القائمة
Memory system with daily logs and keyword search. Use to save facts, search past events, or recall user preferences and project context across conversations.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | memory |
| description | Memory system with daily logs and keyword search. Use to save facts, search past events, or recall user preferences and project context across conversations. |
| always | true |
memory/MEMORY.md -- Long-term curated facts (preferences, project context). Always loaded into your context.memory/YYYY-MM-DD.md -- Daily logs. Append-only, one file per day. Search them with memory_search.Use memory_save to store durable facts and context. Content is appended to today's daily log automatically:
memory_save(content="User prefers dark mode. Project uses OAuth2 for auth.")
Use memory_search to find information across all memory files:
memory_search(query="keyword")
Returns matching lines with surrounding context, indicating which file each match came from.
Use memory_read to read a specific memory file:
memory_read(file="MEMORY.md")
memory_read(file="2026-03-13.md")
memory_read(file="2026-03-13.md", max_lines=50)
memory_read(file="list")
Use file="list" to see all available memory files.
When the conversation context approaches its limit, durable facts are automatically saved to today's daily log before compaction. MEMORY.md is not modified automatically.
Platform context for tvOS. No invoke_platform functions are available on Apple TV.
Platform functions available on watchOS. Use invoke_platform to call native watchOS capabilities like local notifications.
Analyze images from local files, URLs, or base64 data. For user-uploaded images, the path is provided in the [image attached] annotation.
Full browser automation via Chrome DevTools Protocol. Navigate pages, interact with UI elements, take screenshots, extract content, manage tabs, emulate devices, handle cookies/storage, monitor network, and control browser state.
Make HTTP requests (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS) to APIs and web services. Use when the user needs to call a REST API, fetch data from an endpoint, send form data, upload files, download files, or test HTTP services.
Create and edit images locally with no AI (programmatic operations). Use when the user wants to create a new image (blank, gradient, solid color), resize an image, draw rectangles or shapes on an image, add a watermark, paste a logo, overlay one image on another, or do any Pillow/ImageMagick-style image operations. Do not use for text-to-image generation — use generate_image (AI) instead.