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.
82
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly specifies concrete outputs (beamer LaTeX → PDF + PPTX, speaker notes, talk script), the input context (compiled paper, conference talk), and provides comprehensive bilingual trigger terms. It answers both what and when explicitly, and occupies a distinct niche that differentiates it from generic presentation-making skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generate conference presentation slides, produce beamer LaTeX → PDF + editable PPTX, create speaker notes and full talk script, all from a compiled paper. Very concrete and detailed. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate conference presentation slides as beamer LaTeX → PDF + PPTX with speaker notes and talk script from a compiled paper) and 'when' (explicit 'Use when' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms 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'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive: specifically targets conference presentations from compiled papers using beamer LaTeX, producing both PDF and PPTX with speaker notes. The combination of 'beamer', 'compiled paper', and 'conference talk' creates a clear niche unlikely to conflict with general presentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely thorough and actionable with an excellent multi-phase workflow, clear checkpoints, and executable commands throughout. However, it is severely over-verbose — much of the content (full LaTeX templates, complete talk script scaffolding, 8 Q&A placeholders, venue color tables) is template material that Claude can generate without being shown verbatim, wasting significant token budget. The content would benefit greatly from being split across reference files and trimmed to essential rules and constraints.
Suggestions
Reduce the LaTeX template to a minimal skeleton showing only venue-specific customizations and beamer-specific gotchas — Claude knows how to write beamer documents and doesn't need a full template.
Move the full talk script template and Q&A section to a separate reference file (e.g., TALK_SCRIPT_TEMPLATE.md) and reference it from the main skill.
Condense the slide outline tables — instead of showing full tables for each talk type, provide the pattern (e.g., 'allocate ~60% to method+results, scale linearly with duration') and let Claude adapt.
Remove the venue color table duplication (noted as 'Same as /paper-poster') and instead reference the poster skill's color definitions directly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Includes extensive template content Claude could generate on its own (full LaTeX templates, full talk script templates, Q&A templates with 8 placeholder questions, venue color tables). The slide outline tables for each talk type, the full beamer template, and the complete talk script format are all things Claude can produce without being shown verbatim examples. Much of this could be condensed to key rules and constraints. | 1 / 3 |
Actionability | Highly actionable with executable bash commands, complete LaTeX templates, specific python-pptx usage, concrete compilation commands, and explicit error handling loops. Every phase has copy-paste ready commands and clear outputs. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow (Phase 0-8) with explicit checkpoints, state persistence via JSON, error handling loops (max 3 compile attempts), validation steps (page count verification), and clear stop-and-wait points for user confirmation. The Phase 1 checkpoint is explicitly marked as critical with user options. | 3 / 3 |
Progressive Disclosure | Everything is in a single monolithic file with no references to external documents. The slide outline tables, full LaTeX template, full talk script template, and Q&A section could all be split into separate reference files. The content is well-structured with headers but the sheer volume in one file hurts discoverability. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (571 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 | 8 / 11 Passed | |
dc00dfb
Table of Contents
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.