ℹ
Purpose & Capability
Name/description (save & retrieve read-later items) aligns with instructions to read/write a markdown file in the workspace or home directory. However, the SKILL.md requires automatically fetching and analyzing remote URLs using 'kimi_fetch' which is not declared as a required binary/dependency — that is an unexplained requirement.
!
Instruction Scope
Instructions explicitly read and write ~/read-it-later.md or a workspace read-it-later.md (expected). They also instruct automatic fetching of URL content and content analysis. Automatic fetching implies network access and retrieval of potentially large or sensitive web content; the SKILL.md does not declare how fetched data is handled beyond local storage nor what tool/environment will perform the fetch. No instructions attempt to read unrelated system files, but the unspecified fetch step broadens the runtime surface.
✓
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest install risk. Nothing is downloaded or written by an installer per the provided metadata.
✓
Credentials
Skill requests no environment variables, credentials, or special config paths — this is proportionate to a local markdown-based read-later tool. The only oddity is the use of 'kimi_fetch' without declaring it as a required binary or dependency.
✓
Persistence & Privilege
always is false and the skill is user-invocable; it does read/write a file in the user's home or workspace but does not request elevated or persistent platform-level privileges. No evidence it would modify other skills or global agent configuration.
What to consider before installing
This skill is mostly coherent for a local 'read it later' markdown-based tool: it will read and update ~/read-it-later.md or a workspace file and can mark items read/archived. Two things to check before installing or enabling it: (1) The SKILL.md says it will automatically fetch and analyze webpage content using a tool called 'kimi_fetch' but that tool is not declared — ask what 'kimi_fetch' is (a platform tool, an external binary, or a hidden dependency) and whether network access is required. Automatic fetching will retrieve remote content and store analysis locally, which may expose sensitive page contents to the agent's runtime. (2) The skill's source is unknown and there is no homepage; if you care about provenance or privacy, prefer skills with identified authorship or inspect the implementation. If you proceed, ensure you are comfortable with the agent having permission to access the network and to read/write the indicated file, and consider keeping backups of read-it-later.md or restricting the skill to a dedicated workspace.
