coordinate-external-ag…
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Observe suspicious content in a disposable environment. Use when execution, process ancestry, file changes, persistence, network behavior, payloads, or user interaction need measurement after static analysis with isolation and teardown.
$ npx -y skills add gaelic-ghost/socket --skill perform-dynamic-malware-analysis --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/perform-dynamic-malware-analysisContext preview
The summary Claude sees to decide when to auto-load this skill.
Observe suspicious content in a disposable environment. Use when execution, process ancestry, file changes, persistence, network behavior, payloads, or user interaction need measurement after static analysis with isolation and teardown.
name: perform-dynamic-malware-analysis description: Observe suspicious content in a disposable environment. Use when execution, process ancestry, file changes, persistence, network behavior, payloads, or user interaction need measurement after static analysis with isolation and teardown.
Execute only inside an environment chosen by `select-analysis-isolation` and preflighted by `prepare-isolated-analysis-lab`, with an observation plan that can distinguish artifact behavior from baseline noise. Preserve the exact sample, prepared-lab record, and environment identity.
Read [references/dynamic-observation-plan.md](references/dynamic-observation-plan.md) for baseline, stimulus, telemetry, and teardown fields.
1. Define the unresolved question and minimum stimulus. 2. Verify isolation.
3. Capture a baseline.
4. Execute one controlled step.
5. Observe behavior.
6. Repeat only to answer a named question.
7. Export and tear down.
Return the prepared-lab identity, environment/baseline identity, stimulus, observed timeline, artifacts and indicators, absent expected behavior, virtualization/evasion/coverage limits, conclusion, and teardown verification.
Stuff for Agents on macOS Promo audio: Socket Codex Marketplace Promo
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Assign worktree, branch, write, validation, integration, and cleanup ownership before parallel repository work. Use when a worker will inspect or modify…
Design framework-neutral agent and automation workflows before implementation. Use when choosing between Codex app automations, codex exec, Codex subagents,…
Design evaluation workflows for agent, skill, prompt, and automation behavior before implementation. Use when choosing eval cases, graders, thresholds,…
Design safe n8n workflows with deterministic routing, credentials, idempotency, recovery, local-model checks, drafts, and exact approval gates.
Coordinate bounded worker tasks with a launch envelope, report-back, escalation, and synthesis contract. Use before spawning, resuming, steering, cancelling,…