「guard」の検索結果

AI Agent Architect: Design agent systems: single vs multi-agent, tools and MCP, memory, guardrails, evals.

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。

Full safety mode: destructive command warnings + directory-scoped edits. (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 structured perspective-taking activities with anti-projection guardrails. Develops genuine understanding of complexity across history, social sciences, and literature — not performed empathy.

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。

Testing Craft CMS 5 plugins and modules with Pest — test isolation, database safety, and the markhuot/craft-pest-core harness. ALWAYS load when writing, running, fixing, or reviewing tests for a Craft plugin or module, and whenever a suite touches a real Craft install. Covers why rollback is opt-in, tests/Pest.php + tests/bootstrap.php wiring, phpunit.xml.dist <env> pins (force DB name + table prefix, default connection coordinates, pin CRAFT_ENVIRONMENT against server-scoped locks), why --configuration= defeats DB isolation, throwing fail-closed DB guards, installing the plugin under test, process-timezone pinning, per-test site fixtures, idempotent Install migrations, stale service caches when components get swapped, muting audit sinks, queue stubs, factories, HTTP/DB assertions, CI jobs.

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。

React Router v7 best practices for data-driven routing. Use when implementing routes, loaders, actions, Form components, fetchers, navigation guards, protected routes, or URL search params. Triggers on createBrowserRouter, RouterProvider, useLoaderData, useActionData, useFetcher, NavLink, Outlet.

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。

Repo-wide structural-maintainability review — code-judo restructurings, 1k-line file guard, anti-spaghetti branching, canonical-layer enforcement, anti-magic abstractions, explicit type/boundary contracts.

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。

Register, activate, and test a custom detekt rule in :quality:detekt-rules. Use when adding a DI/privacy/suppression guardrail rule or debugging a false positive.

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。

Author the narrowest R8/ProGuard keep rule for a JNI binding, serializable nav route, or proto-lite class. Use when adding one of those or triaging missing_rules.txt after a release build.

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。

Dirigent jednoho workflow kontraktu ve svém super.engineering worktree — deleguje implementaci na subagenta, mezi fázemi pouští wf-gate, review předá skill wf-review, otevře draft PR (guardovaný), vyřeší komentáře, spustí UAT. Použij, když task session říká, že se má kontrakt provést přes wf-impl.

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。

FIRE (Financial Independence Retire Early) calculator covering Lean FIRE, Fat FIRE, Coast FIRE, and Barista FIRE. Calculates FI number, years to FIRE based on savings rate, geographic arbitrage opportunities, sequence of returns risk, and withdrawal strategies (4% rule, dynamic withdrawal, guard rails). Use when the user says "/finance fire", "financial independence", "retire early", "FI number", "Coast FIRE", or any early retirement question.

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。

Drafts professional services agreements for healthcare providers and clients, covering HIPAA/HITECH compliance, BAA requirements, Anti-Kickback and Stark Law guardrails, credentialing warranties, malpractice insurance mandates, and patient care continuity on termination. Use when drafting healthcare provider contracts, medical services agreements, physician independent contractor agreements, or healthcare consulting engagements.

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。

Estate Planning & Legacy Protection for the Owens family. Tracks wills, trusts, beneficiary designations, life insurance, survivor benefits, and powers of attorney. Ensures Lindsey and the kids are protected if something happens to Tory. Triggers on: "Estate plan", "Will", "Life insurance", "Beneficiaries", "What happens if", "Legacy", "Survivor benefits", "Power of attorney", "Trust", "Estate check", "Beneficiary audit", "SGLI", "FSGLI", "Dependent education", "Chapter 35". The only estate plan that fails worse than a bad one is no plan at all.

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。

Drafts U.S. commercial real estate access and indemnity (right-of-entry) agreements for pre-closing due diligence. Covers license grants, non-invasive vs invasive testing gates, insurance/endorsement requirements, indemnity with discovery carve-outs, restoration and lien remedies, confidentiality, and anti-indemnity guardrails. Trigger: access agreement, right of entry, due diligence access, Phase I/II, invasive testing, pre-PSA site inspection.

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。

Expert guide for designing and orchestrating multi-agent systems, agent swarms, 2026 Anthropic agentic design patterns, graph-based workflows (LangGraph, OpenAI Agents SDK, Google ADK, Mastra.ai), shared state memory, and human-in-the-loop guardrails in English and Indonesian.

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。

CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, anti-pattern learning, cross-agent knowledge transfer, trauma guard safety system. Bun/TypeScript CLI.

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。

MCP Agent Mail for multi-agent coordination. Use when agents need file locks, messaging, inboxes, or conflict prevention. Handles macro_start_session, file_reservation_paths, send_message, threading, pre-commit guards.

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。

Handle blocked destructive commands. Use when dcg blocks rm -rf, git reset --hard, DROP DATABASE, kubectl delete, or when configuring agent 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。

Soul Shield — Guard Relic integrity, consent protocol, and ethics boundaries. Trigger on /relic-shield, or when user wants to verify consent, generate fingerprint, or check ethical compliance ("check consent", "ethics review", "灵魂指纹", "授权检查").

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。

Understanding and integrating multiple perspectives in historical analysis. Covers historical empathy (reconstructing how past actors understood their world), analyzing events from multiple viewpoints, constructing inclusive narratives that recover marginalized voices, and avoiding presentism (the imposition of contemporary values on past societies). Use when interpreting historical actors' motivations, assessing whose stories are told and whose are silenced, or guarding against anachronistic judgment.

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 before you shorten, compress, or rewrite the BODY of an existing SKILL.md or agent .md — the moment you are about to cut text to reduce length. First inventory the file's operational anchors (exact code / command / API snippets, fail-closed workflow guards, and rule / threshold statements), preserve every one, then judge the rewrite by expected downstream task cost (exploration, debugging, recovery tokens) rather than by the resulting line count. A shorter skill that strips an anchor makes the agent MORE expensive per task, so length is never the objective and rewrite is not compression. Backed by Preserving Operational Anchors When Compressing Agent Instructions (arxiv 2606.09421v2). Triggers on shortening or refactoring a skill or agent body.

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。

Manages skill-creator integration with GSD workflows including skill loading, session observation, bounded learning guardrails, and pattern detection. Use this skill whenever: executing any GSD phase (to ensure relevant skills are loaded first), starting or resuming a work session (to check for pending suggestions), the user asks about skills, patterns, or skill-creator status, performing code changes that might represent repeating patterns, the user corrects Claude's output (highest-signal observation), or when skill refinement, creation, or suggestion review is discussed. Critical for maintaining the adaptive learning layer.

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 at write time to vector/embedding memory — Grove content-addressed insertion, chroma/pgvector upserts, memory-consolidation promoting session traces to MEMORY.md, or embedding externally-ingested content. Scores each candidate record against a fixed panel of sentinel queries and quarantines any record that would become the nearest neighbor of too many unrelated queries — a hub — whether from adversarial poisoning or accidental over-generality. This is the memory-record-side sibling of skill-injection-guardian (file-side) and the write-side complement of memory-use-warrant (read-side). Quarantine, never silently drop; a human reviews. Backed by the admission-time hubness gate (arxiv 2606.19692v1). Triggers on inserting into vector memory, consolidating memory, and embedding stranger content.

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 writing Python scripts that must run on Windows, Linux, and macOS — especially when Rich or Typer output breaks on Windows, when dealing with Unicode/encoding errors, ANSI escape handling, terminal detection, path separators, or console color support. Provides verified cross-platform patterns covering stdout/stderr encoding guards, Windows console quirks, terminal capability detection, and portable I/O for CLI, TUI (Rich/Textual), and GUI 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。