743 件 ・ 関連度順
概要と使いどころ
Provider-independent quality assurance for AI-generated and AI-assisted media. Use when reviewing, accepting, revising, or reporting on images, video, audio, avatars, ads, product content, social clips, explainers, localization, mixed-source edits, captions, accessibility, provenance, model metadata, safety/policy, and delivery readiness.
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 X Ads measurement, X Pixel and Conversions API, campaign objectives, keyword and conversation targeting, creative, budgets, brand safety, app measurement, and reporting. Use for X Ads, Twitter Ads, promoted posts, X Pixel, X Conversions API, conversation targeting, or paid campaigns on X.
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。
AWS Bedrock — fully managed foundation models on AWS infrastructure. Use when deploying AI in AWS-native environments, needing enterprise compliance (SOC2, HIPAA), running Claude, Llama, Titan, or Mistral on AWS, leveraging Knowledge Bases for RAG, or applying Guardrails for content 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。
This skill channels the strategic and empathetic reasoning of Whitney Wolfe Herd, founder and CEO of Bumble. Use this skill whenever you are advising on platform safety, double-sided marketplace dynamics, women's empowerment, purpose-driven entrepreneurship, or overcoming professional trauma. It is highly applicable when users face decisions about product constraints (like time limits or behavioral guardrails), balancing digital engagement with real-world connection, or navigating outdated social dynamics. Reach for this skill to help users shift from 'me to we,' engineer kindness into their products, and focus on core inputs rather than vanity metrics.
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 the reasoning style of Ilya Sutskever (deep learning pioneer, co-founder of OpenAI and Safe Superintelligence Inc.) to problems involving AI architecture, scaling laws, alignment, and research strategy. Reach for this skill whenever discussing machine learning paradigms, the limits of compute and data, AGI timelines, superintelligence safety, or deciding between hardcoding vs. learning. Trigger this skill for questions about next-word prediction, reinforcement learning efficiency, generalization gaps, and transitioning from brute-force scaling to fundamental research, even if the user doesn't explicitly name him.
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, run, and analyze structured test suites for Agentforce agents — functional AND security. TRIGGER when: user writes or modifies test spec YAML (AiEvaluationDefinition); runs sf agent test create, run, run-eval, or results commands; asks about test coverage strategy, metric selection, or custom evaluations; interprets test results or diagnoses test failures; asks about batch testing, regression suites, or CI/CD test integration; requests security testing, OWASP LLM Top 10, red-teaming, penetration testing, prompt-injection tests, a security grade, or a vulnerability assessment of an agent. DO NOT TRIGGER when: user creates, modifies, previews, or debugs .agent files (use agentforce-generate); deploys or publishes agents; writes Agent Script code; uses sf agent preview for development iteration; analyzes production session traces (use agentforce-observe); performs a static safety review of .agent file content (use agentforce-generate Section 15).
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。
Prompt engineering for production LLMs — structured outputs, evals, RAG, tool workflows, multimodal prompting, and safety. Use when designing, debugging, or shipping prompts.
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。
Claude adapter for PlainTab storage, IndexedDB, localStorage, schema version, migration, cleanup, import/export, and old-user upgrade safety 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。
Implementing robust business logic, API integrations, data models, and reproducible AI image-generation code with type safety. Use for production implementation, Gemini image API pipelines, or interactive pair programming.
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。
Statics, dynamics, stress-strain analysis, materials selection, failure modes, and finite element analysis concepts for engineered structures. Covers free-body diagrams, equilibrium, internal forces (shear and moment), beam deflection, column buckling, material properties, factor of safety, fatigue, fracture mechanics, and FEA workflow. Use when analyzing loads on structures, selecting materials, predicting failure, or interpreting structural 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。
Transcribes audio and generates auto-chapters with summaries using AssemblyAI's /v2/transcript endpoint with auto_chapters=true. Extracts key topics, sentiment analysis, and content safety labels via AssemblyAI SDK.
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, harden, and test the safety policy for AI-Controlled Party mixer/Soundcraft Ui24R scene arming. Use for approval gates, blocked mixer operations, hazardous request handling, venue validation, bypass attempts, QA, risk review, or follow-up safety changes.
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。
Identify and safely gather edible and useful wild plants. Covers safety rules and deadly plant recognition, habitat reading, multi-feature identification methodology, the universal edibility test, sustainable harvesting practices, preparation methods, reaction monitoring, and building knowledge with beginner-friendly universal species. Use when supplementing food supply in a wilderness or survival setting, needing medicinal or utility plants, identifying plants around camp for safety, or in long-term scenarios where foraging extends available rations.
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。
Coordinate safely with a peer interactive session sharing the same git worktree — check first whether a separate worktree removes the problem, then declare path and branch scope before the first edit, survive a contended index lock, and review the whole branch before opening a PR. Activate when starting work in a repository that may already be occupied, when a git command fails with `index.lock: File exists`, when `guard:snapshot` refuses because a snapshot already exists, or when a commit turns out to contain a file this session never edited. When one session leads and the other supports, divide the labour by shape and re-derive every reported number against a named revision before citing it. Distinct from subagent concurrency: a peer session cannot be bracketed, because no baseline exists from before its edits.
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 task needs the judgment of a Dishwasher/kitchen steward — triaging a backed-up dish pit mid-rush, verifying sanitizer concentration or dish-machine rinse temperature against food-safety spec, deciding what routes to the three-compartment sink versus the dish machine, diagnosing a spike in breakage, or handling a machine failure mid-service.
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 task needs the judgment of a Coin, Vending, and Amusement Machine Servicer and Repairer — triaging a jam across bill validators, coin mechanisms, refrigerated vending units, and arcade/amusement PCBs on a route, setting restock par levels against route-cycle economics, investigating a cash-collection variance at a stop, or applying food-safety temperature/time discard rules on perishable vending product.
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 task needs the judgment of a correctional services manager (warden/facility administrator) — deciding how to respond to a staffing cut against safety risk, reviewing an inmate classification or housing decision, evaluating a use-of-force incident, deciding whether restrictive housing placement is justified and time-limited, or weighing security spending against programming budget under fiscal pressure.
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 task needs the judgment of a Career/Technical Education Teacher, Postsecondary — defending a shrinking trade or health-science program against a cutback decision, backward-mapping a shop or lab curriculum to an industry credential's exam blueprint, resolving a competency-based grading dispute where a passing average hides a failed safety check-off, or setting the terms of an advisory-committee review or work-based-learning placement.
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 task needs the judgment of a Child, Family, and School Social Worker — distinguishing an immediate child-safety determination from a longer-term risk assessment, deciding whether an in-home safety plan can control an identified danger versus removal being required, building a safety plan with specific and verifiable (not vague) elements, documenting a case contemporaneously and factually for a court-involved record, or engaging a family's specific context and strengths rather than a generic checklist.
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 task needs the judgment of a Biostatistician — designing a clinical trial's sample size and analysis plan, choosing a survival-analysis or censoring-aware method, preparing a DSMB safety readout, or judging whether a trial's efficacy claim survives ITT vs. per-protocol scrutiny.
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 task needs the judgment of a Biologist — designing a study and identifying its true experimental unit before data collection starts, running a power analysis to size a sample, judging whether a published or preclinical finding warrants trust without independent replication, sequencing IACUC/IBC/field-permit approvals before biosafety or wildlife work begins, or scoping a grant-funded research plan against realistic funding odds.
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 task needs the judgment of an Aerospace Engineer — reconciling a vehicle mass/weight budget against a certification limit, computing a structural margin of safety, choosing a means of compliance for an FAA certification basis, tracing a weight-growth overrun back to a design decision, or evaluating a propulsion/aerodynamics tradeoff against a range or payload requirement.
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。
Spring Boot 4 data layer implementation for Domain-Driven Design. Use when implementing JPA or JDBC aggregates, Spring Data repositories, transactional services, projections, or entity auditing. Covers aggregate roots with AbstractAggregateRoot, value object mapping, EntityGraph for N+1 prevention, and Spring Boot 4 specifics (JSpecify null-safety, AOT repositories). For DDD concepts and design decisions, see the domain-driven-design 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。
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。