3,311 件 ・ 関連度順
概要と使いどころ
Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns
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。
按风险编写和维护项目规范，保留有效功能约定与关键决策。用于明确要求整理 spec、补齐项目文档、更新需求设计或迁移旧文档流程；普通代码修改不自动启动完整文档流程。
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 the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video, narrated explainer, video podcast, or animated infographic-style video from a topic — even if they don't say "video podcast" explicitly. Also trigger when the user wants to regenerate, re-render, rebuild, update, or iterate on a narrated video this skill already produced — e.g. they edited the script/prompt, changed the visuals, or swapped the background music and want the final video remade (reuse the existing videos/{name}/ directory, never start a new project). Do NOT trigger for generic video editing, trimming, format conversion, color grading, or non-narrative video tasks. Produces 4K video via research → script → TTS → Remotion → MP4 + BGM.
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 an external frontier-model referee (Claude Code -> a different vendor's frontier model via the Oracle CLI) on a paper, proof, estimator, or replication package -- and adjudicate what comes back. Use when the user says "send this to oracle", "get an external review", "run a referee round", "deep-check this proof", or before a submission when an independent second opinion is worth more than another in-house pass. Never launches bare: brief first, evidence-forcing prompt, coverage manifest, then CONFIRMED/REFUTED/DOWNGRADED triage.
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。
Create or revise Chinese social-media covers through the registered Skill-封面 asset system, reusable styles, presenter identities, ratio-specific layouts, and exact replacement prompts. Use only when the user explicitly says“skill-cover”“Skill-封面”“实战风格”, requests the registered style/gesture assets, asks for simultaneous 3:4 and 4:3 registered-layout output, replaces a reference cover's person with the current digital-human frame, or extends this registered cover system. Do not use for a generic“制作封面/生成封面”request; generic cover requests belong to dog-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。
Create and composite HeyGen digital-human videos in the content workspace. Use whenever the user asks for a 数字人, 数字人5, HeyGen, AI 口播人物, 数字人小窗, 圆形头像口播, full-screen digital human, or asks to make a video that uses the existing avatar. Enforce Creator-plan CLI OAuth, the configured Digital Twin, local IndexTTS2 narration, Avatar III for an unspecified digital human but Avatar V whenever the named preset 数字人5 is requested, adaptive face measurement plus the approved human-reviewed visual-centering offset in the headroom_08 circular bottom-left layout unless full-screen is explicitly requested, subtitle-safe placement, credit-aware master reuse, final QC/archive routing, and mandatory pairing with `heygen-avatar-motion` before any motion prompt or paid generation.
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。
实操长片策划工作流（B站/YouTube 新赛道，实操+真人出镜）。产出可直接照着录的策划稿：测试题组（含可粘贴 prompt）、 结构时间轴（全身出镜段 vs PiP 段）、出镜口播稿、录屏操作清单、悬念与彩蛋设计。 Use when the user says 做实操长片, 实操视频, 实测视频, 对比实测, xx做成实操, 出个实测策划, 这个选题拍实操, or ra-选题 routes a 实操长片 立项 here. 策划稿落 `01-内容生产/视频工作台/制作中/<日期-主题>/策划稿.md`，frontmatter status 是与制作端交接的唯一状态机。
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。
Invoke the locally installed Grok Build CLI from Codex and return Grok's response. Use whenever the user asks Codex to call, consult, run, or delegate a prompt to Grok or Grok Build, including Grok web/X searches and agentic Grok tasks. This Skill covers only the invocation mechanism, process monitoring, and response capture; it does not prescribe the task itself.
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。
Create dark cinematic SaaS/product motion videos in the Presenton-like "magic UI" style: black starfield stage, bottom purple glow, large kinetic type, cyan-to-magenta CTA buttons, prompt cards, floating UI templates, integration badges, model rings, export objects, speed-blur transitions, and short product capability arcs. Use when the user asks for "这种风格", "同款风格", dark SaaS promo, AI product demo, magic UI product video, or a style-level creation inspired by a reference video. Do not use for pixel-level or frame-accurate replication; use rn-replica-qc first for that.
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。
Generate high-CTR YouTube thumbnails using Nano Banana 2 via the Arcads external API. Handles reference image upload, character likeness alignment, proven CTR-tested prompt formulas, and parallel batch generation. Use when the user asks to create a YouTube thumbnail, video thumbnail, A/B test thumbnail variations, or refers to thumbnail design with their face, brand assets, or product photos.
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。
Clone an existing video ad for a different product or offer. Analyzes the source video's style, pacing, camera work, dialogue, and tone, then adapts and generates a new Seedance 2.0 video customized for the user's product. End-to-end workflow: input video → analysis → adapted prompt → generation → delivery. Use when someone says "clone this ad", "make this ad but for my product", "recreate this video for my brand", or provides a video ad and a product image asking for a similar video.
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。
Analyze a reference video and reverse-engineer its style into a reusable Seedance 2.0 prompting template. The output is a new skill/formula (like seedance-2-ugc.md) that captures the video's structure, pacing, camera work, edit style, and tone so it can be recreated with any product, any person, in any setting. Use this whenever someone provides a video they want to use as a style reference, says "I want to make videos like this", "deconstruct this video", "turn this into a template", "analyze this style", or drops a video file and wants to recreate that format repeatedly.
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 the user types /prompts:hep-build or /agentlas-build, mentions @Hephaestus for build work, asks to create a single Agentlas agent, create a multi-agent team, or package an existing local/external agent into Agentlas architecture.
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。
Scrape BOSS直聘 (job listing site) via Chrome CDP. Searches jobs by keyword/city/filters, fetches JD details, outputs structured JSON/CSV with plaintext salary, and can summarize scraped results into a job-market prompt. Use when user wants to search/analyze jobs on BOSS直聘 or zhipin.com.
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。
Lookup documented AKS fixes only when the prompt includes an exact catalog signature and all of its qualifiers: VMCannotFitEphemeralOSDisk; NodePoolMcVersionIncompatible; 'NodeImageVersion is not accepted'; AKS SkuNotAvailable with size, location, and zone; ZonalAllocationFailed with insufficient zone capacity; OverconstrainedAllocationRequest with listed constraints; nested AKS vmssCSE/CSE VMExtensionError_OutboundConnFail, VMExtensionError_K8SAPIServerConnFail, or VMExtensionError_K8SAPIServerDNSLookupFail; or AllocationFailed with the full cataloged internal-error or insufficient-regional-capacity message. Never use for quota errors, code-only or bare wrappers, generic symptoms, incomplete signatures, or failures outside AKS; use aks-troubleshooting or azure-diagnostics.
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。
List, find, and show Azure resources across subscriptions or resource groups. Handles prompts like "list the websites in my subscription", "list my web apps", "show my app services", "list virtual machines", "list my VMs", "show storage accounts", "find container apps", and "what resources do I have". USE FOR: list websites, list web apps, list app services, show websites in subscription, resource inventory, find resources by tag, tag analysis, orphaned resource discovery (not for cost analysis), unattached disks, count resources by type, cross-subscription lookup, and Azure Resource Graph queries. DO NOT USE FOR: deploying/changing resources (use azure-deploy), cost optimization (use cost-optimization from the optional azure-cost plugin), or non-Azure clouds.
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。
Recover source-bound buyer jobs, struggling moments, desired progress, forces, workarounds, information acts, journey states, criteria, constraints, roles, locales, and authentic language. Use on approved ICP hypotheses plus customer, search, review, forum, procurement, support, or public-market evidence before designing an AI-visibility prompt architecture.
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 QA-approved canonical intent cells into a versioned AI-visibility tracking panel with partitions, variants, lanes, surfaces, locales, repetitions, separate exposure and priority weights, randomization, uncertainty, refresh rules, and campaign controls. Use after prompt QA or when revising an existing panel.
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。
Turn a source-bound company and market dossier into testable ideal-customer-profile hypotheses, buying roles, triggers, constraints, disqualifiers, standing, counterevidence, and research gaps. Use when a URL, company description, monitor profile, or evidence manifest needs to become defensible ICP inputs for buyer research or an AI-visibility prompt panel.
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。
Create and validate HVE Core agents, prompts, instructions, and skills with current frontmatter, package membership, delegation, tracking, documentation, and validation conventions. Use when authoring a GitHub Copilot customization artifact in this repository.
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。
Create, improve, refactor, replace, review, or validate prompts, instructions, agents, subagents, and skills. Use for Copilot customization cleanup, extending HVE workflows with project-specific capabilities, and parent-owned correction of material review findings.
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。
Generate a bounded task plan (and the agent prompt for it) that runs the 5-layer profiling methodology in .claude/skills/model-profiling/METHODOLOGY.md against one model, stops for human confirmation before any GPU work starts, then delegates the actual run to a background agent, verifies its completion claim, and routes findings into a gitignored .profiling-runs/<model>/ directory — durably tracked as a sub-issue under the tracking issue named in SKILL.md's "Result tracking" section — plus the methodology doc.
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 LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests); use `write-code-eval`. To validate an existing judge, use `validate-evaluator`.
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 code evaluators for known failure modes with objective rules. Use when code can check the rule from a trace, with or without a reference answer. Use `write-judge-prompt` when the rule requires interpretation.
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。