supacortex
4
总安装量
4
周安装量
#51675
全站排名
安装命令
npx skills add https://github.com/monorepo-labs/skills --skill supacortex
Agent 安装分布
gemini-cli
4
claude-code
4
github-copilot
4
codex
4
kimi-cli
4
cursor
4
Skill 文档
Supacortex â CLI Skill
Supacortex is a personal memory layer. Two CLI commands: bookmarks and conversations.
Setup
npm i -g @supacortex/cli
scx login
1. Bookmarks (scx bookmarks)
Save and search bookmarks (links, YouTube videos).
Commands
List bookmarks
scx bookmarks list [--search "<query>"] [--type <tweet|link|youtube>] [--limit <n>] [--offset <n>] [--pretty]
Add a bookmark
scx bookmarks add <url> [--pretty]
Get a bookmark by ID
scx bookmarks get <id> [--pretty]
Delete a bookmark
scx bookmarks delete <id> [--pretty]
When to use bookmarks
- User asks to save a link or YouTube video
- User wants to search their saved content
- When you need to reference previously saved URLs
2. Conversations (scx conversation)
Save summaries of AI chat sessions. Every conversation has a tier that determines its depth.
Tiers
| Tier | When to use | Content format |
|---|---|---|
brief |
Throwaway queries, quick lookups | Single sentence: “Asked about JSON parsing in Bun” |
summary |
Most working sessions | Markdown â 3-8 bullet points covering what was discussed, decided, and found |
detailed |
Deep sessions with architectural decisions, research findings | Markdown â full structured document with headings, reasoning, code snippets, follow-ups |
Commands
Save a conversation
scx conversation add "<content>" --tier <brief|summary|detailed> [--title "<title>"] [--metadata '<json>'] [--pretty]
The --tier flag is required. It maps to memory types: conversation_brief, conversation_summary, conversation_detailed.
Examples:
# Brief â one sentence
scx conversation add "Helped debug CORS issue in Hono API" --tier brief
# Summary â bullet points
scx conversation add "- Set up memory table with tsvector search
- Added triggers for auto search vector generation
- Created API routes for CRUD
- Decided on hybrid schema approach" \
--tier summary \
--title "Memory system setup" \
--metadata '{"source": "claude-code"}'
# Detailed â full document
scx conversation add "## Memory Architecture Decision..." --tier detailed --title "Memory layer brainstorm"
List conversations
scx conversation list [--search "<query>"] [--tier <brief|summary|detailed>] [--limit <n>] [--offset <n>] [--pretty]
Get a conversation by ID
scx conversation get <id> [--pretty]
Update a conversation
scx conversation update <id> [--title "<title>"] [--content "<content>"] [--tier <tier>] [--metadata '<json>'] [--pretty]
Delete a conversation
scx conversation delete <id> [--pretty]
When to save conversations
Save when the user says:
- “save to cortex” / “save to supacortex”
- “save this session” / “remember this”
- “log this conversation”
When to recall conversations
Pull past conversations when the user says:
- “check my conversation about X”
- “pull the X conversation”
- “get the summary for X”
- “what did we work on last time?”
Metadata
Metadata is freeform JSON passed via --metadata. The AI decides what to store. Common fields:
sourceâ where this was captured (“claude-code”, “chatgpt”, “opencode”)tagsâ array of topic tagsprojectâ which project the conversation was about (e.g. “supacortex”, “supalytics”)categoryâ topic area: “project”, “life”, “general”, “learning”, “work”
Consistent verbs across all commands
Both commands (bookmarks, conversation) support: list, add, get, delete.
conversation also supports: update.
All commands output JSON by default (optimized for AI agents). Use --pretty for human-readable output.