Claw Self Improving Pro
v1.0.0Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use befo...
⭐ 0· 110·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (self-reflection, learning, memory) matches the requested artifacts and operations: it only requires local file read/write under ~/self-improving/, manages corrections/memory/promotions, and documents expected behaviors. There are no unrelated environment variables, binaries, or external services demanded.
Instruction Scope
SKILL.md and supporting docs instruct the agent to create and maintain files in ~/self-improving/, log corrections, promote/demote patterns, export ZIPs, and optionally run weekly maintenance. These actions are coherent with the purpose. Two caveats: (1) some setup guidance suggests adding lines to AGENTS.md and SOUL.md (workspace config files) — this is advisory but would modify files outside ~/self-improving/ if applied; (2) the 'project detected → preload relevant namespace' behavior is underspecified and could imply scanning workspace context to find the active project. Recommend confirming exactly which files the agent will read/write and whether you want it to edit workspace config files before enabling automatic operations.
Install Mechanism
No install spec and no code files — instruction-only skill. This is lowest-risk from an install perspective: nothing is downloaded or executed from remote sources by the skill itself.
Credentials
The skill requests no environment variables, credentials, or external config paths. It explicitly documents a security boundary forbidding storage of credentials, financial, health, biometric, third-party, or location data. The requested local filesystem access (~/self-improving/) is proportionate to a persistent local-memory feature.
Persistence & Privilege
always:false (not force-included) and autonomous invocation is default but expected. The skill persists data in its own directory only; it does not request elevated/system-wide privileges. The only potential persistence beyond its own scope is the optional advice to edit AGENTS.md/SOUL.md in the workspace — review those edits before applying.
Assessment
This skill appears to do exactly what it says: create and maintain a local self-improvement memory under ~/self-improving/, log corrections, and use that memory to inform future responses. Before installing, consider: (1) Confirm that you are comfortable with the agent creating and editing files in your home directory at ~/self-improving/ (it will create memory.md, corrections.md, index.md, projects/, domains/, archive/, and can export ZIPs). (2) The skill explicitly says never to store credentials/sensitive data, but you should avoid telling it secrets or pasting API keys into its memory files. (3) The setup docs suggest adding lines to AGENTS.md and SOUL.md — verify those target files/paths in your environment before applying edits. (4) If you want to restrict the agent from scanning other workspace files for 'project detection', test the skill in a controlled workspace or review how your agent determines project context. (5) Because this is instruction-only, there is no remote install risk, but if your agent has network privileges, be mindful of where exports/backups are sent; the skill does not itself declare any external endpoints. If you need stricter guarantees, run the skill in a sandboxed account or inspect the created files periodically and keep backups you control.Like a lobster shell, security has layers — review code before you run it.
latestvk97f0307cpavcbjc9zr1f36q0983wqgd
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧠 Clawdis
OSLinux · macOS · Windows