Compatibility entry for remote GPU resource management. Follow the project-local manage-remote-resources lifecycle skill; GPU inference readiness is a workload-specific reference.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Read and follow manage-remote-resources for provisioning, budgets, ownership, credentials, supervision and teardown. It applies to CPU hosts and attached resources as well as GPUs.
For hosted inference or a co-located judge, also read GPU inference readiness. For a batch campaign, use run-ephemeral-hosts. This compatibility entry grants no additional authority.
Choose the service using service selection and security admission; for AWS GPU VMs or Batch, use the AWS operating runbook. Verify actual accelerator memory, architecture, driver/runtime compatibility and job-level device access before admitting inference work.
Read custody mechanics and the canonical secrets contract linked there.
Read the canary procedure when credentials land on a host.
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Plan and use user-consented local camera and microphone observations for an explicitly authorized physical target. Use when a capture can establish a bounded physical-state observation such as whether a test fixture changed state, an instrument reading changed, or equipment noise changed relatively.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Plan vulnerability research using conventional bug-hunting and pentest stage names, specialty playbooks, and a research-hypothesis-experiment loop. Use when designing a bug bounty workflow, selecting tools and strategies, building a decision tree, or turning a target/scope into a staged hunting plan.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Passive code-review lane for authorized repositories, local checkouts, uploaded source archives, and diffs. Use when the security research agent needs deterministic candidate discovery before expensive AI investigation, scoped PR-style review, append-only evidence records, or independent revalidation of code findings.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Run independent, task-matched expert attempts, select a base, and synthesize the strongest result.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Select established CTF and security-research tools for authorized artifact triage, web inspection, reversing, crypto, forensics, networking, and exploit validation. Use when a user provides a CTF-style tool catalog, asks which tools to use, or needs safe usage instructions for common offensive/security tools.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.