4.8万 件 ・ 関連度順
概要と使いどころ
Turns rough intent or a weak prompt into a reliable one — diagnosing why output is inconsistent, restructuring the instruction, and adapting it across models. Use this when a prompt is not producing what was wanted, when output varies run to run, when writing a prompt for a repeated task, when moving a prompt between models, or when someone describes what they want an AI to do and needs it written properly.
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, documents, and fixes operational processes — mapping the current state, finding where work actually stalls, redesigning the flow, and building controls that hold. Use this when the same failure keeps recurring, when a handoff between teams is unreliable, when onboarding a repeated task, when work takes far longer than the work itself, or when deciding whether to automate, standardize, or eliminate a process.
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。
Pressure-tests a decision, plan, or idea before it is committed to — surfacing the assumption it rests on, the case against it, and what would have to be true for it to work. Use this when weighing options, when a plan needs challenging before commitment, when you have already decided and want a genuine gut check, when processing meeting notes into decisions, or when competing initiatives need ranking. Distinct from `chief-executive`, which owns direction; this one interrogates a specific decision.
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。
Sets direction, allocates capital and attention, and makes the calls no one else can make. Use this when a decision spans more than one function, when priorities conflict and something must be cut, when a plan needs pressure-testing before commitment, or when the question is what the organization should do rather than how to do it. Also use to route a request to the right executive when it is unclear who owns it.
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。
Finds the single constraint currently limiting a business's growth and the highest-leverage moves against it, rather than producing a list of everything that could be improved. Use this when growth has stalled or slowed, when deciding where to spend limited time or budget, when revenue rises but profit does not, when prioritizing growth initiatives, or when a business feels busy without compounding.
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。
Optimizes for AI assistants and AI-generated answers — being retrievable, being cited, and being represented accurately when a model answers on your behalf. Use this when traffic is shifting from links to AI answers, when a brand is misrepresented or absent in AI responses, when planning content for retrieval rather than ranking, or when deciding how AI search changes an existing SEO program.
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。
Organic story anatomy from John Truby's The Anatomy of Story (有机结构/设计原则/22步骤/道德议题/四角对立/幽灵/场景编排) — the designing principle (story process plus original execution), the seven key steps as the organic spine, all twenty-two steps with the middle-act machinery the beat sheets lack (ghost, fake-ally opponent, plan, opponent's drive, ally's attack, fake defeat, three revelation-and-decision pairs, audience revelation, visit to death, moral decision), four-corner opposition, the moral-argument chain with the hero-opponent power-balance rule, scene weave with structure-step tags and storyline numbers, and the accordion rule (never fewer than seven steps). Kept side by side with the Field/Snyder page maps. Use when the middle act sags into unconnected episodes, when the premise works but the story feels mechanical, when one antagonist cannot carry the theme, when the theme stays stated instead of acted, or when a BS2 board needs an organic second pass.
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 diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.
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。
Evaluate performance fairly when output is AI-assisted — what still measures the human, what now measures the tooling, and how to run the review conversation. Use when reviewing someone whose work is heavily AI-assisted, when output volume stopped meaning anything, when calibrating a team with uneven AI adoption, or when writing review criteria for the AI era. Produces review guidance: a what-measures-whom analysis, rewritten criteria, calibration rules for mixed-adoption teams, and conversation scripts. For the general review document use performance-review; for redesigning the role itself use role-redesign-for-ai.
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。
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when batch-mapping gene IDs across species, or when comparing the resources for consensus calls. Encodes confidence-level semantics, 1:1 vs 1:many vs many:many, HomoloGene deprecation, and when to defect to de novo computation.
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。
Align protein structures using Foldseek 3Di, TM-align, US-align, DALI, or Foldmason for structural MSA. Predict, score, and superpose backbone coordinates when sequence identity is below the twilight zone or remote-homology detection is required. Use when sequence MSA fails (<25% identity), when the dark proteome is the target, when AlphaFoldDB / ESM Atlas search is needed, or when structural superposition is the goal.
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。
Prove a UI that updates before the server answers puts things back and says so when the request fails, and keeps the change when it succeeds. Use when a like, toggle, rename, reorder, delete or add-to-cart updates instantly, when an optimistic update was added or changed, or when a user reports a change that "saved" but was gone after a reload.
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。
Drive and verify an Electron or Tauri desktop app from the inside, including the main-process and Rust IPC calls a browser tool cannot see. Use when a desktop app needs testing, when a feature works in the browser but not in the packaged app, when an IPC or invoke call needs proving, when a desktop screenshot or visual diff is wanted, or when you need a headless run of a desktop UI in CI.
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 Scenario generation is blocked, refused, or returns a moderation or sensitive-content error, when a video is rejected after rendering or its audio track is flagged, when an output is flagged for likeness to a real person or for IP and copyright detection, when the same prompt passes on one model and fails on another, or when a team's own characters, weapons, or props get flagged. Keywords: blocked prompt, content moderation, refused generation, provider filter, 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。
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not triggering or not loading the right context, when you are auditing a skill that is underperforming, or when you want to publish a skill for others. Also triggers when someone asks "how do I make a skill" or "what makes a good skill". Useful for individuals, teams, and anyone publishing skills publicly.
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。
Pre-publish QA framework for content. Brief adherence, voice consistency, fact accuracy, structure and clarity, AI-content audit, SEO and AEO compliance, internal linking and schema validation, QA at scale via sampling, the QA workflow, and the discipline that distinguishes catch-problems QA from checkbox QA. Triggers on editorial QA, content review, pre-publish review, content audit, content QA process, AI-content audit, hallucination check, content sampling, programmatic QA, voice consistency check, brief adherence check. Also triggers when a content team is shipping sloppy work, when AI-co-authored content is reaching publish unaudited, when a QA process burns reviewers out, or when a programmatic SEO set needs sampling discipline. On a voice consistency check, this skill owns checking a draft against an existing voice system at the publish gate; use `brand-voice` when the voice system itself needs defining or documenting.
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。
Produce honest product reviews and buying guides without fabricated first-hand experience, using disclosed evidence tiers: verified specs, owner-experience synthesis at scale, expert triangulation, and hands-on only when true. Use this skill whenever the user wants to write product reviews or buying guides without hands-on access, set up a review methodology, add evidence disclosure to review content, align reviews with Google's reviews system or FTC affiliate disclosure expectations, or decide when Review and Product schema are honest to use. Triggers on product review, buying guide, best-of list, review methodology, evidence basis, hands-on testing, we tested, affiliate review site, review disclosure, methodology block, original research, reviews system. Also triggers when review content claims testing that did not happen, or when an affiliate site needs a trust mechanism that survives 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。
Pick the right ComfyUI startup flags for VRAM, attention, caching, and speed. The full decision matrix for OOM (--novram / --cache-none / --disable-smart-memory), shared-VRAM creep on Windows (--reserve-vram N), model-switching with big text encoders (--cache-none), high-VRAM throughput (--gpu-only / --highvram), and attention-backend selection (--use-sage-attention for speed, --use-pytorch-cross-attention as the highest-quality / Z-Image-safe fallback). Also the acceleration-stack + Blackwell/RTX 5000 (sm_120) notes. Use when a graph OOMs (especially long video like LTX 2 / WAN), when the GPU spills into shared VRAM and slows to a crawl, when switching between models eats all RAM, when Z-Image produces black/garbled output under Sage, or when deciding which attention backend to launch with. Flag names verified against upstream comfy/cli_args.py; see Sources.
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 Geoffrey Moore's chasm-crossing strategy for B2B tech products moving from visionary early adopters to pragmatist mainstream. Use when a product has early traction but stalls before mainstream adoption, when planning a beachhead/niche strategy, when designing whole-product offerings, when positioning against established competitors, or when scaling from innovator usage to industry standard. Triggers include 'stuck between early adopters and mainstream', 'we need a beachhead', 'pragmatist customers won't buy', 'how do we go from 10 to 1000 customers'. NOT for PLG/freemium SaaS (Slack, Notion, Cursor), pure consumer apps, two-sided marketplaces, or AI-native products with bottoms-up viral adoption - their dynamics break the visionary-to-pragmatist sequence.
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。
Share state between components that don't have a direct parent-child parameter relationship, using cascading values, scoped services with change events, or CascadingValueSource via DI. USE WHEN the user needs a CascadingParameter or CascadingValue that works across render mode boundaries, a shopping cart or notification count accessible from multiple pages, a theme or user preference cascaded app-wide, or when components in different parts of the tree must react when shared data changes. Also USE WHEN cascading values aren't reaching interactive children in per-page interactivity mode, or when the user needs to understand scoped vs singleton service lifetime for state on Blazor Server. DO NOT USE for direct parent-child parameter passing or EventCallback (see author-component), for persisting state across prerender-to-interactive transitions (see support-prerendering), or for service abstractions for data fetching in Auto/WebAssembly (see fetch-and-send-data).
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 complete, runnable Volcengine SDK code and provide SDK configuration guidance. Supports Go, Python, PHP, Java, and Node.js. Trigger this skill whenever the user wants to call a Volcengine API, generate Volcengine SDK code, or describes a cloud operation on Volcengine (e.g., "list ECS instances", "create a VPC on Volcengine", "query Volcengine billing with Python"). Also trigger when the user asks about Volcengine SDK configuration and best practices — including retry, timeout, authentication (AK/SK, STS, AssumeRole), proxy, connection pooling, SSL, debug mode, and error handling (e.g., "how to configure retry for Volcengine Go SDK", "volcengine python sdk proxy setup"). Trigger when the user mentions Volcengine service names such as ECS, VPC, CDN, CLB, RDS, Redis, Kafka, billing, IAM, DNS with code generation or SDK usage intent. When the user only needs API specification queries (parameters, error codes, response structures), hand off to the volcengine-api skill. When the user needs CLI-based operations, hand off to the volcengine-cli skill. Supports both Chinese and English 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。
Lifecycle SOP for **per-model prompt artifacts** — the compiled prompts, instructions, few-shot demos, edit-format pins, and embedding-bound indices that change behavior when the underlying LM, dataset, or framework version changes. Activate when adopting compiled prompts (DSPy, GEPA, BootstrapFewShot output), when supporting multiple LMs in production, when a provider deprecates a model snapshot, or when a framework deprecates a config surface (LlamaIndex `ServiceContext` → `Settings`, Aider edit-format defaults). Do NOT activate for one-off raw prompt edits or for truly model-agnostic system prompts that have been swap-tested. Search keywords: prompt portability, model swap, recompile prompt, model deprecation, prompt per model, prompt breaks on new model, version compiled 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。
Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step as deterministic- computable (emit + execute code, feed the result back) vs judgment (stay in prose). Use when designing or debugging an agent step that does arithmetic/parsing/data transforms, when prose reasoning hallucinates a computation (under-coding), or when a sandbox round- trip is wasted on a judgment task (over-coding). Search keywords: code interpreter, agent does math wrong, calculator hallucination, when to run code vs reason, program of thought, PoT, tool vs reasoning.
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 your human partner has explicitly opted into exploratory or feasibility mode - a compute-heavy simulation, an unproven pipeline, an unbenchmarked solver, an untested cluster job - or when whether the work can run at all is still unknown, when a plan's largest configuration has never been executed, when a memory or wall-clock ceiling is estimated rather than measured, or when someone proposes pre-registering over runs that have never happened
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。