Daily Poem
v1.0.1Daily Poem delivers one carefully chosen poem every morning — rotating between Chinese classical poetry (唐诗宋词), modern Chinese verse, and English poems — com...
⭐ 0· 76·0 current·0 all-time
byCosmos Fang@cosmofang
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (daily poem push and query) align with the included Node scripts and the SKILL.md. The scripts implement prompt-generation, local push-log reading, cron guidance, and enable/disable instructions — all coherent with a poetry push/query skill. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md and scripts limit actions to generating formatted prompts for poem content, reading/updating a local push-log (data/push-log.json), and printing cron commands. They do not call external endpoints, modify other skills, or read unrelated system files. The SKILL.md suggests the agent may use its own knowledge or WebSearch to source poems — that is a content-sourcing choice but remains in scope for a poetry skill.
Install Mechanism
There is no install spec; this is primarily an instruction-and-script package. No downloads, no package installation steps, and no extraction from arbitrary URLs are present.
Credentials
The skill requires no environment variables or external credentials. The only filesystem access is to its own data/push-log.json within the skill directory and to printing cron commands that reference the skill path — both proportional to the stated purpose.
Persistence & Privilege
always is false and the skill does not autonomously alter other skills or system-wide config. It prints openclaw cron commands but does not execute them itself; enabling pushes requires the user to run the provided cron commands, so the skill does not force persistent presence.
Assessment
This skill appears internally consistent and low-risk: review the scripts (they only generate prompts and read a local push-log), and if you enable scheduled pushes, run the printed openclaw cron commands yourself so you know when/where they will run. Note: the agent may use WebSearch or its internal model to source poem text — if you are concerned about copyrighted content, keep in mind the SKILL.md asks to prefer public domain English works and that the agent's behavior (not the scripts) determines sourcing. Finally, confirm where the agent will deliver pushed poems (chat channel, email, etc.) before enabling cron so you understand downstream recipients and privacy implications.Like a lobster shell, security has layers — review code before you run it.
latestvk976we6azxykzkn72stm90kt9h848ctt
License
MIT-0
Free to use, modify, and redistribute. No attribution required.