thiefdroppers/cyber-investigator-skills / ai-agent-skills
cyber-investigator
VerifiedRuns the OSINT, threat-intelligence-pivot, and fraud and scam pattern methodology from the Cyber Investigator Roadmap. Use when asked to research a threat, scam, or fraud pattern, triage a suspicious case, run an OSINT recon cycle, build a link-analysis graph, check whether a scam or phishing message was machine-generated, or draft an intelligence brief or case report. Authorized, defensive, lawful scope only.
| File | Kind | Size |
|---|---|---|
| PORTABLE_PROMPT.md | markdown | 4.9 KB |
| SKILL.md | skill md | 10.1 KB |
| reference/fraud-pattern-taxonomy.md | markdown | 3.2 KB |
| reference/osint-methodology-checklist.md | markdown | 1.7 KB |
reference/osint-methodology-checklist.md
View on GitHub# OSINT recon checklist
The recon cycle from [`SKILL.md`](../SKILL.md) as a checklist you can print. The cycle starts on [Day 19](../../curriculum/phase-2-osint-digital-footprint/day-19.md); [Day 22](../../curriculum/phase-2-osint-digital-footprint/day-22.md) applies it in a Maltego link-analysis lab. [`worksheets/osint-recon-log.md`](../../worksheets/osint-recon-log.md) is the matching log.
## Plan
- [ ] Question written as one specific sentence
- [ ] Authorization or case context confirmed
- [ ] Out-of-scope people, accounts, and systems named
## Collect
- [ ] At least 3 independent source types used (for example WHOIS and DNS, search engines, official records, archived snapshots)
- [ ] Every data point logged with its value, source, and access date and time
- [ ] Historical state checked in the Wayback Machine or a similar archive for anything that looks recently changed
## Process and graph
- [ ] Nodes are concrete entities (domain, IP, certificate, email address, account, organization), never categories
- [ ] Every edge labeled with the relationship that produced it, such as "same registrant email" or "shared TLS certificate"
- [ ] Hubs, clusters, and bridges identified, with the reason each one is connected
- [ ] Shared infrastructure checked before treating a hub as significant (a hosting provider or CDN connects thousands of unrelated sites)
## Analyze
- [ ] Each finding tagged confirmed (2 or more independent sources agree), likely (1 source), or disputed (sources conflict)
- [ ] Contradictions recorded, not dropped
## Report
- [ ] Confidence words match the analysis tags exactly
- [ ] Every claim traces to an entry in the collection log
- [ ] Unverified items labeled as unverified
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |