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

scripts/diagnose.sh

View on GitHub
#!/bin/bash
# OSINT Toolkit Self-Diagnostic
# Run before starting any research to check available tools
# Usage: ./diagnose.sh

SKILL_DIR="$(cd "$(dirname "$0")/.." && pwd)"
WORKSPACE="$(cd "$SKILL_DIR/../.." && pwd)"

echo "=== OSINT TOOLKIT DIAGNOSTIC ==="
echo ""

# 1. API Tokens (env or file)
echo "📡 API Tokens:"
if [ -n "${APIFY_API_TOKEN:-}" ]; then
  echo "  ✅ APIFY_API_TOKEN (env)"
elif [ -f "$WORKSPACE/scripts/apify-api-token.txt" ]; then
  echo "  ✅ APIFY_API_TOKEN (file: scripts/apify-api-token.txt)"
else
  echo "  ❌ APIFY_API_TOKEN"
fi

if [ -n "${JINA_API_KEY:-}" ]; then
  echo "  ✅ JINA_API_KEY (env)"
elif [ -f "$WORKSPACE/scripts/jina-api-key.txt" ]; then
  echo "  ✅ JINA_API_KEY (file: scripts/jina-api-key.txt)"
else
  echo "  ❌ JINA_API_KEY"
fi

if [ -n "${PERPLEXITY_API_KEY:-}" ]; then
  echo "  ✅ PERPLEXITY_API_KEY (env)"
else
  echo "  ❌ PERPLEXITY_API_KEY"
fi

if [ -n "${PARALLEL_API_KEY:-}" ]; then
  echo "  ✅ PARALLEL_API_KEY (env)"
elif [ -f "$WORKSPACE/scripts/parallel-api-key.txt" ]; then
  echo "  ✅ PARALLEL_API_KEY (file: scripts/parallel-api-key.txt)"
else
  echo "  ❌ PARALLEL_API_KEY"
fi

if [ -n "${EXA_API_KEY:-}" ]; then
  echo "  ✅ EXA_API_KEY (env)"
else
  echo "  ⚠️  EXA_API_KEY (not set — exa.sh won't work)"
fi

if [ -n "${TAVILY_API_KEY:-}" ]; then
  echo "  ✅ TAVILY_API_KEY (env)"
else
  echo "  ❌ TAVILY_API_KEY"
fi

if [ -n "${BRIGHTDATA_MCP_URL:-}" ]; then
  echo "  ✅ BRIGHTDATA_MCP_URL (env)"
elif [ -f "$WORKSPACE/scripts/brightdata-mcp-url.txt" ]; then
  echo "  ✅ BRIGHTDATA_MCP_URL (file: scripts/brightdata-mcp-url.txt)"
else
  echo "  ❌ BRIGHTDATA_MCP_URL"
fi
echo ""

# 2. CLI tools
echo "🔧 CLI Tools:"
command -v mcporter &>/dev/null && echo "  ✅ mcporter" || echo "  ❌ mcporter"
[ -f ~/.local/node_modules/.bin/mcpc ] && echo "  ✅ mcpc (Apify actor discovery)" || echo "  ❌ mcpc (npm i @apify/mcpc)"
command -v jq &>/dev/null && echo "  ✅ jq" || echo "  ❌ jq"
command -v curl &>/dev/null && echo "  ✅ curl" || echo "  ❌ curl"
if command -v node &>/dev/null; then
  NODE_V=$(node -v 2>/dev/null)
  NODE_MAJOR=$(echo "$NODE_V" | sed 's/v//' | cut -d. -f1)
  if [ "$NODE_MAJOR" -ge 18 ]; then
    echo "  ✅ node $NODE_V (run_actor.js compatible)"
  else
    echo "  ⚠️  node $NODE_V (need 18+ for run_actor.js)"
  fi
else
  echo "  ❌ node (required for run_actor.js)"
fi
[ -f "$SKILL_DIR/scripts/run_actor.js" ] && echo "  ✅ run_actor.js (embedded, 55+ actors)" || echo "  ❌ run_actor.js (missing from skill)"
[ -f "$SKILL_DIR/scripts/run-actor.sh" ] && echo "  ✅ run-actor.sh (bash wrapper)" || echo "  ❌ run-actor.sh"
echo ""

# 3. Internal Intelligence Tools
echo "📱 Internal Intelligence:"
if [ -f "$WORKSPACE/skills/telegram/scripts/tg.py" ]; then
  echo "  ✅ tg.py (Telegram history/search)"
else
  echo "  ❌ tg.py (no Telegram access)"
fi

if command -v himalaya &>/dev/null || [ -f ~/.local/bin/himalaya ]; then
  echo "  ✅ himalaya (email search)"
else
  echo "  ❌ himalaya (no email access)"
fi

if [ -d "$WORKSPACE/vault/crm" ]; then
  VAULT_COUNT=$(find "$WORKSPACE/vault/crm" -name "*.md" 2>/dev/null | wc -l)
  echo "  ✅ vault/crm ($VAULT_COUNT cards)"
else
  echo "  ❌ vault/crm (no CRM vault)"
fi

if [ -f "$WORKSPACE/scripts/twitter.py" ]; then
  echo "  ✅ twitter.py (X/Twitter reader)"
else
  echo "  ❌ twitter.py (no Twitter access)"
fi
echo ""

# 4. MCP servers
echo "🔌 MCP Servers:"
if command -v mcporter &>/dev/null; then
  MCPORTER_CONFIG="${MCPORTER_CONFIG:-./config/mcporter.json}"
  if [ -f "$MCPORTER_CONFIG" ]; then
    MCPORTER_CONFIG="$MCPORTER_CONFIG" mcporter list 2>/dev/null | grep -E "^[a-z]" | while read -r server; do
      echo "  ✅ $server"
    done
  else
    echo "  ⚠️  mcporter config not found at $MCPORTER_CONFIG"
  fi
else
  echo "  ⚠️  mcporter not installed (npm i -g mcporter)"
fi
echo ""

# 5. Capability summary
echo "📊 Capabilities:"
([ -n "${APIFY_API_TOKEN:-}" ] || [ -f "$WORKSPACE/scripts/apify-api-token.txt" ]) && echo "  LinkedIn scraping (Apify): ✅" || echo "  LinkedIn scraping (Apify): ❌"
([ -n "${APIFY_API_TOKEN:-}" ] || [ -f "$WORKSPACE/scripts/apify-api-token.txt" ]) && echo "  Instagram scraping (Apify): ✅" || echo "  Instagram scraping (Apify): ❌"
([ -n "${APIFY_API_TOKEN:-}" ] || [ -f "$WORKSPACE/scripts/apify-api-token.txt" ]) && echo "  TikTok scraping (Apify clockworks): ✅" || echo "  TikTok scraping: ❌"
([ -n "${APIFY_API_TOKEN:-}" ] || [ -f "$WORKSPACE/scripts/apify-api-token.txt" ]) && echo "  YouTube scraping (Apify streamers): ✅" || echo "  YouTube scraping: ❌"
([ -n "${APIFY_API_TOKEN:-}" ] || [ -f "$WORKSPACE/scripts/apify-api-token.txt" ]) && echo "  Contact enrichment (Apify): ✅" || echo "  Contact enrichment: ❌"
([ -n "${APIFY_API_TOKEN:-}" ] || [ -f "$WORKSPACE/scripts/apify-api-token.txt" ]) && echo "  Google Maps (Apify): ✅" || echo "  Google Maps: ❌"
([ -n "${BRIGHTDATA_MCP_URL:-}" ] || [ -f "$WORKSPACE/scripts/brightdata-mcp-url.txt" ]) && echo "  Facebook scraping (Bright Data): ✅" || echo "  Facebook scraping: ❌"
([ -n "${BRIGHTDATA_MCP_URL:-}" ] || [ -f "$WORKSPACE/scripts/brightdata-mcp-url.txt" ]) && echo "  CAPTCHA bypass (Bright Data): ✅" || echo "  CAPTCHA bypass: ❌"
([ -n "${JINA_API_KEY:-}" ] || [ -f "$WORKSPACE/scripts/jina-api-key.txt" ]) && echo "  Deep search (Jina): ✅" || echo "  Deep search (Jina): ❌"
[ -n "${PERPLEXITY_API_KEY:-}" ] && echo "  Quick answers (Perplexity Sonar): ✅" || echo "  Quick answers (Perplexity): ❌"
[ -n "${PERPLEXITY_API_KEY:-}" ] && echo "  Deep research (Perplexity Deep): ✅" || echo "  Deep research (Perplexity): ❌"
[ -n "${TAVILY_API_KEY:-}" ] && echo "  Agent search (Tavily): ✅" || echo "  Agent search (Tavily): ❌"
[ -n "${EXA_API_KEY:-}" ] && echo "  Semantic search (Exa): ✅" || echo "  Semantic search (Exa): ❌"
[ -n "${EXA_API_KEY:-}" ] && echo "  People/Company search (Exa): ✅" || echo "  People/Company search (Exa): ❌"
([ -n "${PARALLEL_API_KEY:-}" ] || [ -f "$WORKSPACE/scripts/parallel-api-key.txt" ]) && echo "  AI search (Parallel): ✅" || echo "  AI search (Parallel): ❌"
[ -f "$WORKSPACE/skills/telegram/scripts/tg.py" ] && echo "  Telegram intel: ✅" || echo "  Telegram intel: ❌"
(command -v himalaya &>/dev/null || [ -f ~/.local/bin/himalaya ]) && echo "  Email intel: ✅" || echo "  Email intel: ❌"
echo ""
echo "=== END DIAGNOSTIC ==="
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