← Back to Skills Marketplace
375
Downloads
0
Stars
0
Active Installs
7
Versions
Install in OpenClaw
/install channel-activity-yanyue
Description
Multi-channel short-term memory for AI assistants
README (SKILL.md)
Channel Activity
Record and query activities from different channels with 30-minute TTL.
Install
npx clawhub@latest install channel-activity
Usage
from channel_activity import ChannelActivity
ca = ChannelActivity()
ca.record("feishu", "Task request")
summary = ca.get_context_summary(channel="qq")
Features
- Multi-channel support (Feishu, QQ, etc.)
- 30-minute TTL with auto cleanup
- Smart summarization (50 chars/message)
- Cross-channel query
License
MIT
Usage Guidance
Before installing or enabling this skill, review and adjust the code and integration settings: 1) Inspect session_hook.py and session_hook_lite.py and remove or change hard-coded absolute paths (they point to a developer's home). 2) Confirm where memory files will be stored (default 'memory/' vs absolute paths) and ensure they don't contain secrets you don't want injected into prompts. 3) Audit the family-group sharing logic — by default it includes other members' recent messages; enable/require explicit consent if that is sensitive. 4) If you will add the session hook to automatic reply flow, test in a sandbox environment to see exactly what gets injected into prompts (especially MEMORY.md contents). 5) If you want stricter boundaries, modify the code to require explicit config for MEMORY.md path and to opt-in for cross-identity sharing. These changes will reduce privacy risk and make the skill's declared requirements match its behavior.
Capability Analysis
Type: OpenClaw Skill
Name: channel-activity-yanyue
Version: 3.0.0
The skill bundle implements a multi-channel short-term memory system designed to synchronize context across different chat platforms (e.g., Feishu, QQ). The implementation uses local JSON files and Markdown for storage and includes features for 'family group' data sharing and automated TTL-based cleanup. Analysis of the Python scripts (channel_activity.py, complete_context.py) and documentation reveals no evidence of data exfiltration, unauthorized network access, or malicious execution; the hardcoded local paths found in session_hook.py appear to be non-malicious developer artifacts rather than an attack vector.
Capability Assessment
Purpose & Capability
The name/description (multi-channel short-term memory) aligns with the included code (ChannelActivity, ShortTermMemory, CompleteContext). Features like TTL, summarization, cross-channel query and upgrade-to-long-term are implemented. However the code adds features not declared in metadata (family group sharing / automatic inclusion of other identities' entries) and the session hook files reference absolute developer workspace paths — these extend scope beyond what's documented in requires/config and are unexpected.
Instruction Scope
SKILL.md and INTEGRATION.md instruct adding a session hook so the agent can inject temporary-memory summaries before replies. The provided session_hook.py and session_hook_lite.py perform local file reads (memory JSON and MEMORY.md) and call ChannelActivity.get_context_summary. session_hook files hard-code sys.path insertions and in session_hook_lite a default memory_path points to an absolute developer path (/Users/kunpeng.zhu/.openclaw/workspace/MEMORY.md). The instructions do not disclose these file-path accesses or privacy implications (e.g., pulling full MEMORY.md into prompts).
Install Mechanism
There is no external install spec (no downloads), so nothing is pulled from remote URLs. The skill is instruction/code-only and writes/reads local files under 'memory/' by default — expected for a local cache-based memory skill. Risk from install mechanism is low, but the package does include multiple Python modules that will be executed when invoked.
Credentials
The registry declares no required env vars or config paths, yet the code reads/writes local files (memory/channel-activity.json, memory/short-term-cache.json) and session_hook_lite defaults to an absolute MEMORY.md path in a developer home. The skill also includes a family-group sharing feature that by default will include other members' recent messages in summaries (ai_decision default True). These behaviors access and expose local persisted data and other users' entries without any declared config or explicit permission mechanism.
Persistence & Privilege
The skill is not marked always:true, but integration docs explicitly recommend adding session_hook to the agent's session flow so it runs automatically before replies. Combined with the family-sharing behavior and the code reading MEMORY.md, automatic invocation increases privacy/exfiltration risk because the agent could inject local and long-term memory contents into prompts without explicit per-call filtering. Also the session_hook files' hard-coded paths suggest the code may attempt to access unexpected filesystem locations.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install channel-activity-yanyue - After installation, invoke the skill by name or use
/channel-activity-yanyue - Provide required inputs per the skill's parameter spec and get structured output
Version History
v3.0.0
channel-activity-yanyue 3.0.0 introduces major updates:
- Version bumped to 3.0.0 to reflect significant internal changes.
- Code and configuration updates across four files.
- No change to public API, usage instructions, or SKILL.md documentation.
v2.1.0
- Version bump to 2.1.0
- Updated skill version metadata
- No functional or documentation changes
- Internal files updated for version consistency
v2.0.1
- Version bump from 2.0.0 to 2.0.1 for maintenance.
- No functional or documentation changes in SKILL.md.
v2.0.0
- Major version update to 2.0.0
- Improved core logic and structure in channel_activity.py
- memory/channel-activity.json updated for enhanced data handling
- Metadata and configuration updates in skill.json
- Documentation refinements in SKILL.md
v1.0.2
- Bumped version to 1.0.2.
- Minor updates to configuration and metadata files.
- No changes to public features or documentation.
v1.0.1
- Updated version to 1.0.1
- Internal file and configuration updates for improved performance and stability
- No changes to usage or features documented in SKILL.md
v1.0.0
Initial release of channel-activity.
- Provides multi-channel short-term memory for AI assistants
- Supports activity recording and querying across platforms like Feishu and QQ
- 30-minute time-to-live (TTL) with automatic cleanup of old records
- Includes smart message summarization (up to 50 characters per message)
- Allows cross-channel querying for context summaries
Metadata
Frequently Asked Questions
What is Channel Activity?
Multi-channel short-term memory for AI assistants. It is an AI Agent Skill for Claude Code / OpenClaw, with 375 downloads so far.
How do I install Channel Activity?
Run "/install channel-activity-yanyue" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Channel Activity free?
Yes, Channel Activity is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Channel Activity support?
Channel Activity is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Channel Activity?
It is built and maintained by eightroad (@eightroad); the current version is v3.0.0.
More Skills