2,023 件 ・ 関連度順
概要と使いどころ
Exploit AI applications using Indirect Prompt Injection. This skill focuses on hiding malicious instructions within data sources (web pages, documents, emails) that the LLM processes, causing the AI to execute unintended actions or leak data without direct user interaction.
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 for indirect prompt injection vulnerabilities where malicious instructions are injected through external data sources (websites, emails, documents, database records) that the LLM processes. Use this skill when assessing LLM-integrated applications that process user-generated content, retrieve web pages, parse emails, or read documents. Covers injection via web content, email bodies, user profiles, and database records that are fed to LLM context.
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。
Clickjacking playbook. Use when testing whether target pages can be framed, whether X-Frame-Options or CSP frame-ancestors are properly configured, and whether UI redress attacks can trigger sensitive actions.
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。
Activate for any work in the tests/e2e/ directory: creating or editing test files (tests/*.test.ts), page objects (pages/), helpers (helpers/), or vitest config. Enforces agent-browser conventions specific to this project.
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。
Legal, security, privacy, and deliverability requirements every delivered app must satisfy — legal pages, PII/deletion rights, CSP/Trusted-Types/Zod, AI-agent security, RFC7807 errors, email domain auth.
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。
Extract real brands (Wayback for rebuilds). Copy system, headline/CTA rules, trust surfaces, legal pages, SEO+structured data, anti-AI-slop, microcopy, DESIGN.md, W3C DTCG tokens, pSEO 5 types, GEO/AI 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。
Audit technical, on-page, and AI-search SEO for pages, sites, and content. Use when the user asks for `/seo-audit`, `/ai-seo`, SEO review, keyword targeting, heading structure, metadata, internal linking, content gaps, AEO, GEO, LLMO, or competitor SEO comparisons.
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。
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
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 this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this 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。
Write marketing copy for pages, campaigns, product launches, ads, and email sequences. Use when the user asks for `/copywriting`, landing page copy, launch copy, ad variations, direct-response frameworks, AIDA, PAS, BAB, or refreshing existing marketing content.
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 and fix failed Pharos GitHub Actions, adaptive PR checks, Cloudflare deploys, Pages releases, or scheduled automation. Use when a gate/run failed or the user asks to retrigger and iterate until clear.
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 or refresh evidence-grounded editorial summaries for stablecoin detail pages, including draining the AI-summary candidate queue after scoring changes.
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 wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI 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。
Discovery-only global trending extension for Gaia. Snapshots configured external skill sources, prioritizes five-candidate pages for L4 review, and stops before trust, evidence, intake, or registry mutation.
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 this skill whenever the user wants to see how their branch will look on the live Gaia website before merging — "preview this branch", "show me what this looks like", "deploy a preview", "trigger a design preview", "can I see the site with these changes", "preview the skill profile", "check how this renders on the site", "spin up a preview deployment". This skill dispatches a Cloudflare Worker preview deployment for the current branch via GitHub Actions — no local build tooling required. Ideal for containerized environments, design reviews, and confirming that newly curated skills or profile pages render correctly before a PR is merged to main. The preview does NOT regenerate docs; it deploys `docs/` from the branch as-is. If your change depends on regenerated Class S artifacts, run `gaia dev docs` and commit those first — the preview then reflects them.
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 maintain a persistent, interlinked markdown wiki (second brain / research notebook / personal knowledge base) from raw sources. Use this skill when the user wants to ingest an article / paper / note / URL / PDF into their wiki, ask a question against their wiki, lint/health-check their wiki, or set up a new wiki from a folder. Triggers include phrases like "add this to my wiki", "ingest this", "file this article", "update my notes with this", "what does my wiki say about X", "health-check my wiki", "find stale/orphan pages", or any workflow involving a `raw/` source folder, `wiki/` markdown folder, `index.md`, or `log.md`. Compatible with Obsidian vaults.
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。
Health-check a persistent markdown wiki. Use this when the user wants to find orphan notes, dangling links, missing pages, graph gaps, contradictions to review, or general wiki maintenance opportunities.
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 visually polished, editable PPT/PPTX presentations in a clean PPTPRO style. Use when the user asks for a beautiful, designed, non-generic PowerPoint deck, especially course presentations, reading applications, source-backed slides, scripts matched to slide pages, or requests to avoid AI-looking beige/card templates and repeatedly check visual quality.
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。
Runs synapse-docs, /simplify, sync-plugin-skills, and github-pages-sync in parallel for synapse-a2a development workflows. Use when you need doc updates, code simplification, plugin skill sync, and site-docs sync at the same time.
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。
This skill provides guidance for using Chrome DevTools MCP for browser debugging and automation. Use when debugging web pages, analyzing performance, inspecting network requests, viewing console messages, or interacting with Chrome DevTools features programmatically.
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。
This skill enables web scraping and content extraction using Firecrawl API directly via curl. Use when scraping web pages, crawling websites, or extracting structured data. MCP server not required.
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。
This skill provides guidance for using Playwright MCP for browser automation. Use when navigating web pages, interacting with web elements, taking screenshots, filling forms, running browser tests, or automating any browser-based 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。
Deobfuscates malicious JavaScript from droppers, web pages, and HTA/scriptlets: unrolling string-array and char-code encodings, resolving eval/Function chains, and statically recovering payloads and URLs without executing untrusted code. Activates for requests to deobfuscate JavaScript, decode obfuscated JS, or analyze a malicious script dropper.
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。
Analyzes two modern delivery techniques: malicious OneNote (.one) attachments with embedded payloads behind fake buttons, and HTML smuggling pages that reconstruct payloads in the browser from embedded blobs. Activates for requests to analyze a malicious OneNote file, detect HTML smuggling, or extract a smuggled/embedded payload.
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。