skill-presentation
Presentation extraction and slide generation routing
Best use case
skill-presentation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Presentation extraction and slide generation routing
Teams using skill-presentation should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/skill-presentation/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How skill-presentation Compares
| Feature / Agent | skill-presentation | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Presentation extraction and slide generation routing
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Presentation Skill
Thin wrapper that routes presentation operations to the `presentation-agent`.
## Context Pointers
Reference (do not load eagerly):
- Path: `.claude/context/formats/subagent-return.md`
- Purpose: Return validation
- Load at: Subagent execution only
Note: This skill is a thin wrapper. Context is loaded by the delegated agent, not this skill.
## Trigger Conditions
This skill activates when:
### Direct Invocation
- User explicitly runs `/slides` command
- User requests presentation conversion in conversation
### Implicit Invocation (during task implementation)
When an implementing agent encounters any of these patterns:
**Plan step language patterns**:
- "Convert presentation to Beamer"
- "Extract slides from PowerPoint"
- "Generate Polylux slides"
- "Create Touying presentation"
- "Convert PPTX to LaTeX"
**File extension detection**:
- Source file has extension: `.pptx`, `.ppt`
- Target mentions: "Beamer", "slides", ".tex", "Polylux", "Touying", ".typ"
**Task description keywords**:
- "presentation conversion"
- "PowerPoint to LaTeX"
- "slide extraction"
- "academic slides"
### When NOT to trigger
Do not invoke for:
- Document conversions (use skill-filetypes)
- Spreadsheet conversions (use skill-spreadsheet)
- Simple markdown extraction without slide formatting
---
## Execution
### 1. Input Validation
Validate required inputs:
- `source_path` - Must be provided and file must exist
- `output_path` - Optional, defaults to source dir with .tex extension
- `output_format` - Optional, defaults to "beamer"
- `theme` - Optional theme name
```bash
# Validate source exists
if [ ! -f "$source_path" ]; then
return error "Source file not found: $source_path"
fi
# Validate source is presentation format
source_ext="${source_path##*.}"
case "$source_ext" in
pptx|ppt|md) ;; # Valid
*) return error "Not a presentation format: .$source_ext" ;;
esac
# Determine output path if not provided
if [ -z "$output_path" ]; then
source_dir=$(dirname "$source_path")
source_base=$(basename "$source_path" | sed 's/\.[^.]*$//')
case "$output_format" in
beamer|latex|tex) output_path="${source_dir}/${source_base}.tex" ;;
polylux|touying|typst|typ) output_path="${source_dir}/${source_base}.typ" ;;
pptx) output_path="${source_dir}/${source_base}_generated.pptx" ;;
*) output_path="${source_dir}/${source_base}.tex" ;;
esac
fi
```
### 2. Context Preparation
Prepare delegation context:
```json
{
"source_path": "/absolute/path/to/presentation.pptx",
"output_path": "/absolute/path/to/slides.tex",
"output_format": "beamer",
"theme": "metropolis",
"metadata": {
"session_id": "sess_{timestamp}_{random}",
"delegation_depth": 1,
"delegation_path": ["orchestrator", "slides", "skill-presentation"]
}
}
```
### 3. Invoke Agent
**CRITICAL**: You MUST use the **Task** tool to spawn the agent.
**Required Tool Invocation**:
```
Tool: Task (NOT Skill)
Parameters:
- subagent_type: "presentation-agent"
- prompt: [Include source_path, output_path, output_format, theme, metadata]
- description: "Convert {source_path} to {output_format} slides"
```
The agent will:
- Detect available tools (python-pptx, pandoc, markitdown)
- Extract presentation content
- Generate formatted slide output
- Extract and preserve speaker notes
- Return standardized JSON result
### 4. Return Validation
Validate return matches `subagent-return.md` schema:
- Status is one of: converted, partial, failed
- Summary is non-empty and <100 tokens
- Artifacts array present with output file path
- Metadata contains slide count
### 5. Return Propagation
Return validated result to caller without modification.
---
## Return Format
Expected successful return:
```json
{
"status": "converted",
"summary": "Successfully converted presentation.pptx to Beamer slides with 15 slides",
"artifacts": [
{
"type": "implementation",
"path": "/absolute/path/to/slides.tex",
"summary": "Beamer presentation with speaker notes"
}
],
"metadata": {
"session_id": "sess_...",
"agent_type": "presentation-agent",
"delegation_depth": 2,
"tool_used": "python-pptx+pandoc",
"slide_count": 15,
"has_speaker_notes": true
},
"next_steps": "Review and compile slides"
}
```
---
## Error Handling
### Input Validation Errors
Return immediately with failed status if source file not found or not a presentation.
### Unsupported Format
Return failed status with clear message about supported formats.
### Agent Errors
Pass through the agent's error return verbatim.
### Tool Not Available
Return failed status with installation instructions.Related Skills
skill-learn
Scan codebase for FIX:/NOTE:/TODO:/QUESTION: tags and create structured tasks with interactive selection. Invoke for /learn command.
skill-deck
Generate YC-style investor pitch decks in Typst
skill-todo
Archive completed and abandoned tasks with CHANGE_LOG.md updates and memory harvest suggestions
skill-team-research
Orchestrate multi-agent research with wave-based parallel execution. Spawns 2-4 teammates for diverse investigation angles and synthesizes findings.
skill-team-plan
Orchestrate multi-agent planning with parallel plan generation. Spawns 2-3 teammates for diverse planning approaches and synthesizes into final plan with trade-off analysis.
skill-team-implement
Orchestrate multi-agent implementation with parallel phase execution. Spawns teammates for independent phases and coordinates dependent phases. Includes debugger teammate for error recovery.
skill-status-sync
Atomically update task status across TODO.md and state.json. For standalone use only.
skill-spawn
Research blockers and spawn new tasks to overcome them, updating parent task dependencies
skill-researcher
Conduct general research using web search, documentation, and codebase exploration. Invoke for general research tasks.
skill-refresh
Manage Claude Code resources - terminate orphaned processes and clean up ~/.claude/ directory
skill-planner
Create phased implementation plans from research findings. Invoke when a task needs an implementation plan.
skill-orchestrator
Route commands to appropriate workflows based on task language and status. Invoke when executing /task, /research, /plan, /implement commands.