message-chunker
v1.0.0智能消息分段工具。自动将长消息拆分成多条发送，避免飞书API消息长度限制。当需要发送长消息（如汇报、方案、日志）时自动激活。
⭐ 1· 316·2 current·2 all-time
byCode:Z@as9530272755
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (split long messages for platforms like Feishu) aligns with the provided files and runtime instructions; it does not request unrelated credentials, binaries, or config paths.
Instruction Scope
SKILL.md contains only chunking rules, triggers, simple retry guidance, and configuration pointers (TOOLS.md). It does not instruct reading arbitrary files, accessing unrelated environment variables, or sending data to external endpoints.
Install Mechanism
No install spec and no code files are present (instruction-only), so nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no environment variables, credentials, or config paths. That is proportionate: chunking logic can run using the agent's existing messaging capabilities without extra secrets.
Persistence & Privilege
always is false and the skill does not request persistent system-wide changes or elevated privileges. Behavior described is limited to message-sending logic within the agent's normal operation.
Assessment
This skill is instruction-only and internally consistent with its stated purpose. Before installing, verify how your agent sends messages (so you know which messaging integration/credentials will be used) and test behavior with non-sensitive content. Pay attention to retry rules (the doc suggests retrying on Status 400 — you may want to adjust that to avoid repeated client-error retries), decide where the "failure queue" should be stored, and set appropriate maxChunkSize and continuation markers to avoid confusing recipients. If you need stricter behavior (e.g., never splitting tables or excluding sensitive sections), update the configuration in your TOOLS.md and test thoroughly. If you rely on automated sending, ensure the agent's messaging permissions and rate limits are acceptable.Like a lobster shell, security has layers — review code before you run it.
latestvk9717vqgn50byprh6vjf2ywhn582m9sqv1vk9717vqgn50byprh6vjf2ywhn582m9sq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.