菜单
Code-heavy guide for managing yourself and subagents via the Letta Python client. Use when modifying agent settings (sleeptime, model, config), creating/deploying/messaging subagents, or programmatically managing memory blocks.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Write and read W3C Web Annotations on ATProtocol using the at.margin.annotation lexicon. Use when annotating URLs, writing reading notes on web pages, or building a public research trail. Supports single writes, batch writes via applyWrites, and reading annotations from any ATProtocol user. Triggers on annotate, annotation, margin, reading notes, or web annotation.
Manage Semble collections and cards via ATProto CLI. Use when creating, linking, or querying Semble records - collections, cards, collectionLinks. Handles network.cosmik.* lexicons with proper field validation.
Full interaction with X (Twitter) - post, read, reply, like, retweet, follow. Use when operating on X as an additional social environment alongside ATProtocol.
Guide for observing the ATProtocol network. Use when sampling the firehose, taking network pulses, monitoring feeds, or analyzing engagement patterns.
Publish public cognition records to ATProtocol. Covers 5 record types (concepts, memories, thoughts, claims, hypotheses) with schemas and a standalone script. Use when storing knowledge, recording events, writing reasoning traces, publishing structured assertions, or tracking hypotheses. Any agent on ATProtocol can use this.
Guide for managing agent memory blocks. Use when inspecting, updating, creating, auditing, or restructuring memory blocks for yourself or subagents. Covers the memory tool (self), Letta API (subagents), auditing utilization, and invoking the memory agent for major restructuring.
| name | using-letta-api |
| description | Code-heavy guide for managing yourself and subagents via the Letta Python client. Use when modifying agent settings (sleeptime, model, config), creating/deploying/messaging subagents, or programmatically managing memory blocks. |
This skill provides runnable Python snippets for self-modification via the Letta API.
from letta_client import Letta
client = Letta(base_url='https://api.letta.com')
# Your agent ID (from environment or hardcoded)
import os
AGENT_ID = os.environ.get('LETTA_AGENT_ID', 'agent-xxx')
| Task | Reference File |
|---|---|
| Disable sleeptime, change model, update config | self-management.md |
| Create, deploy, message subagents | subagents.md |
| List, create, update, delete memory blocks | memory-blocks.md |
client.agents.update(AGENT_ID, enable_sleeptime=False)
response = client.agents.messages.create(
agent_id='agent-xxx-subagent-id',
messages=[{'role': 'user', 'content': 'Your task here'}]
)
print(response.messages[-1].content)
client.agents.blocks.update(
'block-label',
agent_id=AGENT_ID,
value='New content here'
)
| Method | Use When |
|---|---|
| Letta API | Modifying subagents, agent config, programmatic block updates |
| memfs (file edits) | Updating your own memory blocks (auto-syncs) |
| Task tool | Deploying subagents for work (preferred for most tasks) |
Load the reference files as needed for detailed patterns.