573건 · 관련도순
AI integration review patterns. Use when reviewing model API calls, prompt construction, LLM output handling, RAG pipelines, and tool-calling code. Covers prompt-injection call-chain tracing, output validation, stop reasons, token budgets, retry and timeout handling, streaming, and key/PII exposure.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
LLM observability with Langfuse — OpenTelemetry-based tracing, evaluations, prompt management, datasets, and production best practices
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Study unfamiliar codebases and produce evidence-backed knowledge artifacts. Use for repository orientation, architecture mapping, subsystem tracing, onboarding, or codebase documentation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when writing or reviewing request handlers, RPCs, or background jobs for production; adding tracing, metrics, or structured-log calls; or making diagnosability decisions
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Analyze and detect synthetic media, including deepfake videos, AI-generated images, and cloned voice audio. Use this skill when investigating potential disinformation campaigns, verifying the authenticity of digital evidence, or assessing social engineering attacks leveraging synthetic media (e.g., vishing with voice clones, spear-phishing with deepfake video calls). Covers artifact analysis, frequency detection, metadata tracing, and automated detection tools.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
White-box source code security review structured around OWASP ASVS 5.0 (427 verification requirements across 16 chapters). Reads and understands application source code to build a security-aware knowledge base that enriches all downstream skills. Covers: tech stack identification, route/endpoint mapping, authentication and authorization architecture, dangerous function patterns, source-to-sink data flow tracing, IaC review, dependency analysis, ASVS compliance mapping, and LLM integration security (prompt injection, tool abuse, output handling, RAG poisoning, MCP server patterns). When LLM/AI framework usage is detected, automatically reviews OWASP LLM Top 10 patterns from source code and chains into /ai-redteam with white-box context for live endpoint testing. Chains into /pentester, /threat-modeling, /web-exploit, /api-security, /cloud-security, /analyze-cve, /credential-audit, and /ai-redteam — providing white-box context that transforms black-box testing into targeted, informed assessment.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Analyzes CVE vulnerabilities in project dependencies with code path tracing and PoC generation for Burp Suite. Traces vulnerable code from user input to sink, assesses exploitability, and generates HTTP requests for testing.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
This repo is indexed by graft/. For ANY task here, whether understanding how something works, finding where code lives, tracing what calls a symbol or what a change breaks, or scoping an edit, get your context from graft before grepping or reading source files.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Investigate stuck runs and execution failures by tracing Symphony and Codex logs with issue/session identifiers; use when runs stall, retry repeatedly, or fail unexpectedly.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reverses .NET/managed malware: decompiling MSIL back to C#, defeating common .NET protectors and string encryptors, and tracing reflection-based loaders to recover the real payload. Activates for requests to analyze a .NET sample, decompile MSIL, or unpack a managed loader.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of a dental assistant — sequencing instrument transfer during a procedure, troubleshooting a retake-worthy radiograph before re-exposing the patient, tracing a failed sterilization-cycle indicator back to the affected instrument batches, or timing a chairside material mix against its working-time window across multiple prepped teeth.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of a Commercial and Industrial Electronics Repairer — diagnosing a VFD fault trip on a production line, tracing a PLC I/O fault back to the sensor, the wiring, or the ladder logic, selecting arc-flash PPE for live-panel diagnostic work, triaging multiple simultaneous down-lines by downtime-cost-per-hour, or deciding drive/board swap versus component-level repair.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of a Coating/Painting/Spraying Machine Operator — calculating wet film thickness from a target dry film thickness and the coating's percent volume solids, deciding whether flash-off time can be shortened to increase throughput, verifying cure by actual part temperature rather than oven setpoint, or tracing an adhesion failure back to surface prep rather than the coating application.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of a systems engineer/architect working at the whole-program level — decomposing requirements across hardware/software/network subsystems, writing or reviewing an interface control document (ICD), making a build-vs-buy tradeoff for a subsystem, or tracing a verification failure back through the requirements baseline. Distinct from a software engineer (owns one service's code) or DevOps/SRE (owns operational reliability) — this role owns the technical baseline for a whole system-of-systems and is accountable when subsystems built by different teams or vendors don't fit together.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of a Calibration Technologist/Technician — computing a Test Uncertainty Ratio (TUR) and deciding whether it meets the 4:1 target, building a measurement uncertainty budget (Type A/Type B, GUM-style) for a calibration, tracing a reference standard's chain of custody to NIST/SI, setting or adjusting a calibration interval from in-tolerance/out-of-tolerance history, or writing the accept/reject call and guard-banded pass/fail on a calibration certificate.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of a Bookkeeping, Accounting, and Auditing Clerk — reconciling a bank or credit card account, resolving an AP three-way-match discrepancy before payment, coding an expense to the correct account and department, tracing a general ledger discrepancy to root cause, or running a month-end close checklist.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of a Baker — scaling a formula using baker's percentages to hit an exact batch weight, diagnosing whether a fermentation problem traces to dough temperature or mixing development, judging proof readiness from a poke test rather than a fixed clock, or tracing a poor-oven-spring result back to over- or under-proofing instead of the oven.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of an Aerospace Engineer — reconciling a vehicle mass/weight budget against a certification limit, computing a structural margin of safety, choosing a means of compliance for an FAA certification basis, tracing a weight-growth overrun back to a design decision, or evaluating a propulsion/aerodynamics tradeoff against a range or payload requirement.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Autonomous human-like browser control and professional QA/QC testing. Powered by agent-browser (Rust native CDP, zero Playwright) with ISTQB test matrix generation, automated testcase execution, console/network error tracing, and defect reporting.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Analyze existing KiCad projects, schematics, PCB layouts, Gerbers, netlists, and PDF reference schematics. Use when files such as .kicad_sch, .kicad_pcb, .kicad_pro, or Gerbers are supplied and the user wants review, debugging, net tracing, ERC/DRC/DFM, schematic-to-PCB comparison, or pre-fabrication checks. Do not use to create a new design from requirements or for standalone sourcing and ordering.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Transform reference photographs and visually dense images into sparse, recognizable, high-saturation flat-vector-style illustrations through semantic compression rather than literal tracing. Use when the user asks for photo-to-flat illustration, photo-to-vector-style redraw, 照片转扁平插画, 无渐变高饱和插画, iconification, visual simplification, composition-preserving abstraction, a consistent minimal illustration set, or revisions that remove gradients, glow, texture, blur, clutter, text, logos, numbers, or UI. Default to human-perceived semantic complexity 6 out of 10 or lower, fixed-HSB solid fills, crisp boundaries, and no gradients or light-halo effects.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Verify code-review or security-review findings for false positives using deep codebase tracing, framework-aware analysis, and web research. Produces a .verified.md report alongside the original. Use when a review report has been generated and needs independent verification, or when user runs /verify-findings, mentions "verify review", "check false positives", or "validate findings".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Spring Boot 4 observability with Actuator, Micrometer, and OpenTelemetry. Use when configuring health indicators, health checks, custom metrics, distributed tracing, production endpoint exposure, Kubernetes probes, Cloud Run probes, logging, or monitoring. Covers Actuator endpoint security, Micrometer Timer/Counter/Gauge patterns, OpenTelemetry span customization, liveness/readiness probe setup, and metric tag best practices.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.