4,034 件 ・ 関連度順
概要と使いどころ
Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search. Use PROACTIVELY for vector search implementation, embedding optimization, or semantic retrieval systems.
日本語の概要は準備中です。原文の説明を表示しています。
Specialized skill for testing file system operations using System.IO.Abstractions. Use when you need to test File, Directory, Path operations, or simulate file system. Covers IFileSystem, MockFileSystem, file read/write testing, directory operation testing, etc. Keywords: file testing, filesystem, file testing, file system testing, IFileSystem, MockFileSystem, System.IO.Abstractions, File.ReadAllText, File.WriteAllText, Directory.CreateDirectory, Path.Combine, mock file system, file abstraction
日本語の概要は準備中です。原文の説明を表示しています。
Executes authorized attack simulations against Active Directory environments to identify misconfigurations, weak credentials, dangerous privilege paths, and exploitable trust relationships that could lead to domain compromise. The tester uses BloodHound for attack path analysis, Mimikatz for credential extraction, and Impacket for protocol-level attacks including Kerberoasting, AS-REP Roasting, and delegation abuse. Activates for requests involving Active Directory pentest, AD attack simulation, domain compromise testing, or Kerberos attack assessment.
日本語の概要は準備中です。原文の説明を表示しています。
Detect DCSync attacks where adversaries abuse Active Directory replication privileges to extract password hashes by monitoring for non-domain-controller accounts requesting directory replication via DsGetNCChanges.
日本語の概要は準備中です。原文の説明を表示しています。
Sets up vector databases for semantic search including Pinecone, Chroma, pgvector, and Qdrant with embedding generation and similarity search. Use when users request "vector database", "semantic search", "embeddings storage", "Pinecone setup", or "similarity search".
日本語の概要は準備中です。原文の説明を表示しています。
Audit or design server-side indexes, directories, reputations, or aggregates that are DERIVED from traffic a platform witnesses (chain heads, run verdicts, heartbeats, publish activity) so that consent gates the derivation, not merely the read: no shadow index over non-consenting principals, post-consent-only evidence windows, retention bounds and delete-propagation into derived rows, activity-oracle threat modeling, and audit-logged ranking discretion. Use when building a capability directory / whois from witnessed activity, a reputation ledger from settled outcomes, vitals aggregation across tenants, or any "the yellow pages can't lie because they index signatures" feature. Keywords: shadow index, derived index, consent gates derivation, activity oracle, phone book not a log, delist propagation, ranking weight audit, k-anonymous aggregate, subpoena surface. NOT for the consent-screen UX and scope-ladder mechanics themselves (use local-first-tenancy-boundary), reputation scoring math and Sybil economics (use agent-identity-continuity-reputation), or discovery-layer architecture L1/L2/L3 (use agent-discovery-directories-guilds).
日本語の概要は準備中です。原文の説明を表示しています。
Prepare MCP/vendor integrations through cited research, a content PR, exact-revision human approval, and one governed Paperclip connector PR per approved connection. Use for new integration research and delivery; not for ad hoc connector coding that bypasses the playbooks.
日本語の概要は準備中です。原文の説明を表示しています。
The shared Claude Docs viewer — an artifact TYPE. An artifact made from it is a doc: a live document that people and Claude read and edit together (people may also call it a page). The doc's content does not live in this artifact's files at all — it lives in the Claude Docs service and is read and written ONLY through the Claude Docs connector (its create, batch, read and update tools). Read this before touching such an artifact: it says what the files are, that an instance owns none of its own, how to change what the doc says (the connector, never a publish), and where a comment on the doc — including one sent to you from it — is read and answered (the connector's comment verbs; never these files, never the artifact's comment relay).
日本語の概要は準備中です。原文の説明を表示しています。
Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
日本語の概要は準備中です。原文の説明を表示しています。
Detect DCSync attacks (MITRE T1003.006) where adversaries abuse Active Directory replication privileges to extract password hashes, by auditing Event ID 4662 for the DS-Replication-Get-Changes GUIDs and flagging non-domain-controller accounts issuing DsGetNCChanges RPC calls. Use when hunting for credential theft via Mimikatz lsadump::dcsync or Impacket secretsdump, investigating lateral movement with domain admin credentials, or auditing AD replication permissions.
日本語の概要は準備中です。原文の説明を表示しています。
Deploys deception-based honeytokens in Active Directory including fake privileged accounts with AdminCount=1, fake SPNs for Kerberoasting detection (honeyroasting), decoy GPOs with cpassword traps, and fake BloodHound paths. Monitors Windows Security Event IDs 4769, 4625, 4662, 5136 for honeytoken interaction. Use when implementing AD deception defenses for detecting lateral movement, credential theft, and reconnaissance.
日本語の概要は準備中です。原文の説明を表示しています。
Implement Microsoft's Enhanced Security Admin Environment (ESAE) tiered administration model for Active Directory, covering Tier 0/1/2 separation, privileged access workstations (PAWs), administrative forest design, and authentication policy silos. Use when designing or hardening AD privileged-access architecture, segmenting Domain/Enterprise Admin accounts into tiers, or containing lateral movement and credential theft (pass-the-hash, Kerberoasting, golden tickets).
日本語の概要は準備中です。原文の説明を表示しています。
Conduct internal Active Directory reconnaissance using BloodHound Community Edition's graph database with the SharpHound (AD) and AzureHound (Entra ID) collectors, mapping ACLs, sessions, and group memberships into attack paths from a low-privileged foothold to Domain Admin. Use after an initial AD foothold to identify privilege escalation chains, or to validate that AD hardening closed known attack paths.
日本語の概要は準備中です。原文の説明を表示しています。
Build dumb-pipe and traffic-filtering C2 redirectors with nginx (proxy_pass) and Apache (mod_rewrite), deriving filter rules from a Malleable C2 profile, layering Let's Encrypt TLS, and applying OPSEC controls like domain fronting and UA/geo filtering. Use when standing up red-team C2 that must survive blue-team triage or ensuring only profile-matching implant traffic reaches the hidden team server.
日本語の概要は準備中です。原文の説明を表示しています。
Auditing Microsoft Entra ID (Azure Active Directory) configuration to identify risky authentication policies, overly permissive role assignments, stale accounts, conditional access gaps, and guest user risks using AzureAD PowerShell, Microsoft Graph API, and ScoutSuite.
日本語の概要は準備中です。原文の説明を表示しています。
Detect dangerous ACL misconfigurations in Active Directory using ldap3 to identify GenericAll, WriteDACL, and WriteOwner abuse paths
日本語の概要は準備中です。原文の説明を表示しています。
Reads a forwarded customer email or ticket, pulls order and refund status from a payments connector (PayPal, Square, or Stripe) or Shopify, account history from the CRM, and open tickets from a support desk (Zoho Desk), drafts a tone-matched reply in the owner's writing voice, and can issue a refund through the payments connector with explicit owner approval. With Shopify connected it also runs a proactive order-triage mode that surfaces orders needing attention — unfulfilled past the promised window, payment problems, pending refunds, stuck shipments — and drafts the next action for each before the customer has to ask. Use when the user says "draft a response," "answer this customer," "where's my order," "I want a refund," "check my orders," or "anything about to blow up."
日本語の概要は準備中です。原文の説明を表示しています。
Planificación persistente basada en archivos para tareas multipaso de agentes de IA. Mantiene task_plan.md, findings.md y progress.md en disco; los hooks del ciclo de vida inyectan contexto seleccionado de planificación del proyecto. La recuperación automática solo lee los archivos de planificación del proyecto. session-catchup.py --metadata, solicitado de forma explícita, puede inspeccionar metadatos locales de sesiones del mismo proyecto; --replay puede emitir extractos limitados y enmarcados con nonce. El modo con gate opcional solo puede solicitar que el host continúe si este lo admite y nunca ejecuta comandos declarados en Markdown. El skill no tiene ninguna ruta de carga por red. Úsalo para investigación o trabajo que requiera 5 o más llamadas a herramientas.
日本語の概要は準備中です。原文の説明を表示しています。
Discovers requirements, and generates architectural, design, and deployment guidance for a retrieval-augmented generation (RAG)-capable enterprise search system in Google Cloud. Use when users need a vector-enabled SQL database as the store and index for the embedding vectors, an open model and open-source inferencing framework, and Kubernetes containers to host all the application components. DON'T use this skill for fully-managed RAG, or SaaS search services, or when a non-SQL vector database is required.
日本語の概要は準備中です。原文の説明を表示しています。
The continual-harness refinement protocol — how an agent inspects its recent trajectory for failure signatures and improves its own harness (agent prompts, sub-agents, skills, memory) in place, mid-session, landing changes on the session branch immediately and promoting them to `main` only through a change request. Load this skill when a refinement prompt arrives mid-session, when the `harness-reflector` agent runs, or whenever you decide your own scaffolding needs repair. The sub-agent fan-out in this skill is for the top-level `harness-reflector` run only; if you loaded this as a subagent, do the four passes yourself and skip the fan-out.
日本語の概要は準備中です。原文の説明を表示しています。
How to reach a user's CONNECTED COMPUTER (their laptop, desktop, or server) from a Kortix session — read/write files, run shell commands, and drive the desktop (click/type/screenshot) on that machine. A connected computer is an ACCOUNT of the project's `computer` connector, called through the same `kortix connectors` path as every other connector, with `--account` picking the machine. Load this when the task is about acting ON a specific physical computer the user has connected ("on my laptop…", "read ~/Downloads on my machine", "run this on my desktop", "click the button on my screen"), or when the user asks how the agent reaches their computer. ALSO load it when the user mentions their own machine or its files and no computer may be connected yet ("my local files", "my Desktop", a path like `~/…`, `/Users/…`, "the repo on my laptop") — this sandbox cannot see their disk, and the skill says how to tell them to connect it. For files INSIDE this sandbox, use normal shell/fs — not this.
日本語の概要は準備中です。原文の説明を表示しています。
Use Kortix connectors to reach external systems from a session, an App, a Convex backend, or an external program. Use the `kortix connectors` CLI for agent work, `@kortix/sdk` for durable TypeScript workflows and for App, backend, and script code, and the hosted Kortix MCP server (`<api>/v1/mcp`) for an MCP client outside Kortix. Load this skill to inspect, add, connect, or call external tools without exposing third-party credentials to the sandbox, an App, or a backend.
日本語の概要は準備中です。原文の説明を表示しています。
Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious.
日本語の概要は準備中です。原文の説明を表示しています。
Add a new built-in OpenWiki source connector. Use when a user asks to create or implement an OpenWiki connector.
日本語の概要は準備中です。原文の説明を表示しています。