daily-editor
v1.0.3运行一个私人编辑部，把每日信息整理成 A4 竖版 PDF 日报，支持自定义板块、克制稳妥的编辑判断、更安全无害的包装方式，以及指向原始报道的来源链接。适用于用户提到 私人编辑部、每日推送、日报 PDF、信息编排、A4 单页简报、自定义板块、今日简报、单页快报、newsletter-style digest、dai...
⭐ 0· 114·0 current·0 all-time
byIgloos@igloomatics
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (daily-editor / 把每日信息整理成 A4 PDF 日报) aligns with the SKILL.md and supporting files. Templates, layout guidance, scheduling notes, and editorial rules are all proportional to a PDF editorial generator. There are no unrelated required binaries, env vars, or external services requested.
Instruction Scope
The instructions are detailed and remain focused on editorial judgment, layout, and PDF generation. They explicitly instruct saving PDFs locally, producing preview artifacts, and producing scheduler commands (launchd/cron) when asked. They do not instruct reading unrelated system files or sending data to external endpoints, nor do they demand secrets. Users should note that following the scheduling guidance implies creating filesystem artifacts and possibly scheduling jobs if the agent is allowed to act beyond text generation.
Install Mechanism
No install spec and no code files — instruction-only. This is low-risk from an installation perspective: nothing will be downloaded or written by an automated installer as part of skill setup.
Credentials
The skill requests no environment variables, credentials, or config paths. All required inputs are user-provided parameters (title, date, sections, etc.) or defaults. There are no disproportionate secret requests.
Persistence & Privilege
always:false and no special privileges are requested. The SKILL.md includes guidance for generating scheduler commands and saving files, which could lead to persistent scheduled runs if the agent is later authorized to execute those commands — this is a functional feature, not an unexplained privileged request. If you permit autonomous execution, be aware the agent might create files or schedule tasks per user instructions.
Assessment
This skill is internally consistent and focused on producing A4 PDF daily briefs. Before enabling autonomous runs, consider: (1) Do you want the agent to write files or create scheduler entries on your machine? If not, restrict the agent to manual, user-invoked runs. (2) If you expect the skill to fetch web articles automatically, provide URLs or explicit permission — the skill itself contains no web-scraping code. (3) Confirm output path and preview preference so generated commands don't write to unexpected locations. (4) Avoid supplying any credentials; the skill doesn't require them. If you need stronger guarantees, run the first few editions manually and review generated PDF and any scheduler instructions before permitting automatic execution.Like a lobster shell, security has layers — review code before you run it.
latestvk972ccmvmp3j16ex5j1bwhj32x832am0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.