Auto-learns your study habits for academic success. Adapts techniques, timing, and materials to you.
Security Analysis
high confidenceThe skill's requests and instructions are consistent with an adaptive study-helper: it stores simple preferences in a local file and has no network or credential requirements.
Name/description match the behavior: the skill adapts study techniques, timings and materials and persists preferences to ~/studying/memory.md. There are no unexpected binaries, credentials, or external services required.
Instructions are instruction-only and confined to observing user interactions and writing a plain-text memory file in the user's home. However 'observe and fill' is somewhat vague about what signals are used; the skill may update memory based on user messages or agent interactions without an explicit per-update confirmation unless the agent is constrained by higher-level policies.
No install steps or downloaded code — instruction-only. This minimizes supply-chain risk because nothing is written to disk except the explicitly declared memory file.
The skill requests no environment variables, credentials, or config paths. The only file path used (~/studying/memory.md) is proportional to the stated purpose of persisting preferences.
always:false and no special privileges are requested. Still, the skill is autonomous-invocation-capable by default and will persist changes to memory.md; that combination can cause behavior to drift over time without manual review. The skill's internal criteria help limit updates, but automatic confirmation after '2+ signals' means updates can happen without explicit user confirmation.
Guidance
This skill appears coherent and low-risk: it stores study preferences locally and doesn't ask for credentials or network access. Before installing, consider: (1) review ~/studying/memory.md after use to ensure no unintended content was saved (it’s plaintext by default); (2) ask the skill/agent to require explicit confirmation before writing new 'confirmed' entries if you want tighter control; (3) if you have sensitive notes, avoid sharing them with the agent or move the memory file to an encrypted location; and (4) remember that the agent may adapt over time — periodically check and prune stored preferences if its behavior diverges from your expectations.
Latest Release
v1.0.1
Preferences now persist across skill updates
More by @ivangdavila
Published by @ivangdavila on ClawHub
