305 件 ・ 関連度順
概要と使いどころ
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
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。
Advanced Agentic Coding framework providing mission briefs, guardrails, and integration hints for complex tasks. This skill ensures high-quality output through disciplined automation and systematic workflows.
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 reliable, safe, and trustworthy agent systems that fail gracefully and operate within bounds. Use when building guardrails, handling edge cases, preventing harmful outputs, monitoring for failures, implementing safety constraints, or designing error recovery. Covers failure modes, constraint systems, oversight mechanisms, and safety validation.
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 signup or onboarding conversion needs targeted analysis of friction, motivation, guardrails, and experiment opportunities.
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 a feature launch needs experiment design, test sequencing, rollout guardrails, and measurement logic before exposure to users.
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。
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。
Prevent common AI report pitfalls — bug blending, inflated threat models, and generic language. Train Claude with your best past reports for concise, technical submissions. Based on Critical Thinking Bug Bounty Podcast Episode 166.
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。
Natural-language orchestration of security tools through Gemini. Translates intent ("scan this scope for exposed admin panels") into safe, parameterized tool pipelines using nmap, masscan, naabu, httpx, nuclei, ffuf, gobuster, subfinder, amass, dnsx, katana, gau, semgrep, trivy, checkov, gitleaks, syft, grype, and custom scripts. Use when the user wants Gemini to drive a chain of CLI tools end to end with 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。
AI and LLM red-teaming skill for evaluating prompt injection, jailbreak, data exfiltration, tool abuse, agent hijack, RAG poisoning, model denial of service, and unsafe tool-use chains in Gemini, Claude, GPT, and open-weight models. Use to build evaluation harnesses, attack corpora, defensive guardrails, and red-team reports for AI systems you own or are authorized to test.
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。
Embed security into DevOps — pipeline security gates, guardrails, and culture that ships fast and safe.
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。
NLP on clinical text — de-identification, concept extraction, phenotyping from notes, and LLM safety 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。
Build on AWS with Amazon Bedrock — managed foundation models, agents, knowledge bases, and 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。
Design and build LLM agents: ReAct loops, tool schemas, planning, memory, guardrails, evals, and human-in-the-loop. Use when building autonomous multi-step AI 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。
Ship AI features to production — model selection, evals, latency/cost optimization, guardrails, monitoring, and iteration loops. Use when turning an LLM prototype into a reliable product feature.
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。
AI agent guidance — agent architecture, tool design, planning loops, guardrails, evaluation, and production agents.
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 legal case prediction systems for bias, fairness, accuracy, and ethical guardrails. Use when: 'check my prediction model for bias', 'audit case outcome fairness', 'evaluate legal ML model', 'review sentencing prediction ethics', 'analyze bail risk algorithm', 'fairness metrics for justice system AI'.
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。
Behavioral guardrails against the six most common LLM coding failure modes. Apply on every coding task: writing, editing, reviewing, or refactoring.
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。
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。
Write and harden reusable agent-loop specification documents for biomechanics, data science, and vailá coding work. Use when the user says `/preto-loop`, asks to write/create/forge/specify/document an agent loop, turn an iterative vailá task into an autonomous loop, make an overnight loop, or design a biomechanics, data-pipeline, markerless-tracking, testing, refactoring, or performance loop. Include external verification, scientific validity, GUI/CLI parity, reproducibility, memory, guardrails, and named terminal states. Do not use merely to repeat a fixed scheduled prompt, execute an existing loop, or create unrelated documents.
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 designing or reviewing Agentforce topic (renamed subagent in April 2026) structure, including topic boundaries, instruction quality, handoff rules, out-of-scope behavior, and topic-selector strategy. Triggers: 'agentforce subagents (formerly topics)', 'topic design', 'topic selector', 'agent scope boundary', 'handoff conditions'. NOT for restricting what the agent may do or say (topic Scope, action filters, abuse prevention) — use agentforce/agentforce-guardrails. NOT for the mechanics of transferring a live conversation out — Omni-Channel routing and the context package — use agentforce/agentforce-agent-handoff-patterns.
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。
Safety guardrails for destructive operations. Wraps workflows and agent actions in configurable safety modes: CAREFUL (warns before destructive commands), FREEZE (restricts file edits to one directory), GUARD (both modes combined). Use when working in production, running destructive scripts, or debugging in sensitive areas. Voice triggers: "be careful", "safety on", "guard mode", "freeze scope". Also used automatically by the workflow engine when a workflow preset has safety: "guard" enabled.
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, build, deploy, and operate production AI agent systems — single agents, multi-agent teams, and autonomous swarms. Complete methodology from agent architecture through orchestration, memory systems, safety guardrails, and operational excellence.
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。