tutor-for-all

v1.0.0

根据你的学习目标和时间,制定个性化课程及计划,跟踪进度,答疑解惑,并推荐优质学习资源辅助提升。

0· 77·1 current·1 all-time
by枳初@futureidiot
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (personal tutor: plans, tracking, Q&A) align with the files and behavior described: learning_profile.md, curriculum.md, schedule.md, progress_log.md, session_notes.md. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
Runtime instructions explicitly confine activity to reading/writing Markdown files under skills/tutor-for-all/data/ and to conversational modes (/learn, /checkin, /study, /ask, /think, /adjust, /progress). The only external behavior allowed is an optional network search for resource discovery if the agent's network-search tool is enabled; instructions do not ask for unrelated system files, credentials, or transmission of user data to third parties.
Install Mechanism
Instruction-only skill with no install spec and no code files to execute. This is the lowest-risk install model: nothing is downloaded or written by an installer step.
Credentials
No environment variables, primary credential, or external config paths are requested. The skill only needs file read/write capability for its own data files, which is proportional to its purpose.
Persistence & Privilege
always:false and no special privileges requested. The skill persists state only by writing files in its own data directory (normal for a stateful tutor). It does not modify other skills or system-wide settings.
Assessment
This skill appears coherent and low-risk: it stores and updates learning artifacts as local Markdown files in skills/tutor-for-all/data/. Before installing, confirm the agent has only the file read/write APIs you expect and that those APIs are sandboxed. If you enable the optional network search tool, be aware the agent may perform web queries to find resources. Avoid putting sensitive personal data into the learning files (they are plain text). Finally, review the System Prompt text that will be pasted into the agent to ensure it contains no secrets and matches your desired assistant behavior.

Like a lobster shell, security has layers — review code before you run it.

latestvk97apsz9gk028ad6x9a3kyc5fd83p5ar

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments