「multi-step」の検索結果

Test AI agent systems for tool abuse, unauthorized actions, privilege escalation through tool chaining, and safety bypass via agentic workflows. Use this skill when assessing autonomous AI agents that use tool-calling (function calling, plugins, actions) to interact with external systems. Covers multi-step attack chains, implicit trust exploitation, and capability boundary testing for AI 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。

Use when building or reviewing substantial forms with React Hook Form, Zod schemas, typed validation, dynamic fields, controlled third-party inputs, file upload, multi-step flows, dependent validation, or form performance. Do not use for trivial 1-3 field forms without validation; Chinese triggers include form, form validation, dynamic fields.

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 and task-specification skill for improving prompts, agent instructions, system messages, evaluation prompts, coding-agent tasks, multi-step workflows, and LLM output reliability. Use when rewriting vague prompts, adding constraints, reducing ambiguity, improving safety, creating reusable prompt templates, or converting goals into actionable agent instructions.

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 excellent web forms: UX patterns, validation, accessibility, multi-step flows, and file uploads. Use for any form beyond trivial inputs.

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。

Elicit step-by-step reasoning from language models to boost accuracy on math, logic, and multi-step problems.

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 LLM applications with chain-style orchestration frameworks — prompts, chains, tool-calling agents, memory, and retrieval pipelines. Use when structuring multi-step LLM programs, adding tools to a model, or composing RAG systems in 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。

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。

Build agents on OpenAI's platform patterns — assistants-style threads, function calling, structured outputs, and multi-step tool workflows. Use when working with OpenAI models as the agent engine.

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 multi-email nurture sequences for lead-gen, onboarding, re-engagement, sales, and lifecycle marketing using the Hook Model (Nir Eyal) to architect the sequence arc and PAS (Problem-Agitate-Solution) to structure each email body. Use when the user asks for an email sequence, drip campaign, nurture flow, onboarding emails, re-engagement campaign, "write 5 emails for X", welcome series, or any multi-step email program. Reads brand voice and ICP from knowledge/. For a single cold outreach email, see pr-pitch-writer. For the newsletter, see newsletter-writer. For testing subject lines, see ab-copy-writer.

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 you have a spec or requirements for a multi-step task, before touching 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。

Configuring Salesforce In-App Guidance: floating, docked, and targeted prompts, multi-step walkthroughs, audience targeting, scheduling, and adoption analytics. Use when designing user onboarding or feature adoption programs in Lightning Experience. Covers the Prompt metadata type, promptVersions, displayType, uiFormulaRule, stepNumber, isPublished, PromptAction and PromptError. NOT for guidance on a record's Path — use admin/path-and-guidance. NOT for adoption and training — use admin/change-management-and-training.

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。

Ticket system and work logs for context anchoring. Use when creating tickets, managing work logs, or anchoring context across multi-step tasks or sessions. Do NOT use for simple patches or single-step tasks.

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 a self-retrospective on a SKMTC-related session — generator authoring, CLI configuration, debugging, or any sustained interaction involving `@skmtc/core`, `@skmtc/cli`, or `@skmtc/gen-*` packages. Captures three distinct outputs: (1) friction entries (mistakes, surprises, overridden defaults, multi-cycle struggles), (2) a "knowledge acquired" block recording facts the agent learned during the session that weren't in its training — the primary signal for doc gaps — and (3) a closing priority list ranking the top 2-3 findings for docs/skills triage. Wins are logged only when they identify a pattern worth codifying that isn't already in a skill. Use this skill when the user asks to "retro", "skmtc retro", "log friction", "reflect on this session", "what did we learn", "run a retrospective", or after substantive SKMTC work (generator authoring, multi-step debugging, non-trivial CLI configuration) where capturing observations would help improve skills, docs, or SKMTC itself. Distinct from the `skmtc-cli` and `skmtc-generator` skills — those guide *doing* the work; this skill captures observations *about* the work. Do not invoke this skill during ordinary work; it is end-of- session (or mid-session-checkpoint) only.

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 you have a spec or requirements for a multi-step task, before touching 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。

Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step 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。

Scaffold new spell step commands and connectors. Use when building new step commands for spells or extending the spell engine with new capabilities. Connectors are for new I/O transport types OR platforms requiring complex multi-step interaction (e.g., browser-based automation).

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。

Senior {{engine_name}}/{{engine_code_language}} developer that performs direct, ad-hoc code tasks without a formal plan — and the code-execution engine other unikit skills and agents delegate to. Use it whenever the user asks to do something in code right now, e.g. "add this method to this class", "refactor this function", "write a script that does X", "change this code", "optimize this class". Phrases like "without a plan", "no plan", "just do it", or "directly" are strong signals to use this skill rather than planning. Covers writing, refactoring, optimizing, and discussing {{engine_code_language}} code and patterns (DI, ECS, MVC, state machines, event systems). For a larger multi-step feature, plan it with /unikit-plan and build it with /unikit-implement — this skill is for direct, unplanned code 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。

Use when you have a spec or requirements for a multi-step task, before touching 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。

One-command pre-execution review pipeline. Runs scope review → architecture review → security review → design review (auto-detects which apply) before executing any workflow. Surfaces only taste decisions for user approval. Auto-fixes obvious issues. Use before executing multi-step workflows, deploying, or when user says "review this plan", "check before running", "pre-flight", or "is this ready?". Runs CEO → eng → security automatically with encoded decision principles.

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。

Session retrospective. Runs after a workflow, coding session, or multi-step task completes. Analyzes what shipped, what failed, patterns observed, and growth opportunities. Generates a retro summary with per-step breakdowns, shipping streaks, and test health trends. Use after any significant session (>3 steps or >15 min). Proactively suggest when the user finishes a workflow, completes a feature, or says "let's review what we did." Also supports global retro across all projects.

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。

CEO/founder-mode scope review. Challenges the scope of any plan, workflow, or feature before execution. Four modes: SCOPE EXPANSION (dream bigger), SELECTIVE EXPANSION (cherry-pick worthwhile expansions), HOLD SCOPE (maximum rigor within current scope), SCOPE REDUCTION (strip to essentials). Use before executing any multi-step workflow or when questioning whether the scope is right. Prevents scope creep and missed opportunities. Use proactively when the user defines a plan, creates a workflow, or says "is this enough?" or "am I thinking too small?".

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 signal-based forms in Angular v21+ using the new Signal Forms API. Use for form creation with automatic two-way binding, schema-based validation, field state management, and dynamic forms. Triggers on form implementation, adding validation, creating multi-step forms, or building forms with conditional fields. Signal Forms are experimental but recommended for new Angular projects. Don't use for template-driven forms without signals or third-party form libraries like Formly or ngx-formly.

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。

Relentless delivery mode for complex, multi-step tasks. Use when: multi-file features, unclear root cause debugging, multi-angle research, architecture decisions with trade-offs. Activates parallel subagent dispatch and strict verification.

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。

Evidence-first multi-step research with bounded parallel collection, contradiction checks, and cited synthesis.

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。