1,830 件 ・ 関連度順
概要と使いどころ
LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments
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。
Produce a high-confidence, CONCISE implementation / architecture / strategy PLAN that follows the OMC plan system end to end. It first runs OMC's real requirements interview (auto-chains the `omc-plan` skill: one question at a time, explore-first, Analyst consult) to produce an initial plan in `.omc/plans/`, then DEEPENS that plan with a 3-round ITERATIVE fusion loop — each round an Opus 4.8 panelist (Agent subagent) and a GPT-5.5 panelist (via codex) critique/improve it IN PARALLEL and BLIND, then Opus 4.8 (the orchestrator) judges and synthesizes one tighter plan that seeds the next round, stopping early on convergence. Writes the final dense plan back to the same `.omc/plans/<slug>.md`, then offers the OMC handoff (`/omc-plan --review` → `/team` or `/ralph`). Use for high-stakes planning, architecture decisions, strategy calls, and hard debugging — especially when the user runs /plan or asks how to approach a non-trivial build. Reuses the `fusion` skill's run_codex.sh + judge rubric. NOT for trivial tasks (single pass is enough).
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。
做机构级研究报告与学术论文——行业报告、白皮书、年度调研、数据洞察、arXiv论文，也含16:9咨询deck型报告（一页一结论）。定结构、写发现、建图表视觉系统。规范提炼自2026年顶级机构报告实测。单篇文章、纯演示PPT不适用（走design/slides）。
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 when reviewing, designing, or modifying Java enterprise systems from a maintainer-authored or maintainer-sanitized NIS2 engineering evidence inventory. Supports essential or important entities, critical-sector services, managed service providers, supply-chain dependencies, and cybersecurity incident escalation obligations without ingesting raw code, logs, runbooks, tickets, provider documents, or other operational free text. Part of Plinth Toolkit
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 when you need to design, review, or improve security in Spring Boot applications — including SecurityFilterChain, OAuth2/JWT resource server patterns, form login basics, method security (@PreAuthorize), CSRF and CORS for APIs, session fixation, security headers, exception handling, password encoding, and sensitive-data-safe logging. This should trigger for requests such as Add Spring Boot security support; Review Spring Boot security configuration; Improve API authorization in Spring Boot; Add JWT resource server security in Spring Boot; Harden Spring Boot security headers and CSRF settings. Part of Plinth Toolkit
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。
Security: review git changes for vulnerabilities, threat-model a system's attack surface, audit supply-chain risks.
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。
数据分析全流程：体检脏表、清洗、定口径、算指标、对账、出报告。处理 Excel/CSV/系统导出数据，做透视写公式，查两个数为什么对不上，判断一个数靠不靠谱时用。核心是让算出来的数字经得起追问。幻灯片和 PPT 交给 huashu-design。
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。
Email operations skill for sending, fetching, and reading emails via IMAP/SMTP. Uses curl with OpenSSL/LibreSSL for reliable TLS compatibility with Tencent Enterprise Mail and other providers. Credentials are securely stored in macOS Keychain.
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 when ready to document findings, generate a report, or summarize binary analysis results. Compiles analysis findings into structured reports - correlates facts from triage/static/dynamic phases, validates hypotheses, generates documentation with evidence chains. Keywords - "summarize findings", "generate report", "document analysis", "what did we find", "write up results", "export findings"
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 when reverse engineering tools are missing, not working, or need configuration. Installation guides for radare2 (r2), Ghidra, GDB, QEMU, Frida, binutils, and cross-compilation toolchains. Keywords - "install radare2", "setup ghidra", "r2 not found", "qemu missing", "tool not installed", "configure gdb", "cross-compiler"
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。
Re-ingest-correctness SOP for production RAG. Activate when a calling agent builds, reviews, or debugs an ingestion pipeline that runs more than once over a changing corpus — scheduled re-index, incremental updates, CI re-ingest, or a "retrieval has duplicates / shows deleted docs" bug. Encodes the rule — **ingestion must be idempotent: a document's content hash decides insert/update/skip, so re-running over unchanged docs is a no-op** — plus the docstore + doc-hash upsert machinery (LlamaIndex `IngestionPipeline` + `DocstoreStrategy`), the delete-propagation problem, and cross-framework equivalents (LangChain `index()` + `RecordManager`, manual hash table). ENHANCE overlay over [[llamaindex]]: the IngestionPipeline exists in the base skill but the re-ingest-correctness contract is not surfaced.
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。
Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call. The load-bearing premise: the *tool surface* is an LM-friendly subset of the *API surface* — one tool per user intent, not one per endpoint. Activates when a coder agent must expose an external HTTP API to a model (function calling, tool_use, MCP, LangChain `@tool`, CrewAI `BaseTool`). Encodes the *what to surface, how to name, how to shape, how to fail* — not any single framework's API. ~80% of agent tools in production are HTTP wrappers; this is the SOP for getting them right.
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。
Enhancement-overlay decision protocol for STREAMING the output of long-running LLM / agent runs from the *backend*, not just wiring a typing animation in the UI. Activates when a coder agent must stream final tokens to a chat client, surface intermediate agent steps (which tool, which node, partial reasoning), emit custom tool-progress events, choose a transport (SSE vs WebSocket), or decide what to do when the client disconnects mid-stream. The langchain / langgraph skills mention stream modes but stop at "you can stream"; this skill encodes *what to stream, over what transport, and how to fail safely*.
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。
Decision protocol for building, debugging, and operating LangGraph-based agent systems. Activates when a coder agent is asked to design a stateful LLM workflow, add human-in-the-loop, choose a multi-agent pattern (supervisor / swarm / hierarchical), pick a checkpoint backend, or migrate a fragile chain into a durable graph. LangGraph is positioned by its maintainers as a "low-level orchestration framework for building, managing, and deploying long-running, stateful agents" — this skill encodes the *when* and *why*, not the API.
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。
Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query engines, routers, agents), or pick LlamaIndex vs LangChain / Haystack / raw vector store for a coding task. Encodes the 5-layer mental model (Documents → Nodes → Indices → Retrievers → Query Engines / Response Synthesizers), the canonical RAG bootstrap SOP from baseline `VectorStoreIndex` through hybrid + reranker + eval-loop hardening, the official 13-failure-mode checklist, and 5 dilemma cases distilled from docs, GitHub issues, and 2025 production post-mortems.
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。
Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph, LlamaIndex, DSPy, CrewAI, vLLM, Aider, Dify) into one layered rubric. Core stance: frameworks are LAYERS, not competitors — a real project usually combines DSPy (compile) + LlamaIndex (retrieve) + LangGraph (orchestrate) + vLLM (serve), and you choose ONE per layer, not one to rule all. Use when starting any LLM/agent/RAG project, or whenever the "which framework?" question is asked. Deliberately neutral — unlike vendor docs and the LangChain-biased `framework-selection` on skill.sh, this skill has no horse in the race.
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。
Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover. Each of those installs one backend; none of them help you DECIDE which backend fits your stack/scale/budget, nor give you a one-line autolog that turns it on fast. Use when starting any LM project, before the first deploy, or the moment someone asks "why did it do that?" and there are no traces to answer with. The skill picks a backend by stack (LangSmith for LangChain/LangGraph; Phoenix for OSS/local OpenTelemetry; MLflow for ML-shops already on MLflow; Langfuse for self-host), wires one-line autolog, verifies traces land, and adds eval hooks — instrumenting BEFORE you need it. Cross-links the first-debug-move skill [[agentsop-prompt-history-inspect]]. Do NOT activate to re-teach a backend you already chose (defer to its own skill), or for non-LM ML experiment tracking with no LLM calls (that is plain MLflow).
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。
Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Activate when the user says any of: "use DSPy", "compile a prompt", "optimize prompts/programs", "MIPRO/MIPROv2", "BootstrapFewShot", "GEPA", "Signatures + Modules", "teleprompter", "auto-tune prompts for a different LM", or whenever a brittle hand-crafted prompt pipeline needs to be turned into a *compiled*, measurable, swappable program. Do NOT activate for one-shot prompt tweaks, no-metric exploratory work, or pipelines where prompts must remain human-authored verbatim — use raw prompting or LangChain templates instead.
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。
Tool skill — the *first move* in any LM-debugging session: dump the actual rendered prompt the framework sent to the model, before changing anything else. Activate when an LM call produced an unexpected output (wrong answer, schema violation, refusal, truncation, cost spike, latency spike, infinite loop, "model got dumber after upgrade"). The skill enforces a 30-second inspect step BEFORE any prompt edit, model swap, retry, or temperature tweak. Cross-framework cheat sheet: DSPy `inspect_history`, LangGraph `get_state_history`, CrewAI `step_callback`, LangChain `set_debug`/`set_verbose`, Aider `/diff`+`--verbose`, raw OpenAI/Anthropic via `OPENAI_LOG=debug`/`ANTHROPIC_LOG=debug` or HTTPX event hooks. Do NOT activate for first-time prompt authoring, exploratory prompt design, or non-LM bugs.
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。
Security-first SOP for multi-tenant RAG systems. Activate when a calling agent is building, reviewing, or debugging any retrieval pipeline whose vector store is shared across more than one user, organisation, workspace, customer, or permission scope. Encodes the single non-negotiable rule — **filter at the vector store query, never after retrieval / never after rerank** — together with the per-vendor query-time filter APIs (Pinecone namespaces + `$eq`/`$in`, Weaviate `multiTenancyConfig` + tenant handle, Qdrant `is_tenant` payload index + `Filter.must`, Chroma `where`, pgvector RLS), and the cross-framework adapters (LlamaIndex `MetadataFilters`, LangChain `filter=` dict). Frame the work as preventing CVE-2024-41892 / EchoLeak / Slack-AI-class cross-tenant leakage, not as "adding a filter for relevance".
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。
Enhancement overlay for multi-agent / tool-using coder agents. Encodes the per-agent tool- scoping discipline that role-based frameworks (CrewAI, LangChain) document only as a passing best-practice: which agent gets which tool, and why blanket-sharing every tool to every agent is a correctness and blast-radius risk. Activates when an agent system has tools AND there is more than one agent (or one agent holding many tools). Treat a tool as a capability grant; scope by least-privilege. ENHANCE overlay — read alongside [[crewai]], [[agentsop-http-tool-wrapping]], [[agentsop-llm-tool-idempotency]]. Search keywords: which tools per agent, least-privilege agent, agent tool access, tool permissions, limit agent tools, scope tools to roles.overlay_type: enhancement
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。
Verify every @path chain import and every markdown link inside every CLAUDE.md in this project resolves to an existing file. Read-only — returns broken links with file:line refs, never edits.
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 applications and infrastructure handling Protected Health Information against HIPAA — Security Rule (administrative, physical, technical safeguards), Privacy Rule, Breach Notification Rule, plus HITECH. Covers ePHI scoping, the 18 HIPAA identifiers, Business Associate Agreement (BAA) chain-of-liability, minimum-necessary standard, and breach notification timing. Use when the user mentions 'HIPAA,' 'HIPAA Security Rule,' 'HIPAA Privacy Rule,' 'PHI,' 'ePHI,' 'protected health information,' 'BAA,' 'business associate agreement,' 'covered entity,' 'business associate,' 'minimum necessary,' 'HIPAA breach,' 'HITECH,' 'healthcare compliance,' 'medical data,' 'patient data,' or audits any system that creates, receives, maintains, or transmits PHI.
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 project dependencies, frameworks, languages, and dev tools for known vulnerabilities, CVEs, and security anti-patterns. Use when the user mentions 'dependency audit,' 'npm audit,' 'CVE,' 'vulnerable packages,' 'supply chain security,' 'outdated dependencies,' 'known vulnerabilities,' 'security advisory,' 'package security,' 'framework vulnerability,' 'is this package safe,' or needs to check whether their stack has known security issues.
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。