smixs/osint-skill / osint
osint
VerifiedConduct 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 22.4 KB |
| assets/dossier-template.md | markdown | 2.9 KB |
| references/content-extraction.md | markdown | 3.2 KB |
| references/platforms.md | markdown | 4.6 KB |
| references/psychoprofile.md | markdown | 2.9 KB |
| references/tools.md | markdown | 12.7 KB |
| scripts/apify.shexecutable | script | 2.1 KB |
| scripts/brightdata.shexecutable | script | 2.1 KB |
| scripts/diagnose.shexecutable | script | 6.3 KB |
| scripts/exa.shexecutable | script | 3.6 KB |
| scripts/first-volley.shexecutable | script | 3.0 KB |
| scripts/jina.shexecutable | script | 1.5 KB |
| scripts/mcp-client.pyexecutable | script | 3.8 KB |
| scripts/merge-volley.shexecutable | script | 1.6 KB |
| scripts/package.json | manifest | 21 B |
| scripts/parallel.shexecutable | script | 1.9 KB |
| scripts/perplexity.shexecutable | script | 2.8 KB |
| scripts/run-actor.shexecutable | script | 1.7 KB |
| scripts/run_actor.js | script | 9.8 KB |
| scripts/tavily.shexecutable | script | 2.3 KB |
scripts/mcp-client.py
View on GitHub#!/usr/bin/env python3
"""Lightweight MCP client for Streamable HTTP/SSE transport.
Usage:
python3 mcp-client.py <mcp_url> --list-tools
python3 mcp-client.py <mcp_url> <tool_name> '<json_args>'
"""
import json
import sys
import http.client
from urllib.parse import urlparse, urlencode
def mcp_request(url: str, method: str, params: dict | None = None,
req_id: int = 1, session_id: str | None = None) -> tuple[dict, str | None]:
"""Send MCP JSON-RPC request and parse SSE response. Returns (result, session_id)."""
parsed = urlparse(url)
payload = {
"jsonrpc": "2.0",
"id": req_id,
"method": method,
}
if params:
payload["params"] = params
data = json.dumps(payload).encode()
headers = {
"Content-Type": "application/json",
"Accept": "application/json, text/event-stream",
}
if session_id:
headers["Mcp-Session-Id"] = session_id
conn = http.client.HTTPSConnection(parsed.hostname, timeout=120)
path = parsed.path
if parsed.query:
path += "?" + parsed.query
conn.request("POST", path, body=data, headers=headers)
resp = conn.getresponse()
# Get session ID from response headers
new_session_id = resp.getheader("Mcp-Session-Id") or session_id
body = resp.read().decode()
conn.close()
if resp.status >= 400:
return {"error": f"HTTP {resp.status}: {body[:200]}"}, new_session_id
# Parse SSE: look for data: lines
for line in body.split("\n"):
if line.startswith("data: "):
try:
return json.loads(line[6:]), new_session_id
except json.JSONDecodeError:
continue
# Try direct JSON
try:
return json.loads(body), new_session_id
except json.JSONDecodeError:
return {"raw": body[:500]}, new_session_id
def init_and_call(url: str, method: str, params: dict | None = None) -> dict:
"""Initialize session then make a call."""
# Step 1: Initialize
init_result, session_id = mcp_request(url, "initialize", {
"protocolVersion": "2024-11-05",
"capabilities": {},
"clientInfo": {"name": "osint-skill", "version": "3.1"},
}, req_id=1)
if "error" in init_result:
return init_result
# Step 2: Send initialized notification (optional but polite)
# Step 3: Make actual call
result, _ = mcp_request(url, method, params, req_id=2, session_id=session_id)
return result
def list_tools(url: str) -> list:
"""List available tools on MCP server."""
result = init_and_call(url, "tools/list")
tools = result.get("result", {}).get("tools", [])
return tools
def call_tool(url: str, tool_name: str, arguments: dict) -> dict:
"""Call a specific tool on MCP server."""
result = init_and_call(url, "tools/call", {
"name": tool_name,
"arguments": arguments,
})
return result
def main():
if len(sys.argv) < 3:
print(__doc__)
sys.exit(1)
url = sys.argv[1]
if sys.argv[2] == "--list-tools":
tools = list_tools(url)
if not tools:
print("No tools found or error occurred")
return
for t in tools:
desc = t.get("description", "")[:100]
print(f" {t['name']}: {desc}")
return
tool_name = sys.argv[2]
args = json.loads(sys.argv[3]) if len(sys.argv) > 3 else {}
result = call_tool(url, tool_name, args)
# Extract content from MCP response
content = result.get("result", {}).get("content", [])
if content:
for item in content:
if item.get("type") == "text":
print(item["text"])
else:
print(json.dumps(result, indent=2, ensure_ascii=False))
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |