

Completeness

Explicitly answers both what (generate slides/PPTX/notes/script from a compiled paper) and when (a 'Use when user says...' clause with concrete trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms including bilingual synonyms — '做PPT', '做幻灯片', 'make slides', 'conference talk', 'presentation slides', '生成slides', '写演讲稿', 'beamer slides' — exactly what a user would say.

5 / 5

Distinctiveness Conflict Risk

Clear niche (conference talk slides from a compiled paper via beamer) with distinct triggers; only minor overlap risk with generic presentation/pptx-editing skills via the PPTX export mention.

4 / 5

Total

19

/

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 (572 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.