菜单
This skill should be used when users have audio interview recordings to transcribe, need to convert PDF documents, mentions 'import data', 'transcribe', 'convert', or is starting data preparation for Stage 1 or Stage 2.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Examine philosophical assumptions and check for methodological coherence. Use when users question their philosophical stance, their language contradicts their declared epistemology, they are moving between stages and want to verify coherence, or something feels 'off' about their analytical approach. Checks language coherence, method-epistemology alignment, and AI relationship consistency.
Shared infrastructure for Interpretive Orchestration. Provides state management, configuration I/O, batched file operations, and enforcement utilities for qualitative research projects. Use when working with .interpretive-orchestration/config.json, checking stage completion, updating progress, or validating project setup.
Dialogical coding for qualitative research. Acts as thinking partner in Stage 1 (never suggests codes, only asks questions) and reflexive coding partner in Stage 2 (4-stage visible reasoning). Use when coding interview transcripts, field notes, or other qualitative data.
Initialize a new qualitative research project with Socratic onboarding. Guides researchers through philosophical foundation establishment via interactive dialogue. Use when starting a new project, setting up epistemic stance, or configuring methodological preferences.
Deep reasoning and paradox navigation via MCP tools. Integrates Sequential Thinking for systematic analysis and Lotus Wisdom for navigating contradictions. Use when planning complex analysis, working through theoretical tensions, or making methodological decisions.
Progress dashboard and navigation for Interpretive Orchestration. Shows current stage, progress indicators, next steps, and atelier status. Use when checking progress, navigating between stages, or planning next steps.
| name | interview-ingest |
| description | This skill should be used when users have audio interview recordings to transcribe, need to convert PDF documents, mentions 'import data', 'transcribe', 'convert', or is starting data preparation for Stage 1 or Stage 2. |
Audio transcription and document conversion for qualitative data import. Converts interview recordings, PDFs, and other formats into analyzable markdown.
Use this skill when:
This skill operates at two capability tiers:
# Check for MinerU
[ -n "$MINERU_API_KEY" ] && echo "MinerU available (Tier 1)" || echo "Manual conversion (Tier 2)"
Recommended transcription services:
Best practices:
Tier 1 (MinerU - recommended for complex PDFs):
# Parse PDF with VLM mode for tables/images
mineru_parse({
url: "file:///path/to/paper.pdf",
model: "vlm",
formula: true,
table: true
})
Tier 2 (Manual conversion):
| Format | Conversion Method | Notes |
|---|---|---|
| DOCX | Copy/paste or Pandoc | Good formatting |
| PPTX | Export to text | Manual extraction |
| XLSX | Export to CSV/text | Tables preserved |
| Images | OCR tools | Tesseract, Google Lens |
| YouTube | Download captions | Auto-generated transcripts |
| Web pages | WebFetch or Jina | Full content extraction |
Batch process interview recordings.
node skills/interview-ingest/scripts/process-audio.js \
--project-path /path/to/project \
--input-dir /path/to/recordings \
--output-dir stage1-foundation/manual-codes
stage1-foundation/
├── manual-codes/
│ ├── P001-interview.md # Transcribed interviews
│ ├── P002-interview.md
│ └── ...
├── raw-data/ # Original files (optional)
│ ├── P001-recording.mp3
│ └── ...
└── data-inventory.json # Tracks all data sources
{
"documents": [
{
"id": "P001",
"original_file": "P001-recording.mp3",
"converted_file": "P001-interview.md",
"format": "audio",
"conversion_tool": "otter.ai",
"conversion_date": "2025-01-15",
"duration_minutes": 45,
"notes": "Good audio quality"
}
]
}
If automated transcription unavailable:
Audio Options:
PDF Options: