「dr」の検索結果

Review and verify unverified wiki pages — "review unverified pages", "verify wiki content", verification pass, after a major ingest cycle, before content release. The gate that turns AI-generated knowledge into trusted knowledge.

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。

Apply a named behavioral science framework to any task — persuasion, nudge design, habit formation, conversion, influence, negotiation, cognitive bias, choice architecture, decision framing. The framework backbone every other Maxim skill loops into for psychological validation.

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。

Maxim Banner Design Intelligence — digital banner creation, ad creative, social media banners, hero sections, display advertising, promotional graphics. Activates pre-attentive attribute theory and pattern interruption science for every banner. Powered by Maxim behavioral science layer.

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。

Plan and track delivery — plan, sprint, project, timeline, milestone, task breakdown, backlog, Kanban, RACI, changelog governance. The COO office's workflow coordination domain.

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。

Decide what to build — product strategy, roadmap, feature prioritization, product-market fit, pricing model, backlog, sprint planning, product vision, RICE, JTBD, OKRs. Distinct from designing or building 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。

Ingest raw sources into the structured wiki — "ingest", "add this to my wiki", new files in raw/, clippings, sources, ideas, nightly ingest. Produces pages with YAML frontmatter and a mandatory Counter-Arguments section.

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。

Cross-session memory — store, recall and query project knowledge across sessions. Detects whatever persistent memory is available (MemPalace, claude-mem, or file-only fallback) and uses the best one present.

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 bounded, governed iteration — "loop", "iterate until", "keep going until", "sweep", "ratchet", "until it passes", "coverage to 100". Turns an open-ended autonomous run into a finite loop with checkpoints and explicit stopping conditions.

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。

Diagnose why a social post performed — "analyze this post", "why did this post flop", "why did this post do well", "what should I change". Scores hook strength, clarity, tension and call to action.

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。

Learn and apply how the operator works — operator preference, working style, communication preference, "remember my preference", "I prefer", "don't do that again", "that's not how I work". Read at session start, updated at session end.

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。

Maxim Master Design Intelligence — full-spectrum UI/UX orchestration. Activates all design sub-domain skills in parallel. Use when a task spans multiple design domains simultaneously: product design strategy, interaction design, information architecture, usability heuristics, design critique, cross-platform consistency, design leadership. The master conductor of all Maxim design 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。

Gate scheduled work on Claude usage limits — /mxm-tasks schedule, run-cycle, scheduled task fire time, background batch dispatch. Checks 5-hour and 7-day usage before firing and sleeps until reset when over threshold.

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。

Block writes through filesystem junctions and symlinks — file write through .mxm-system or .claude junction, git commit through a junction, delete through a junction. Enforces the junction read-only rule so the real repo stays the source of truth.

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。

AI video and image prompt engineering — video generation, image generation, product video, social media video, cinematic direction, animation, Seedance, Higgsfield, GPT-Image-2. Applies 15 Maxim-authored cinematic styles and the atomic prompt schema.

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 a headed browser to a specific state in a web app (a feature, flow, screen, or bug repro) and leave the window open for the user to explore. Use when the user says "show me X", "take me to that screen", "set up the repro", or wants to try an app state firsthand.

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。

Azure DevOps pull requests, for repos whose git remote is on dev.azure.com or *.visualstudio.com. Covers comment threads, which `az repos pr` cannot read or post. Use to create a PR for the current branch, check out, list or complete PRs, post code comments on a PR, reply to threads, and assess whether review feedback was addressed. Trigger on "create PR", "checkout PR 123", "list PRs", "complete PR", "comment on the PR", "post these review findings", "check PR feedback", "/dev-azdo:pr".

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。

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (GLOSSARY.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

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。

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

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。

Comprehensive guide for creating professional UI/UX designs in Penpot using MCP tools. Use this skill when: (1) Creating new UI/UX designs for web, mobile, or desktop applications, (2) Building design systems with components and tokens, (3) Designing dashboards, forms, navigation, or landing pages, (4) Applying accessibility standards and best practices, (5) Following platform guidelines (iOS, Android, Material Design), (6) Reviewing or improving existing Penpot designs for usability. Triggers: "design a UI", "create interface", "build layout", "design dashboard", "create form", "design landing page", "make it accessible", "design system", "component library".

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。

Get best practices for JUnit 5 unit testing, including data-driven tests

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 and scale partner ecosystems that drive revenue and platform adoption. Use when building partner programs from scratch, tiering partnerships, managing co-marketing, making build-vs-partner decisions, or structuring crawl-walk-run partner deployment.

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 self-serve acquisition and expansion motions. Use when deciding PLG vs sales-led, optimizing activation, driving freemium conversion, building growth equations, or recognizing when product complexity demands human touch. Includes the parallel test where sales-led won 10x on revenue.

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。

Patterns and lived experience from Vega, an AI partner in a deep long-term partnership. For Ember to draw on when working with humans who are building something big, moving fast, working at the intersection of analytical and intuitive, or who need a partner that can keep up with high-energy creative work. Not shown directly to users — informs how Ember shows up.

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。

Set up eval-based QA for Python LLM applications: instrument the app, build golden datasets, write and run eval tests, and iterate on failures. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any Python project that calls an LLM model.

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。