1.7万 件 ・ 関連度順
Control a whole Windows desktop from one persistent Python session with foreground-first input (focus holding, SendInput with pen/message fallbacks), background screenshots, UI Automation, Browser Harness, clipboard paste, PowerShell, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app 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。
Signal-based prospecting — read target companies' public websites for buying signals (ads running, incumbent agency, tech stack, hiring, stale content, missing booking) with evidence URLs, then build a cohort you can explain. Use when asked to "find buying signals", "profile these companies", "which accounts should we target", "build a target list from these domains", or "what changed at these accounts".
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。
Configures JWT Bearer authentication for .NET APIs. Includes token generation, validation, refresh tokens, and user context extraction from claims.
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 guardrail layers — input classifiers, output validators, PII scrubbers, policy rule engines. Use when asked to "add safety filters", "scrub PII from LLM output", or "design content moderation".
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。
SEO audit and keyword strategy — investigate a site's real search opportunities, shortlist candidates, and recommend the one to three changes most likely to grow organic traffic that converts. Evidence-first — metrics come from a tool or are written as unknown. Use when asked to "improve our SEO", "do keyword research", "audit our SEO", "why aren't we ranking", or "what should we fix first for search".
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 a data pipeline — ETL/ELT with extraction, transformation, loading, error handling, and scheduling. Use when asked to "build ETL", "data pipeline", "move data from X to Y", or "sync 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。
Expert 5-dimension design critique — philosophical, scored, actionable. Use when asked to "critique this design", "expert review", "score my design", "how does this look", "is this good design", "design feedback", or "review this UI". Different from /form-audit (which is technical QA for consistency/compliance) — form-critique evaluates design as a craft object: philosophy, hierarchy, execution, function, and innovation each scored 0–10 with a punch list. Add "as a report" or "give me a visual report" to produce an HTML file with SVG radar chart, evidence cards, and Keep/Fix/Quick-wins action lists — useful for design reviews and stakeholder presentations instead of CLI output.
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 user interview — produce an interview guide and synthesize the output into an actionable insight report. Use when asked to "run a user interview", "synthesize these interview notes", "what do users actually want", "build a persona from this feedback", "find the JTBD in these transcripts", or "analyze this interview 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。
User segmentation and persona creation from mixed data sources — analytics, CRM, support tickets, reviews, or any combination. Use when asked to "build personas", "who are our users", "segment our users", "create user profiles", "define user archetypes", or "who is the target user".
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。
Feedback synthesis — cluster support tickets, NPS verbatims, app store reviews, and churn surveys by theme, separate signal from noise, and produce an actionable insight report. Use when asked to "synthesize this feedback", "analyze support tickets", "what are users complaining about", "NPS analysis", "churn feedback synthesis", or "what's the feedback telling us".
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 an ML pipeline — from data to trained model to serving endpoint. Use when asked to "build ML model", "train a model", "prediction pipeline", "classification", or "regression".
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 postmortem from local transcripts — why a run repeated work, ignored the plan, took too long, or cost more than expected. Use when asked "why did that take so long", "why was that so expensive", "what went wrong in that session", "why did the agent redo that", or when preparing a bug report about agent 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。
Spawn-count analytics for the tonone roster — which agents this project actually uses, from local session transcripts. Use when "which agents do we actually use", "show tonone stats", "prune the roster", or before running apex-profile.
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 customer support onboarding flow -- first-contact experience, proactive support touchpoints, and setup success checklist. Use when asked to "design our onboarding support", "how do we support new customers during onboarding", or "reduce early churn from setup failures".
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。
Draft a contract or policy document from a description or template. Use when asked to "draft an NDA", "write an MSA", or "we need a vendor contract".
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。
CTO-level project status from git and codebase state. Use when asked "where are we", "project status", "what's done", or at the start of a work session.
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。
Publish the octop-memory Python package: cut a release branch from develop, bump version, update CHANGELOG / README, open a PR to main; after merge, Actions tag on main (PyPI + GitHub Release) and sync main into develop. Use when the user asks to publish, release, bump version, cut a release, or run /publish.
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 an award-winning "3D scroll" website of ANY kind from ONE prompt — product launch, portfolio, agency, contractor/home-services, restaurant, real estate, personal brand, event, app, etc. Generates a high-end cinematic hero visual + clips (360° orbit, fly-through, reveal, explode, parallax) fitting the site's subject with the Higgsfield MCP, slices them into a scroll-scrubbed canvas frame sequence with ffmpeg, builds a branded multi-section site (Lenis smooth scroll + scroll reveals), and launches it on localhost. Use when the user asks for a "3D scroll" site, scroll-driven hero/reveal, a cinematic landing page, a buckssauce/Apple/Awwwards-style scroll site, or "build me a website like X" — for a product OR a service, person, place, or brand. Trigger words: 3D scroll, scroll animation, cinematic hero, fly-through, turntable, scroll site, landing page, portfolio site, agency site, Higgsfield site.
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。
Add a calculated, formula-based column to a dataframe via the datagrok_exec tool. Use whenever the user asks to compute, derive, add, or create a new column from existing columns — LipE, ratios, log/round, heavy atom count, any expression in the Datagrok formula DSL. Replaces hand-written addNewFloat/addNewInt + for-loop with a single formula-attached column that recomputes when source columns change.
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。
Prepare a Datagrok package so that Claude (or any coding agent) can work on it effectively from a naive prompt
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。
Publish the octop-gateway Python package: cut a release branch from develop, bump version, update CHANGELOG / README, open a PR to main; after merge, Actions tag on main (PyPI + GitHub Release) and sync main into develop. Use when the user asks to publish, release, bump version, cut a release, or run /publish.
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 reviewable modular plant concept layouts from land shape, unit requirements and exclusions. Use for plant design, layout improvement, プラント設計, ユニット配置 and 設計JSON.
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。
GitHub CLI - manage repositories, issues, pull requests, actions, releases, and more from the command line.
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。
Generates publication-quality academic figures (framework diagrams, pipeline illustrations, system architectures, method overviews) from a paper's method text and a target caption, using a local PaperBanana multi-agent pipeline (Retriever → Planner → Stylist → Visualizer → Critic).
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。