1,914 件 ・ 関連度順
概要と使いどころ
Automate and research the GitHub Copilot app desktop experience. Use for driving Copilot App sessions, creating isolated app experiments, mapping app UI/accessibility controls, taking app screenshots, saving PNG captures, optimizing WebP images, testing prompts without submitting, using app/session APIs, canvases, automations, macOS Accessibility, AppleScript, and safe end-to-end Copilot App workflow probes.
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。
Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead.
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 marketing audit of a third-party local business (café, roaster, shop, restaurant, hotel, clinic, home service) from a Google Maps, share.google or website link — located DataForSEO rankings, map packs, search volume and seasonality, listings, reviews, backlinks, AI-assistant answers and a site crawl, plus direct checks (real-browser access, page weight, store shipping quotes, email DNS, mobile screenshots) — delivered as an owner-facing report with priced offers, an exact change list and a 12-week plan, optionally localized and bilingual. Use when "audit this business", "full marketing audit of <business>", "prospect audit", "local business audit", "use DataForSEO for the hard SEO data", "go deeper", "rerun it for local <market>", "also in Spanish", "give me the offers, changes and 3 month plan", or a business link arrives with "audit". For auditing your own product across channels use /kai-audit.
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。
UI Component Editor workflow. Use when the user wants to implement a React component from a screenshot in an SDD project, iterating visually with live preview.
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。
Fallback local Playwright daemon for real-browser visual QA / screenshots / smoke. Use ONLY when the host platform has no native browser mode — prefer the host browser first.
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 need visual QA, screenshots, or post-deploy smoke testing through a real browser with Playwright.
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 product pitch videos for the Erode project from screenshots. Use this skill whenever the user wants to create, update, or regenerate the product demo video, landing page animation, or pitch clip for erode.dev or the GitHub repo. Also trigger when the user mentions "product video", "demo video", "pitch video", "update the video", "regenerate video", or "landing page animation" in the context of Erode.
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。
Browserless turns Chrome, Firefox, and WebKit into a remote browser service you can self-host or consume as a managed platform. It gives automation stacks a stable WebSocket and REST surface for screenshots, PDFs, scraping, persistent sessions, and debugging without hand-managing browser fleets.
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。
Automates browser tasks with Browser Use, the open-source library that connects LLM reasoning to Playwright-driven web actions. Useful for navigating sites, filling forms, extracting structured page data, and running agentic browser workflows with screenshots and stateful sessions.
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。
Drives headless Chrome via the Browserless.io API for scraping dynamic SPAs. Uses /content, /screenshot, and /pdf endpoints with stealth mode. Manages session tokens and concurrent connection limits.
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。
BackstopJS gives agents a repeatable way to capture reference screenshots, compare UI states, and flag visual regressions before changes ship. This skill centers on the real BackstopJS project and turns browser-based layout comparison into a structured QA workflow for web teams.
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 repeatable evaluation suite for browser agents against static web task snapshots instead of judging them from demos or one-off 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。
Auto-Editor is a command-line application that automatically edits video and audio by analyzing loudness, motion, and other signals to cut dead space. It exports to Premiere Pro, DaVinci Resolve, Final Cut Pro, ShotCut, and Kdenlive timelines.
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。
Diagnoses firing AWS CloudWatch alarms by querying CloudWatch Metrics, alarm history, and related AWS Config resource snapshots via the AWS SDK. Correlates metric anomalies with recent infrastructure changes to suggest root cause hypotheses. Outputs a structured incident summary with remediation options.
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。
Give coding agents a design skill for greenfield UI, component work, audits, redesigns, and visual DNA extraction from screenshots or URLs.
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 the MixerSceneIntent, approval state, JSON schema, CLI examples, audit entries, and tests for AI-Controlled Party mixer/Soundcraft Ui24R scene arming. Use whenever a task mentions mixer scenes, Ui24R snapshots/cues, operator-approved mixer control, show-director contract updates, schema updates, dry-run CLI shape, or follow-ups that revise this 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。
Design the Soundcraft Ui24R adapter boundary for AI-Controlled Party: dry-run, Bitfocus Companion, direct Node bridge, connection health, config, failure handling, and live-validation gates. Use whenever a task mentions Soundcraft, Ui24R, snapshots, cues, Companion, soundcraft-ui-connection, mixer bridge, or revising the adapter design.
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。
Orchestrates the AI-Controlled Party mixer/Soundcraft Ui24R design team. Use whenever the user wants to design, update, refine, re-run, or implement-plan the Soundcraft Ui24R scene-arming expansion, mixer-aware AI party, operator-approved mixer cues, snapshots/cues/show control, Companion bridge, or any follow-up based on prior mixer design results. Produces a spec for tdmcp-pipeline; does not implement runtime 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。
AI browser automation via CDP. Use when you need to control a browser, navigate pages, click elements, fill forms, extract content, or take screenshots.
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 says 'run an seo aeo audit', 'improve my search visibility', 'optimize my site for search engines', or wants the site cited by AI answer engines. Audits on-page SEO and AEO, generates schema markup, and applies fixes on duplicates for review after a snapshot.
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 says 'run a sale', 'discount this category', 'set up a coupon', 'reprice these products', 'end the sale', or asks what a discount would cost them. Plans the price change, shows it as a preview before anything moves, writes it with a snapshot, and can put it back.
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 says 'send this to my client', 'get feedback on this page', 'send a review link', 'what did the client say', or 'work through the review notes'. Sends a Murmur review link, reads the notes reviewers pin to the page, replies, applies each change on a duplicate, and resolves every note with the snapshot of the 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。
Use when the user says 'fix my catalog for ai', 'improve my ai readiness score', 'get my catalog to 90', or 'my products keep getting rejected by google'. Runs an ordered fixlist that writes the missing alt text, descriptions, brands, GTINs, and category mappings, snapshotting before each 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。
Measure Mycelium's own scaffold token cost (CLAUDE.md + engine + harness + canvas + memory) and surface a structured estimate. One-shot audit; pair with /framework-health for trend tracking.
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。