356 件 ・ 関連度順
概要と使いどころ
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
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。
End-to-end test the polly multi-agent coding orchestrator's critical user journeys (CUJs). Two halves — a deterministic mock-LLM driver (polly_cuj.py) that boots a throwaway local server + mock LLM and asserts the substrate (boot, bridged sys_* tool dispatch, the blast_radius / spawn_bounds / headless_subagent_purpose_guard guardrails, fan-out delegation), and a live real-CLI recipe (real claude/codex/pi, real worktrees/PRs) for polly's actual judgment. Load when developing, testing, or debugging examples/polly — its config.yaml, the claude_code/codex/pi sub-agents, the investigate/fanout/cross-review skills, or the omnigent.inner.nessie.policies guardrails — or reproducing a polly orchestration bug.
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。
Design KPI frameworks, metric definitions, targets, guardrails, and measurement plans for product or business decisions. Use when success metrics, drivers, guardrails, targets, or the measurement approach need to be defined or improved.
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。
NVIDIA NeMo Guardrails configuration for conversational safety and control
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。
Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.
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。
Set up a repo or project so an AI coding agent works well in it — the CLAUDE.md, the context, the guardrails, and the conventions the agent needs to be useful instead of lost. Use when asked how do I set up CLAUDE.md, configure my repo for Claude Code, my AI agent keeps getting my project wrong, or onboard an AI agent to my codebase. Produces a structured CLAUDE.md/project-context file (architecture, conventions, commands, do-nots), the right level of detail (enough to orient, not a novel), the guardrails that keep the agent safe (what not to touch, how to test), and a maintenance habit so it stays current — turning a repo an agent flails in into one it navigates like a teammate.
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。
Specify an autonomous or tool-using AI agent before building it. Use when asked to design an AI agent, define an agent's tools and guardrails, scope what an agent is allowed to do, or write an agent spec/PRD. Produces an agent spec — goal & scope, tools with permissions, the control loop, guardrails & approval gates, memory, escalation/handoff, evaluation, and failure handling.
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 AgentGuards enforces its guardrails in Codex — fully automatic, via hooks, with nothing for you to call. Load this if asked how AgentGuards works, whether you need to screen something yourself, or why no agentguards check_input / authorize_action tools are available.
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 the user mentions Foundation Models review, on-device AI audit, LanguageModelSession issues, or @Generable/guardrail problems — including missing availability checks, manual JSON parsing, and guardrail handling.
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。
A discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question you asked. Hypothesis writing, sample size, duration, segment analysis, running discipline, matching a result to a pre-committed decision rule, and the common failure modes that produce confidently wrong shipping decisions. Use this skill whenever the user is planning a test that has not run yet: framing a hypothesis, sizing the sample, setting duration, choosing guardrails, or deciding whether something is worth testing at all. Triggers on design an experiment, experiment plan, A/B test, split test, multivariate test, holdout, experiment hypothesis, sample size, minimum detectable effect, MDE, test duration, guardrail metric, no peeking, pre-committed decision rule, is this worth testing. Use `experimentation-analytics` instead when the test has already run and the question is how to read the result panel.
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。
Always-on operational guardrails, model-independent. Apply on EVERY task and EVERY model whether or not fable-mode's staged loop is running. Three rules: verify-before-flag, warning batching, and find-and-replace safety. Trigger whenever a response would flag a problem, raise a warning, or edit files with search-and-replace.
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。
Always-on spam and deliverability guardrails for cold email copy. Apply these rules whenever writing, reviewing, or QA-ing subject lines, openers, follow-ups, CTAs, or any cold outreach copy. Trigger on phrases like "check this for spam", "spam word check", "deliverability review", "QA this copy", "flag banned words", "check subject line", "is this safe to send", "scan for spam triggers", or any time cold email copy is being generated or reviewed. Also trigger automatically as a background rule whenever the campaign-copywriting or cold-email-copywriting skill is active -- these guardrails apply to EVERY piece of outbound copy generated, even if the user does not explicitly ask for a check.
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。
Define deterministic guardrails for agent tool calls — protected paths, test-file locks during bug fixes, post-edit formatters, production approval gates, secret deny rules. Use when writing or reviewing a hook policy, or moving an always-do-X rule out of prose into enforcement.
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。
Provides AWS CloudFormation patterns for Amazon Bedrock resources including agents, knowledge bases, data sources, guardrails, prompts, flows, and inference profiles. Use when creating Bedrock agents with action groups, implementing RAG with knowledge bases, configuring vector stores, setting up content moderation guardrails, managing prompts, orchestrating workflows with flows, and configuring inference profiles for model optimization.
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。
Assess an openai-guardrails-python GitHub issue or pull request as a maintainer. Use to verify the claimed need and practical impact, compare supported alternatives or competing approaches, separate code quality from repository readiness, recommend the maintainer action, and draft a copy-ready comment when evidence, changes, or closure should be requested.
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。
Choose compatibility-aware scope for runtime and API changes in openai-guardrails-python. Use before initial implementation and each review-feedback batch to decide whether to patch, reset the design, preserve compatibility, or reject unsupported cases.
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。
Create the required PR-ready summary block, branch suggestion, title, and draft description for openai-guardrails-python after runtime, tests, examples, build/test configuration, or behavior-impacting docs change.
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 an openai-guardrails-python release plan or final release candidate against the previous remote tag, determine the compatible release type, audit runtime and packaging risk, inspect current CI, and produce an English ship-or-block report. Use for pre-release readiness checks, not ordinary PR review or implementation.
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。
Start and carry an explicitly invoked openai-guardrails-python implementation through a fresh isolated worktree and a local PR-ready handoff. Fetch the latest origin/main, keep task changes uncommitted, replay them onto the latest main before final review, run applicable verification and $implementation-final-review, use $pr-draft-summary to generate the complete PR draft and branch name, then create one clean local commit with takeover provenance when applicable. Use only when the user explicitly invokes this skill; never push, open a PR, or mutate GitHub.
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。
Run the mandatory verification stack when changes affect runtime code, tests, examples, or build and test behavior in the OpenAI Guardrails Python repository.
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。
当需要为 AI 系统设计多层安全防线、内容过滤策略和伦理边界时调用此 skill。典型场景包括：设计拒绝策略与升级机制、防御 prompt 注入攻击、实现领域特定安全规则（教育、医疗、金融等）、定义 AI 的价值观锚点。 不适用于：定义工具操作权限（应使用 tool-specification）、定义 AI 身份（persona-design）、调整输出风格（personality-system）。 关键 trigger 信号：AI 涉及敏感话题、需要设计"拒绝回答"策略、存在 prompt 注入风险、特定行业合规要求、需要多层防御而非单一规则。
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。
Safe-release techniques DURING rollout: feature flags, progressive rollouts, canary analysis, guardrail metrics, production smoke tests, and synthetic users. Bridges QA and SRE practices. Use when: "feature flag testing," "canary deploy," "progressive rollout," "guardrail metrics," "dark launch," "safe rollout." Not for: scheduled probes that run continuously after release — use `synthetic-monitoring`. Not for: designing tests from prod telemetry — use `observability-driven-testing`. Related: release-readiness, synthetic-monitoring, observability-driven-testing, qa-metrics.
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。
Run AI agent code safely in isolated sandboxes with resource limits, audit trails, and kill switches. Use when someone asks to "sandbox my agent", "run agent code safely", "add guardrails to AI agent", "isolate agent execution", "audit agent actions", "prevent agent from deleting files", "restrict agent permissions", or "add safety controls to AI coding agent". Covers Docker isolation, filesystem restrictions, network policies, resource locking, and comprehensive audit logging.
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。
/aegisops-ai — Autonomous Governance Orchestrator workflow skill. Use this skill when the user needs Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
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。