Memory Landscape Review
v1.0.0Use when the user wants to review auto-memory, promote durable instructions into CLAUDE.md or local memory, and clean up duplicates or conflicts.
⭐ 0· 27·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the runtime instructions: the skill reviews repo memory files and auto-memory, classifies entries, finds duplicates/conflicts, and proposes promotions to durable memory. Asking for repo memory files and auto-memory state is reasonable for this purpose.
Instruction Scope
SKILL.md limits actions to gathering memory entries, classifying them, reporting, and making changes only after explicit approval. It does not instruct reading unrelated system files, environment variables, or exfiltrating data. Guardrails explicitly forbid silent edits and guessing personal/shared intent.
Install Mechanism
No install spec and no code files to execute; this is an instruction-only skill, which minimizes installation risk.
Credentials
The skill declares no environment variables, no credentials, and no config paths. Its inputs (repo memory files, auto-memory state, user preference) are proportionate to the stated task.
Persistence & Privilege
always:false (normal). The skill can be invoked autonomously (platform default) — not a concern on its own. Note that the agent will need access to the agent's auto-memory and repository memory files at runtime; ensure you are comfortable granting that scope.
Assessment
This skill appears coherent and low-risk: it will analyze your repository memory files and the agent's auto-memory and propose promotions or cleanups but explicitly will not make edits without your approval. Before enabling, confirm that you are comfortable allowing the agent to read the repository memory files and its auto-memory state (these are the only inputs it needs). If you have sensitive personal data in those memories, review or remove it first. No external credentials or installers are requested by this skill.Like a lobster shell, security has layers — review code before you run it.
claude-codevk97cjt3nxqtehzybx8jm2aqvnn843n0sextractedvk97cjt3nxqtehzybx8jm2aqvnn843n0slatestvk97cjt3nxqtehzybx8jm2aqvnn843n0s
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
