Digest
v1.0.0Curate external information into personalized updates. Auto-learns format, timing, sources, and depth preferences.
⭐ 2· 758·2 current·3 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name and description match the instructions: the skill curates external content into personalized digests. It only references local preference files (preferences.md, dimensions.md) that are included and needed for personalization. There are no unexpected environment variables, binaries, or config paths required.
Instruction Scope
SKILL.md stays on-task (Source → Filter → Prioritize → Format → Deliver → Learn) and only references the included preference/dimension files. It is somewhat vague about the mechanics of 'Pull from configured feeds, news, social' and 'Deliver' to channels (Telegram/Slack/email) — it does not specify how credentials or channel integrations are obtained or used. The instructions do explicitly tell the agent to update preferences.md (writing its own file), which is coherent for a learning preference system.
Install Mechanism
Instruction-only skill with no install spec and no code files. This minimizes disk-write/execution risk. Nothing is downloaded or installed by the skill itself.
Credentials
The skill requires no environment variables, credentials, or config paths. That is proportionate to the instruction set given. Note: delivering to external channels or scraping private sources would normally require credentials, but the skill does not request them — it likely expects the platform or other skills to provide channel integrations. Verify where those credentials live on your agent platform before connecting to private sources.
Persistence & Privilege
always is false and model invocation is allowed (default). The skill writes/updates its own preferences.md, which is normal for a learning digest. It does not request system-wide privileges or modify other skills' configs.
Assessment
This skill is internally coherent: it reads and updates the included preferences files and outlines a reasonable digest workflow. Before installing, confirm the following: 1) How will the agent fetch external sources (web browsing, platform connectors, or separate skills)? If you plan to include paywalled or private sources, understand where credentials must be stored and who has access. 2) How will delivery channels (Slack, Telegram, email) be connected — check whether those credentials live on the agent platform and review their scope. 3) Because the skill can update preferences.md, review or back up that file if you want an audit trail of changes. 4) Monitor initial runs (or restrict autonomous invocation) to ensure it only pulls from sources you expect and doesn't post to channels you didn't authorize. If any of the above integration details are unclear, treat the setup as incomplete until you confirm where credentials and connectors live.Like a lobster shell, security has layers — review code before you run it.
latestvk972jeq74dtwywrfgj5pss8nn98116nq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.