「safety」の検索結果

Reference when designing autonomous agent systems or deciding agent freedom/safety/context management/collaboration infrastructure. 10 design principles distilled from Karpathy autoresearch (autonomous ML experiment loop) + AgentHub (agent-native Git DAG). Triggered by "autoresearch", "agenthub", "ratchet" ("래칫"), "context budget", "dumb platform", "program.md", "overnight", "autonomous experiment" ("자율 실험"), "branchless", "single-file constraint" ("단일 파일 제약"), "fixed time budget" ("고정 시간 예산") keywords.

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。

Applies local reliability, viewport, tab-safety, stale-ref, widget, and browser-boundary lessons to every agent-browser automation. Use alongside the upstream agent-browser skill whenever navigating, clicking, filling, testing, extracting, taking screenshots, or debugging any website with agent-browser.

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 TypeScript code, fixing type errors, or configuring strict type safety. Auto-activates on .ts/.tsx files. Covers null handling, utility types, and ESLint.

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 implement infrastructure, container, CI/CD, deployment-safety, observability, and rollback changes. Does not read dotenv files or approve/release deployments.

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。

JIRA comments, attachments, watchers, notify via jira-as. Internal-vs-public comment safety enforced. NOT issue CRUD (mk:jira-issue) or issue links (mk:jira-relationships).

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。

Confluence comments, attachments, labels, watchers via confluence-as. Inline-vs-footer safety enforced. NOT page CRUD (mk:confluence-page) or bulk ops (mk:confluence-bulk).

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 TypeScript code, fixing type errors, or configuring strict type safety. Auto-activates on .ts/.tsx files. Covers null handling, utility types, and ESLint.

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。

Manage JIRA collaboration surface via the jira-as wrapper: comments, attachments, watchers, notify. Triggers: 'comment on KEY', 'add attachment to KEY', 'watch KEY', 'notify KEY watchers'. Internal-vs-public comment safety enforced. NOT for issue CRUD (mk:jira-issue); NOT for issue links (mk:jira-relationships).

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。

Manage Confluence collaboration surface via the confluence-as wrapper: comments, attachments, labels, watchers. Triggers: 'add comment to page 12345', 'upload attachment to page 12345', 'label page 12345 as urgent', 'watch page 12345'. Inline-vs-footer comment safety enforced. NOT for page CRUD (mk:confluence-page); NOT for bulk ops (mk:confluence-bulk).

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 constraints and quality gates for pipeline and workflow execution

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。

Alembic migration patterns for naming conventions, safety checks, expand-contract, env.py configuration, and CI integration

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。

Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. Born from real production incidents: server crashes, token leaks, code rewrites. Works with Claude Code, Clawdbot, Cursor. Install once, enforce forever.

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。

Verify data validity through Openapi Trust - email deliverability, mobile number HLR checks, IP reputation, URL safety scans, document-based identity verification (IDV). Use for anti-fraud validation of user-provided contact data and identities.

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。

Designs human-in-the-loop review points for DAG workflows. Determines what to present to the human, how to collect feedback, and how to route approve/reject/modify decisions back into the DAG. Use when adding approval gates, designing review UX, or handling human feedback in agent workflows. Activate on "human review", "approval gate", "human-in-the-loop", "human gate", "approval workflow", "user review step". NOT for executing human gates at runtime (use dag-runtime with Temporal signals), general UX design, or chatbot conversation design.

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。

Decision-theoretic framework for agents embedded within the environments they model and act upon

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。

Schema design, normalization decisions, indexing strategies, and migration safety for relational databases. Use when designing tables, choosing between normalize vs denormalize, selecting index types, planning zero-downtime migrations, or setting up connection pooling. Activate on "schema design", "normalization", "denormalization", "foreign key", "index strategy", "migration", "connection pooling", "composite key", "surrogate key", "soft delete", "polymorphic association". NOT for PostgreSQL-specific query tuning or EXPLAIN analysis (use postgresql-optimization), NoSQL or document database design, or cloud database provisioning.

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 of Cognitive Systems Engineering applications and current practice in safety-critical domains

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。

Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols. Implements suicide ideation detection, automated escalation, and crisis resource integration. Use for mental health apps, recovery platforms, support communities. Activate on "crisis detection", "suicide prevention", "mental health NLP", "intervention protocol". NOT for general sentiment analysis, medical diagnosis, or replacing professional help.

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。

Select colormaps and qualitative palettes for scientific figures using perceptual-uniformity, color-vision-deficiency safety, and luminance-monotonicity criteria. Covers Crameri scientific colormaps, viridis/cividis/magma, Okabe-Ito categorical, ColorBrewer, and the rainbow/jet critique. Use when choosing palettes for heatmaps, scatter, networks, or any encoding where color carries quantitative or categorical meaning.

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。

Designs Bayesian clinical trials including Phase I dose-finding (BOIN, CRM, EWOC, mTPI-2), meta-analytic-predictive (MAP) priors with robust mixtures for external data borrowing, EXNEX for basket trials, hierarchical models for safety AE (Berry-Berry), Bayesian platform trials (I-SPY 2, GBM AGILE, REMAP-CAP), and posterior probability stopping rules. Covers FDA Bayesian Devices Guidance (2010), FDA Bayesian Methodology in Drugs Draft (January 2026), BOIN Fit-for-Purpose qualification (December 2021), and Project Optimus dose-optimisation. Use when designing dose-finding studies, platform trials, or sensitivity analyses with informative priors.

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。

Prepares statistical reports for clinical trials following CONSORT 2025, SPIRIT 2025, ICH E9(R1) estimands, and FDA 2023 covariate adjustment guidance. Covers Table 1 generation, analysis populations (ITT/FAS/PP/Safety), the 5 ICH E9(R1) intercurrent-event strategies, MMRM under MAR (mmrm), reference-based MI (rbmi J2R/CR/CIR), Permutt tipping-point sensitivity, and Rubin's-rules vs frequentist variance debate. Use when preparing regulatory submissions, defining estimands, or implementing missing-data sensitivity analyses.

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。

Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG/CYP/AMES endpoints, and PAINS / Lipinski / Ro5 / Veber / BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.

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。

Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and 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。

Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA fine-tuning, hybrid RAG handoff (see dedicated skill), vLLM 24x throughput, multi-layered security (90%+ bypass for single-layer), automated drift detection (18-second response), and CI/CD-aligned evaluation.

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。