Skip to content

smixs/osint-skill / osint

Conduct deep OSINT research on individuals. Build full digital footprint, psychoprofile (MBTI/Big Five), career history, social graph with confidence scores. Recursive self-evaluation until completeness threshold is met. Includes internal intelligence (Telegram history, email, vault contacts) before going external. Use when: "osint", "досье", "research person", "find everything about", "пробей", "разведка", "due diligence", "background check", "digital footprint", "найди всё про", "собери информацию", "кто это", "профиль человека". NOT for: company/product research without a named person, competitive analysis, market research, content generation, or general web scraping tasks.

FileKindSize
SKILL.mdskill md22.4 KB
assets/dossier-template.mdmarkdown2.9 KB
references/content-extraction.mdmarkdown3.2 KB
references/platforms.mdmarkdown4.6 KB
references/psychoprofile.mdmarkdown2.9 KB
references/tools.mdmarkdown12.7 KB
scripts/apify.shexecutablescript2.1 KB
scripts/brightdata.shexecutablescript2.1 KB
scripts/diagnose.shexecutablescript6.3 KB
scripts/exa.shexecutablescript3.6 KB
scripts/first-volley.shexecutablescript3.0 KB
scripts/jina.shexecutablescript1.5 KB
scripts/mcp-client.pyexecutablescript3.8 KB
scripts/merge-volley.shexecutablescript1.6 KB
scripts/package.jsonmanifest21 B
scripts/parallel.shexecutablescript1.9 KB
scripts/perplexity.shexecutablescript2.8 KB
scripts/run-actor.shexecutablescript1.7 KB
scripts/run_actor.jsscript9.8 KB
scripts/tavily.shexecutablescript2.3 KB

references/content-extraction.md

View on GitHub
# Content Extraction Guide

When you find a content platform (YouTube, podcast, blog, conference talks) -
**extract everything immediately.** Don't just note the URL and move on.

## Principle

Content platforms are the richest source for psychoprofile and real personality.
LinkedIn is a resume. Instagram is a highlight reel. YouTube/podcasts are unfiltered.

A person talking for 20 minutes on camera reveals more than 100 LinkedIn posts.

## YouTube

### Discovery
```bash
# Search for channel
web_search "site:youtube.com <Name> <context>"
bash skills/osint/scripts/exa.sh search "<Name> youtube channel"
```

### Channel metadata
```bash
# Fetch channel page - subscriber count, video count, about
web_fetch "https://www.youtube.com/@<handle>"
# Or channel page
bash skills/osint/scripts/jina.sh read "https://www.youtube.com/@<handle>/about"
```

### Transcript extraction (CRITICAL)
Pick 3-5 most viewed or most recent videos. Extract transcripts:
```bash
# Fetch video page - title, description, comments
web_fetch "https://www.youtube.com/watch?v=<id>"
# Get auto-generated transcript via Jina
bash skills/osint/scripts/jina.sh read "https://www.youtube.com/watch?v=<id>"
```

If transcripts unavailable via fetch, try:
```bash
bash skills/osint/scripts/brightdata.sh scrape "https://www.youtube.com/watch?v=<id>"
```

### What to extract from YouTube:
- **Topics** - what they talk about = what they care about
- **Speaking style** - formal/casual, speed, filler words, humor
- **Vocabulary** - jargon level, code-switching between languages
- **Self-presentation** - humble/confident/arrogant, claims vs evidence
- **Recurring themes** - across videos, what keeps coming back
- **Guest interactions** - how they treat guests, who they invite
- **Comment section** - audience demographics, sentiment
- **Upload frequency** - consistency = discipline trait
- **Video titles** - clickbait vs informative = marketing approach
- **Playlists** - how they organize knowledge = thinking structure

### Budget: 3-5 video transcripts via Jina = ~$0.02-0.05

## Podcasts / Audio Appearances

Search for podcast appearances:
```bash
web_search "<Name> podcast interview"
bash skills/osint/scripts/exa.sh search "<Name> podcast episode guest"
```

Podcast interviews are gold - the host asks personal questions.
Look for: origin story, career pivots, failures mentioned, mentors named.

## Blog / Personal Website

```bash
web_fetch "<personal-site>"
bash skills/osint/scripts/jina.sh read "<blog-url>"
# Crawl multiple pages
bash skills/osint/scripts/exa.sh crawl "<blog-url>"
```

Extract: writing style, topics, frequency, tone evolution over time.

## Conference Talks / Speaker Bios

```bash
web_search "<Name> speaker conference talk"
web_search "site:youtube.com <Name> conference keynote"
```

Speaker bios at conferences are often more honest than LinkedIn -
written for specific audience, include unique details.

## Rule: Immediate Deep Extraction

When you discover ANY content platform during Phase 1-2:

1. **STOP** current task
2. **Extract** 3-5 pieces of content immediately
3. **Analyze** for psychoprofile signals
4. **Resume** original task with enriched data

Do NOT bookmark for later. Later = never.
The insight from 3 YouTube transcripts outweighs 10 LinkedIn connections.
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall