「ai safety」の検索結果

Complete bedside prescribing reference for Mirago (mirabegron, beta-3 adrenoceptor agonist) for overactive bladder — covering contraindications, safety screening, drug interactions, dose selection in special populations, titration, and administration. Use when a clinician asks how to start mirabegron, what dose to use in renal or hepatic impairment, is mirabegron safe in this patient, mirabegron drug interactions, or Mirago for OAB.

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 workflow orchestrator. Walks the 11-phase pipeline, invoking each phase skill in order inside an internal loop, yielding at consent gates (/approve-direction, /approve-swarm, /grant-commit), and exiting cleanly on yield/failure/done. Decides swarm-vs-solo at Phase 6. Auto-loops /tdd on integrate failures that don't require a spec change. The harness_continuation Stop hook is a safety net that re-fires harness only when the loop exited mid-flow.

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 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。

Mathematical foundations, logical structures, and formal verification guidance. Trigger when: - Designing protocol contracts, formal specifications, verifying state spaces, or using proof assistants. - Tasks involve: TLA+, Alloy, Lean, Coq, model checkers, invariants, temporal logic. - Prompt contains keywords: formal verification, alloy, tla+, lean, coq, invariant, state machine, model checker, liveness, safety.

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。

Knowledge base from the NIST Framework for Cyber-Physical Systems (SP 1500-201/202/203, v1.0, 2017). Use for engineering and analyzing cyber-physical systems (CPS) and IoT: the CPS Framework's aspect × facet grid (nine aspects of concern examined through conceptualization, realization, and assurance facets), cross-property trustworthiness risk management (safety/security/privacy/reliability/resilience together), data interoperability (syntactical/semantic/contextual, canonical models, identifiers, provenance), the timing aspect (time-interval classes, time domains, time-aware networking) and secure/resilient time (GNSS jamming/spoofing, PTP/NTP attacks, holdover, the clock-error model and Allan/MTIE metrics), plus the use-case requirements method. Bridges IT and OT under a clock. Scope limits: a 2017 living/draft document, thin on post-2017 standards and on detailed control catalogs; it names but does not reproduce ISO/IEC/IEEE 42010 and 15288 process text or permission-licensed third-party figures.

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。

Knowledge base from the DoD Risk, Issue, and Opportunity (RIO) Management Guide for Defense Acquisition Programs (OUSD R&E, Sep 2023 incl. Change 2.2). Use for the defense-acquisition mechanics of program risk management: the RIO definitions (risk/issue/opportunity), the five-step risk process (plan-identify-analyze-mitigate-monitor), 1-5 likelihood/consequence scoring and the 5x5 risk matrix, the four mitigation options (accept/avoid/transfer/control), burn-down plans, issue management (probability=1), opportunity management toward should-cost, cross-program/interface risk, tailoring RIO to the six AAF acquisition pathways (UCA/MTA/MCA/Software/DBS/Services), specialized methods (RMF, MBCRA/Cyber Table Top, Agile metrics, FMECA, ITRA/DTRAM), and institutionalizing RIO via the PRMP, boards (RMB/JRMB/ROMB/RWG), tools, tiered roles, and WBS/IMP/IMS/EVM/TPM integration. This is the DoD-acquisition complement to nasa-risk (general CRM/RIDM theory) and dau-se-guidebook (the SE process frame). Does NOT teach general risk theory from scratch, and defers specialized risk regimes (system safety/ESOH, HSI, detailed cyber/RMF, spectrum) to their own DoD instructions and the relevant packs.

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。

Proposes tag and number structures for the new lines and instruments in a P&ID draft according to the project's numbering procedures, checks every tag extracted from the PFD against the quoted procedure format, and lists cross-section identifier mismatches and the registry checks a human must run. Never invents a numbering convention, never alters a PFD tag and never assigns a sequence number the procedure reserves for the registry. Use when the user asks to "run the tagging and numbering section", "check the tags against the numbering procedure", "propose the tag structure for the new lines and instruments" or "list the registry checks before validation" after the process safety flags. Do not use for validating the four sections, use validation-and-review-package instead; do not use for instrument content, use instrumentation-and-control-enrichment. Drafts for human review; never approves, authorises or signs 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。

Run the vault data-safety runbook: 3-2-1 backup, the never-deleted originals archive, the schedulers that keep it running, and the restore or new-machine migration procedure. Verifies by reading state rather than trusting exit codes. Triggers: "make a backup", "verify the backup", "the backup looks broken", "restore the vault".

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。

Agentic design-to-build pipeline that turns a Figma design into a built WordPress site using the Figma MCP server (read side) and the Elementor MCP server (write side) attached as MCP Apps on an NV oOS assistant. Covers the 7-stage pipeline (Scope → Read → Plan → Tokenize → Build → Verify → Handoff), the normative stage rules (get_design_context first, tokenize before build, drafts only, never publish, Figma read-only), the build-manifest contract (schema + example in reference/build-manifest.md), the design-file contract (frame/section/variable naming in reference/design-file-contract.md), assistant wiring (figma + elementor MCP Apps, OAuth + application passwords, host allowlist), safety rules, and troubleshooting. Use when asked to build or create a site, page, or landing page from a Figma design, to wire Figma MCP or Elementor MCP for design-to-build work, to approve or produce a build manifest, or to debug a failed design-to-build run.

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。

Remove signs of AI-generated code from a codebase while preserving behavior. Use when editing or reviewing code to make it read like a human engineer on this team wrote it. Works through a test-guarded detect-modify-verify loop: pin down the functional contract and edge cases first, write or run tests as a safety net, then rewrite AI tells (redundant comments, emoji, verbose names, reflexive try/except, defensive null-guards, over-decomposition, speculative abstraction, dead code, non-idiomatic constructs, hallucinated dependencies) and re-verify after every change. The tests decide whether a defensive block is slop or a real safeguard.

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。

Validate Claude Ads contracts, scoring inputs, run bundles, capabilities, source freshness, safety, installation, uninstall, or release readiness. Use for ads validate, ads status, ads next, stale claims with missing tool access, maturity checks, ownership-manifest uninstall, preserving unrelated ads-* skills, checksum verification, preflight, QA, or release audits. Missing access must demote stale evidence for the run and block dependent release-current claims before recovery guidance.

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 Snapchat Ads measurement, Snap Pixel and Conversions API, mobile and app campaigns, creative, AR and catalog formats, audiences, budgets, brand safety, and reporting. Use for Snapchat Ads, Snap Ads, Snap Pixel, Snapchat Conversions API, AR Lens ads, app-install campaigns, or Snapchat dynamic product ads.

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 YouTube Ads campaign setup, video and Demand Gen inventory, Shorts, in-stream, CTV, creative, audiences, brand safety, bidding, and measurement. Use for YouTube Ads, video ads, pre-roll, bumper ads, skippable in-stream, Shorts ads, Demand Gen, VAC migration, CTV, or YouTube campaign 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。

実装計画（plan.md / pbi-input.md）に含まれる危険操作・触れてはならないスコープ・人間承認必須条件を検出し、AI 自律実行前のゲートとして機能する

Reviews Laravel migrations for destructive operations, change() dropping modifiers, locking index creation on large tables (PostgreSQL), and asymmetric down().

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。

リファクタリング（構造変更）と機能変更（behavior change）が同一 diff に混在していないかを識別し、structural change に対する external behavior preservation の証拠（テスト・型・静的解析）が揃っているかを diff-time で確認する。証拠不足のときは Characterization Test 追加を促すか question とする。DTO/公開 API の破壊的変更検出は api-compatibility、完了主張の反証や抽出リファクタの性能特性退行は refactor-claim-audit、新知識の命名・責務・境界への反映は knowledge-to-code-alignment、投機的抽象化・スコープ逸脱は altitude-generalization / fix-scope-integrity へ委譲する

Apply a short artistic effect or VFX transformation to an approved media parent with explicit intent, provenance, and safety labeling.

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 operator-facing and public documentation plans for AI-Controlled Party mixer/Soundcraft Ui24R scene arming. Use for runbooks, rehearsal checklists, show-day checklists, EN/PT docs updates, demo scripts, safety wording, and follow-up documentation revisions.

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。

Search NHTSA vehicle recalls, FDA food/drug recalls, and CFPB consumer complaints. 3 tools for product safety monitoring.

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 working with Caddy — caddy web server management, automatic TLS certificate handling, reverse proxy configuration, site management, and plugin inspection. Covers Caddyfile analysis, admin API usage, access logs, and upstream health monitoring. Read this skill before any Caddy operations — it enforces discovery-first patterns, anti-hallucination rules, and safety constraints.

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 working with Snowflake — snowflake data warehouse analysis, query performance tuning, cost optimization, warehouse management, and schema inspection. Covers QUERY_HISTORY analysis, credit consumption, warehouse utilization, storage analysis, data sharing, and Time Travel. Read this skill before any Snowflake operations — it enforces two-phase execution, anti-hallucination rules, and read-only safety constraints.

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。

Shaping the Safety Boundaries: Understanding and … — Vor einem Tag · Abstract Jailbreaking in Large

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。

Training Details of the Second RL Stage 4 Experiment 5 Ethics and Safety Statement 6 Conclusion, Limitation, and Future Work 7 Author List A Backgroun

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, deploy, and secure Model Context Protocol (MCP) servers on Netlify. Use whenever the task involves creating an MCP server, exposing an app or API to AI agents as MCP tools, letting Claude / Cursor / Claude Code call a custom remote server, or adding MCP tools to an existing Netlify site. Covers the MCP SDK + Streamable HTTP transport on a Netlify Function, authentication (single shared secret vs per-user API keys with Netlify Identity), read/write safety, file uploads, and connecting clients. Use even when the user just says "MCP", "tool server for an agent", or "let an AI use my 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。