transcript-to-content
This skill transforms training and onboarding meeting transcripts into structured learning materials, documentation, and actionable review content. Use this skill when processing meeting transcripts from onboarding sessions, training meetings, or knowledge transfer conversations to extract key information and generate study guides, quick reference sheets, checklists, FAQ documents, action item lists, and training effectiveness assessments.
What this skill does
# Transcript to Content
Transform raw meeting transcripts and training session recordings into structured learning materials, documentation, and actionable insights.
## When to Use This Skill
Use this skill when:
- User provides meeting transcripts, training session recordings, or onboarding notes
- User requests structured learning materials from verbal/conversational data
- User asks to extract key information, procedures, or action items from meetings
- User needs to create training documentation, SOPs, or reference materials from transcripts
- User wants to generate study guides, checklists, or FAQ documents from training sessions
## Core Workflow
### Step 1: Understand the Request
Identify what type of content the user needs:
| Output Type | When to Use |
|------------|-------------|
| **Master Knowledge Source** | Comprehensive structured learning module with metadata, terminology, SOPs, nuances, and assessments |
| **Presentation/Slide Deck** | Visual training presentation for delivery or reference |
| **SOP Document** | Step-by-step procedural documentation |
| **Quick Reference Sheet** | Concise one-page summary of key points and procedures |
| **Study Guide** | Organized review material for learners |
| **Checklist** | Actionable task list extracted from procedures |
| **FAQ Document** | Common questions and answers from training content |
| **Action Items List** | Tasks, owners, and deadlines from meeting discussions |
### Step 2: Locate and Analyze Source Material
**If transcripts are in project directory:**
```bash
ls -lah /home/ubuntu/projects/[project-name]/
```
**Search for relevant content by keyword:**
```bash
grep -ri "keyword" /home/ubuntu/projects/[project-name]/*.md
```
**Read and identify:**
- Main topics and concepts
- Step-by-step procedures
- Critical warnings or nuances
- Terminology and definitions
- Real examples or scenarios
- Action items and decisions
- Questions and answers
### Step 3: Extract Structured Content
Apply **Chain of Thought processing:**
1. **Read entire transcript(s)** for macro-context and overall themes
2. **Isolate distinct topics** and group related information
3. **Extract facts, steps, and definitions** with precision
4. **Remove conversational filler** ("um," "uh," "I think," "maybe," "let's try")
5. **Convert to imperative, authoritative language** (use action verbs)
6. **Flag unknowns** with `[MISSING INFO]` rather than fabricating
**For Master Knowledge Source format:**
Read `/home/ubuntu/skills/transcript-to-content/references/master-knowledge-source-format.md` for complete schema and examples.
Extract these sections:
- **Module Metadata:** Topic and learning objective (1 sentence)
- **Key Terminology:** Definitions of jargon, acronyms, tools
- **Standard Operating Procedures:** Numbered steps in "Action > Result" format
- **Critical Nuances:** Warnings, consequences, best practices, context
- **Assessment Data:** 3-5 multiple-choice questions based strictly on content
**For other document types:**
- **Checklists:** Extract sequential action items with checkboxes
- **FAQs:** Identify questions asked and answers provided
- **Study Guides:** Organize by topic with key concepts and examples
- **Action Items:** Extract tasks with owners and deadlines
### Step 4: Apply Branding (if applicable)
**If user provides brand assets:**
- Ask for logo file, brand colors, and font preferences
- Store logo in working directory
- Apply brand colors consistently (primary color for accents, highlights, charts)
- Use specified fonts or professional web fonts (Inter, Roboto, Open Sans)
**If no branding provided:**
- Use clean, professional neutral palette
- Focus on clarity and readability
- Apply consistent styling throughout
### Step 5: Create Deliverables
#### For Presentations
Read `/home/ubuntu/skills/transcript-to-content/references/presentation-guidelines.md` for detailed guidelines.
**Workflow:**
1. Initialize presentation using `slide_initialize` tool
2. Create outline (max 12 slides by default unless user specifies)
3. Copy logo to project directory if provided:
```bash
cp [logo-path] [project-dir]/logo.png
```
4. Edit slides one by one using `slide_edit` tool
5. Present using `slide_present` tool
6. Export to PDF if requested:
```bash
manus-export-slides manus-slides://[version-id] pdf
```
**Standard presentation structure:**
1. Title slide
2. Definition/overview
3. Step-by-step content (4-6 steps)
4. Critical success factors
5. Common pitfalls
6. Key takeaways
7. Closing slide
**Design requirements:**
- Use brand color (if provided) or professional neutral palette
- Include logo on every slide (if provided)
- Maintain 720px height limit
- Use clean, grid-based layouts
- No excessive shadows, rounded corners, or animations
#### For SOP Documents
Create Markdown documents with:
- Clear hierarchical structure (H1, H2, H3)
- Numbered procedures with imperative language
- Warning/caution callouts in blockquotes
- Tables for reference data
- Inline citations where applicable
**Example structure:**
```markdown
# [Procedure Name]
## Overview
[Brief description]
## Prerequisites
- [Required items or conditions]
## Procedure
1. [Action step]
2. [Action step]
3. **CRITICAL:** [Important step with warning]
## Troubleshooting
- **Issue:** [Problem]
**Solution:** [Resolution]
```
#### For Quick Reference Sheets
Create concise one-page documents with:
- Key terminology in definition list format
- Essential steps in numbered lists
- Critical warnings in highlighted boxes
- Common scenarios with solutions
#### For Study Guides
Organize by topic with:
- Learning objectives
- Key concepts with explanations
- Examples and scenarios
- Practice questions
- Additional resources
#### For Checklists
Extract action items with:
- Checkbox format (`- [ ]`)
- Clear, actionable language
- Logical sequence
- Optional: Priority indicators or time estimates
#### For FAQ Documents
Structure as:
- Question in bold
- Answer in clear, concise language
- Optional: Related questions or resources
#### For Master Knowledge Source
Follow the schema in `references/master-knowledge-source-format.md` exactly:
- Output ONLY the structured content (no preamble or postscript)
- Use strict Markdown formatting
- Convert all conversational language to authoritative instructions
- Flag unknowns with `[MISSING INFO]`
## Quality Standards
**Content Accuracy:**
- Base all content strictly on source material
- Never fabricate steps, data, or information
- Flag incomplete procedures clearly with `[MISSING INFO]`
- Verify terminology definitions against source
**Clarity and Readability:**
- Use imperative voice for instructions ("Click", "Navigate", "Set")
- Maintain clear visual hierarchy
- Ensure scannability with headings and lists
- Remove all conversational filler
**Consistency:**
- Apply formatting standards throughout
- Use consistent terminology
- Maintain uniform structure across similar sections
**Branding (if applicable):**
- Use brand colors consistently
- Include logo on all branded materials
- Apply specified fonts
- Follow brand style guidelines
## Common Patterns
### Pattern 1: Single Topic Training Presentation
User provides transcript(s) on one topic → Extract key content → Create 8-12 slide presentation
### Pattern 2: Multiple Topics to Learning Modules
User provides multiple transcripts → Extract each as separate module → Deliver as structured documents
### Pattern 3: Quick Reference SOP
User needs specific procedure → Extract relevant steps → Create concise SOP document
### Pattern 4: Training Overview Summary
User requests summary of topic → Search transcripts → Extract and synthesize key points → Deliver as Markdown
### Pattern 5: Onboarding Checklist
User provides onboarding transcript → Extract sequential tasks → Create checklist with checkboxes
### Pattern 6: Meeting Action Items
User provides meeting notes → Extract decisions and tasks → Create action itRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.