「guardrails」の検索結果

Safety guardrails for destructive commands. (gstack)

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 spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description.

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。

Configure agy-auto PreToolUse security gate to run Antigravity CLI (agy) unattended with layered policy controls instead of --dangerously-skip-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。

Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.

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。

Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.

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 and implement Arduino integration with Azure IoT Hub and IoT Edge, including secure provisioning, resilient telemetry, command handling, and production 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。

How SGLang's runtime configuration and process-global state are organized (RuntimeContext tiers, publish + namespace config bags, the pristine ServerArgs seed, override entry points, resource/stream/buffer leases, per-forward flags), the CI guardrails that enforce the design, and the idioms for developing and testing against it. Load this before touching server_args, model overrides, module-level state, or per-forward state in sglang.

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。

Turn a fuzzy intention into a /goal objective the Goal verifier can actually judge - one outcome, numbered binary "Done when" checks that leave evidence in the transcript, guardrails, a budget, and a block protocol. Use when the user wants to set or define a goal, asks whether a goal is good enough, or says "keep going until X". Usage - /goal-draft <what you want done>, or /goal-draft <existing goal> to tighten it. This skill only writes the objective; it never starts the work.

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。

Discover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, verification, stopping conditions, guardrails, and handoffs. Use when a user asks to analyze a codebase for potential loops, mine coding-thread history for work done more than once, turn repeated engineering work into a loop, find or recommend a published loop, create a recurring agent workflow or automation cadence, turn an outcome into a bounded copy-ready loop, or review an existing loop for weak checks, unsafe authority, unbounded repetition, stale state, or unclear stopping behavior.

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。

Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.

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 a baseline landing zone foundation for a Google Cloud Organization, establishing security guardrails using Organization Policies, resource hierarchy folders and projects, billing association, and centralized logging and monitoring. Deploys Google Cloud's recommended security controls and architecture. Use when setting up a new Google Cloud Organization or establishing a secure, enterprise-grade landing zone foundation. Don't use for individual project onboarding (use google-cloud-recipe-onboarding or product-specific skills 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。

Provides safety-critical validation, guardrails, and data reduction for gcloud CLI operations across Google Cloud Platform (GCP) services and infrastructure. Use when planning, generating, constructing, proposing, describing, or executing any gcloud CLI commands - including when answering questions about gcloud syntax, or formatting flags. Don't use when writing Google Cloud client library code or raw REST/gRPC API requests.

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。

Publish a website or web app from the sandbox to a public URL, and deploy to cloud providers — get a live link to share, ship a static site or SPA, put a built site online, or deploy a framework app / container. Use when the user says 'publish this', 'deploy it', 'put it online', 'give me a live URL', 'host this', 'share a preview link', or wants to make a site/app they (or you) just built reachable on the web. Covers the zero-account instant path (Cloudflare) and permanent hosting (Vercel, incl. any Dockerfile). Also owns the publish GUARDRAILS: never publish unprompted, how to honestly take a site down, the runtime-dependency and data-persistence checks, and the mandatory pre-publish security review. Prefers Kortix Apps (a stable Kortix URL behind Kortix sign-in) when the project has Apps on. Points at kortix-marketplace for other providers and deeper provider-specific skills.

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。

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.

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 and evaluate paid-ad experiments with hypotheses, randomization units, sample-size and duration assumptions, guardrails, platform experiment tools, analysis, and decision rules. Use for A/B test, split test, experiment design, hypothesis, statistical significance, sample size, test duration, or experiment readout.

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。

Generate documents with write_file when retrieval tools fail, with explicit guardrails against task context drift

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。

Ship every change the way the user requires, with the guardrails. Take screenshots of the start, the key moment and the result; give the change its own changelog version with pictures; verify with tests; commit only your own files; merge with the latest main and push as a fast-forward; publish that exact main live; confirm each step; and report measured sizes, asking before any upload over 50 MB. Use at the end of every change (feature, fix, tweak, art, balance, polish) and whenever the user says "ship it", "commit", "push", "merge", "publish", "deploy", "go live" or "update the changelog". Project specifics (hosting, the changelog pipeline, merge conflicts) go in an optional local references/<project>.md next to this skill.

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 React loading, processing, selected, current, focus, and pressed states with the border-beam package's animated edge glow. Use when a card, button, input, tab, option, task panel, or agent surface needs a restrained traveling or breathing beam; includes installation, imports, prop selection, state wiring, reduced motion, accessibility, and performance and layout 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。

Password spray methodology for bug bounty — when to do it vs web-vuln hunting, the wordlist-gen + breach-check + osint-employees + spray pipeline, mode selection (http-form / oauth / o365 / okta), rate-limit + lockout tactics, BBP legal guardrails, success detection, and the spray → authenticated /hunt chain pattern. Use when assessing whether credential attack is worth running on a target, picking the right mode, or recovering from common pitfalls.

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。

Opinionated Bayesian modeling workflow with PyMC and ArviZ. Contains critical guardrails (nutpie sampler, prior/posterior predictive checks, LOO-PIT calibration, prior sensitivity checks, 94% HDI, non-centered parameterizations, reproducible seeds) that agents won't apply unprompted — always consult before writing Bayesian model code. Trigger on: building probabilistic/Bayesian models, prior elicitation, MCMC inference, convergence diagnostics (divergences, R-hat, ESS), model comparison (LOO-CV, ELPD, stacking weights), hierarchical/multilevel models, count regressions, logistic regression with uncertainty, prior sensitivity analysis, reporting Bayesian results, or mentions of PyMC, ArviZ, InferenceData, credible intervals, posterior distributions, shrinkage, uncertainty quantification. Also trigger for model comparison, diagnosing sampling problems, choosing priors, or presenting stats to non-technical audiences.

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。

Production-grade Bayesian causal inference with PyMC, CausalPy, and DoWhy. Enforces DAG-first thinking, mandatory user checkpoints for assumptions, design-specific refutation, and defensible reporting with causal language guardrails. Trigger on: causal inference, causal effect estimation, treatment effects, counterfactuals, difference-in-differences (DiD), synthetic control, regression discontinuity (RDD), interrupted time series (ITS), instrumental variables (IV), propensity scores, DAGs, causal graphs, confounders, backdoor criterion, do-calculus, interventional distributions, pm.do(), pm.observe(), CausalPy, DoWhy, mediation analysis, refutation, sensitivity analysis, parallel trends, placebo tests, or any question of the form "does X cause Y" or "what is the effect of X on Y."

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。

Configure a shared guard against catastrophic shell commands in local AI agents. Use when changing block patterns, adding an agent or machine, or investigating why a command was or wasn't blocked.

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。

Plan and review Amazon Ads with margin-aware ACoS, product, and search-term guardrails. Use for Amazon advertising, Sponsored Products, Sponsored Brands, Sponsored Display, ASIN targeting, Amazon ACoS, or Amazon Ads performance exports.

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 RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more).

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。