osint

Name: osint
Author: assafkip

47stars4forks

How to install osint?

assafkip/huntkit/osint

$npx -y skills add assafkip/huntkit --skill osint

Installs into the current project.

Summary

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, va

Files · 1

View on GitHub

SKILL.md

1	# OSINT Skill v3.2
2
3	Systematic intelligence gathering on individuals. From a name or handle to a scored
4	dossier with psychoprofile, career map, and entry points.
5
6	## Phase Router
7
8	Determine entry point from context:
9
10	- New name/handle/URL, "пробей", "find out about" → Phase 0 (full cycle)
11	- "Add LinkedIn/Instagram data" to existing dossier → Phase 2 (extraction)
12	- "Build psychoprofile" from existing data → Phase 4
13	- "Rate completeness" of existing dossier → Phase 5
14	- "Reformat" or "present" findings → Phase 6
15
16	Default (full research request): Phase 0 → 1 → 1.5 → 2 → 3 → 4 → 5 → 6.
17
18	## Environment
19
20	All API keys via environment variables. Never hardcode tokens.
21
22	- `PERPLEXITY_API_KEY` — Perplexity Sonar (fast answers + deep research)
23	- `EXA_API_KEY` — Exa AI (semantic search, company/people research, deep research)
24	- `TAVILY_API_KEY` — Tavily (agent-optimized search + extract, $0.005/req basic)
25	- `APIFY_API_TOKEN` — Apify scraping (LinkedIn, Instagram, Facebook)
26	- `JINA_API_KEY` — Jina reader/search/deepsearch
27	- `PARALLEL_API_KEY` — Parallel AI search
28	- `BRIGHTDATA_MCP_URL` — Bright Data MCP endpoint (full URL with token)
29	- `MCPORTER_CONFIG` — mcporter config path
30
31	## Scripts
32
33	Run from skill dir: `bash scripts/<name>.sh`.
34	Each script validates env vars, exits with descriptive error + URL to get the key.
35
36	Search & Research:
37	- `diagnose.sh` — run FIRST. Capability map of all tools.
38	- Perplexity (first-pass default): when operating through Claude, call the MCP tool `mcp__perplexity-ask__perplexity_ask` directly. It returns an AI answer with citations (equivalent to `sonar` mode). Use the shell script for `search` (ranked web results), `reason` (reconcile contradictions), and `deep` (long-form research) modes, or from bash pipelines.
39	- `perplexity.sh` — `search <query>` \| `sonar <query>` (AI answer) \| `reason <query>` (sonar-reasoning-pro, compare leads / reconcile contradictions) \| `deep <query>` (deep research). Required by `first-volley.sh` and any bash-only pipeline.
40	- `tavily.sh` — `search <query>` (basic $0.005) \| `deep <query>` (advanced) \| `extract <url>`
41	- `exa.sh` — `search <query>` \| `company <name>` \| `people <name>` \| `crawl <url>` \| `deep <prompt>`
42	- `first-volley.sh "Name" "context"` — parallel search, all engines at once.
43	- `merge-volley.sh <outdir>` — deduplicate and merge first-volley results.
44
45	Scraping:
46	- `apify.sh` — `linkedin <url>` \| `instagram <handle>` \| `run` \| `results` \| `store-search`
47	- `run-actor.sh` — universal Apify runner (55+ actors). Embedded from [apify/agent-skills](https://github.com/apify/agent-skills).
48	Quick answer: `bash scripts/run-actor.sh "actor/id" '{"input":"json"}'`
49	Export: `bash scripts/run-actor.sh "actor/id" '{"input":"json"}' --output /tmp/out.csv`
50	- `jina.sh` — `read <url>` \| `search <query>` \| `deepsearch <query>`
51	- `parallel.sh` — `search <query>` \| `extract <url>`
52	- `brightdata.sh` — `scrape <url>` \| `scrape-batch` \| `search` \| `search-geo <cc>` \| `search-yandex`
53
54	## Research Escalation Flow
55
56	Принцип: от дешёвого к дорогому, от быстрого к глубокому.
57
58	### Level 1: Quick Answers (секунды, ~$0.00)
59	Начни ВСЕГДА с этого. Получи быстрый контекст прежде чем копать.
60	Запускай ВСЕ параллельно:
61	```bash
62	# Perplexity (default: MCP tool, not the shell script)
63	# Claude call: mcp__perplexity-ask__perplexity_ask with a structured prompt
64	# (see "Prompt Templates" section — use the Entity Profile template, not ad-hoc "Who is X")
65	# Shell fallback (bash pipelines or when you need sonar explicitly):
66	# bash skills/osint/scripts/perplexity.sh sonar "<structured prompt from Entity Profile template>"
67	# Brave Search — классический поиск
68	web_search "<Name> <company> <role>"
69	# Tavily — agent-optimized search с AI answer
70	bash skills/osint/scripts/tavily.sh search "<Name> <context>"
71	# Exa — семантический поиск + company/people research
72	bash skills/osint/scripts/exa.sh search "<Name> <context>"
73	bash skills/osint/scripts/exa.sh people "<Name>"
74	```
75	→ Получаешь: быстрые факты, ссылки, контекст.
76	→ Решение: достаточно? → Phase 6. Нужно больше? → Level 1.5.
77
78	### Level 1.5: Breach Intel (free, run before any social scraping)
79
80	HudsonRock Cavalier -- unauthenticated, instant, often CRITICAL. Run this immediately after Level 1 before spending

People who liked this also viewed

6 picks

Type

osint

47stars4forks

View on GitHub

How to install osint?

assafkip/huntkit/osint

$npx -y skills add assafkip/huntkit --skill osint

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# OSINT Skill v3.2
2
3	Systematic intelligence gathering on individuals. From a name or handle to a scored
4	dossier with psychoprofile, career map, and entry points.
5
6	## Phase Router
7
8	Determine entry point from context:
9
10	- New name/handle/URL, "пробей", "find out about" → Phase 0 (full cycle)
11	- "Add LinkedIn/Instagram data" to existing dossier → Phase 2 (extraction)
12	- "Build psychoprofile" from existing data → Phase 4
13	- "Rate completeness" of existing dossier → Phase 5
14	- "Reformat" or "present" findings → Phase 6
15
16	Default (full research request): Phase 0 → 1 → 1.5 → 2 → 3 → 4 → 5 → 6.
17
18	## Environment
19
20	All API keys via environment variables. Never hardcode tokens.
21
22	- `PERPLEXITY_API_KEY` — Perplexity Sonar (fast answers + deep research)
23	- `EXA_API_KEY` — Exa AI (semantic search, company/people research, deep research)
24	- `TAVILY_API_KEY` — Tavily (agent-optimized search + extract, $0.005/req basic)
25	- `APIFY_API_TOKEN` — Apify scraping (LinkedIn, Instagram, Facebook)
26	- `JINA_API_KEY` — Jina reader/search/deepsearch
27	- `PARALLEL_API_KEY` — Parallel AI search
28	- `BRIGHTDATA_MCP_URL` — Bright Data MCP endpoint (full URL with token)
29	- `MCPORTER_CONFIG` — mcporter config path
30
31	## Scripts
32
33	Run from skill dir: `bash scripts/<name>.sh`.
34	Each script validates env vars, exits with descriptive error + URL to get the key.
35
36	Search & Research:
37	- `diagnose.sh` — run FIRST. Capability map of all tools.
38	- Perplexity (first-pass default): when operating through Claude, call the MCP tool `mcp__perplexity-ask__perplexity_ask` directly. It returns an AI answer with citations (equivalent to `sonar` mode). Use the shell script for `search` (ranked web results), `reason` (reconcile contradictions), and `deep` (long-form research) modes, or from bash pipelines.
39	- `perplexity.sh` — `search <query>` \| `sonar <query>` (AI answer) \| `reason <query>` (sonar-reasoning-pro, compare leads / reconcile contradictions) \| `deep <query>` (deep research). Required by `first-volley.sh` and any bash-only pipeline.
40	- `tavily.sh` — `search <query>` (basic $0.005) \| `deep <query>` (advanced) \| `extract <url>`
41	- `exa.sh` — `search <query>` \| `company <name>` \| `people <name>` \| `crawl <url>` \| `deep <prompt>`
42	- `first-volley.sh "Name" "context"` — parallel search, all engines at once.
43	- `merge-volley.sh <outdir>` — deduplicate and merge first-volley results.
44
45	Scraping:
46	- `apify.sh` — `linkedin <url>` \| `instagram <handle>` \| `run` \| `results` \| `store-search`
47	- `run-actor.sh` — universal Apify runner (55+ actors). Embedded from [apify/agent-skills](https://github.com/apify/agent-skills).
48	Quick answer: `bash scripts/run-actor.sh "actor/id" '{"input":"json"}'`
49	Export: `bash scripts/run-actor.sh "actor/id" '{"input":"json"}' --output /tmp/out.csv`
50	- `jina.sh` — `read <url>` \| `search <query>` \| `deepsearch <query>`
51	- `parallel.sh` — `search <query>` \| `extract <url>`
52	- `brightdata.sh` — `scrape <url>` \| `scrape-batch` \| `search` \| `search-geo <cc>` \| `search-yandex`
53
54	## Research Escalation Flow
55
56	Принцип: от дешёвого к дорогому, от быстрого к глубокому.
57
58	### Level 1: Quick Answers (секунды, ~$0.00)
59	Начни ВСЕГДА с этого. Получи быстрый контекст прежде чем копать.
60	Запускай ВСЕ параллельно:
61	```bash
62	# Perplexity (default: MCP tool, not the shell script)
63	# Claude call: mcp__perplexity-ask__perplexity_ask with a structured prompt
64	# (see "Prompt Templates" section — use the Entity Profile template, not ad-hoc "Who is X")
65	# Shell fallback (bash pipelines or when you need sonar explicitly):
66	# bash skills/osint/scripts/perplexity.sh sonar "<structured prompt from Entity Profile template>"
67	# Brave Search — классический поиск
68	web_search "<Name> <company> <role>"
69	# Tavily — agent-optimized search с AI answer
70	bash skills/osint/scripts/tavily.sh search "<Name> <context>"
71	# Exa — семантический поиск + company/people research
72	bash skills/osint/scripts/exa.sh search "<Name> <context>"
73	bash skills/osint/scripts/exa.sh people "<Name>"
74	```
75	→ Получаешь: быстрые факты, ссылки, контекст.
76	→ Решение: достаточно? → Phase 6. Нужно больше? → Level 1.5.
77
78	### Level 1.5: Breach Intel (free, run before any social scraping)
79
80	HudsonRock Cavalier -- unauthenticated, instant, often CRITICAL. Run this immediately after Level 1 before spending

People who liked this also viewed

6 picks

Type