Self Improving 1.2.16
v1.0.0Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⭐ 0· 1.5k·68 current·75 all-time
byTaron M.@taron-ai
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, persistent memory, learning) matches what the SKILL.md asks the agent to do: create and maintain a local ~/self-improving/ directory, load a small HOT memory on startup, log corrections, and run conservative maintenance. Required resources (filesystem access, workspace edits) are appropriate for this purpose and there are no unrelated env vars or binaries requested.
Instruction Scope
Runtime instructions direct the agent to read and write multiple local files (memory.md, corrections.md, heartbeat-state.md, AGENTS.md, SOUL.md, HEARTBEAT.md) and to scan the ~/self-improving/ tree for changes. It also describes periodic maintenance (heartbeat, weekly compaction) and an optional flow to install a companion 'Proactivity' skill. These behaviors are coherent with a persistent memory feature, but they do grant the agent persistent local state and recurring file I/O — the user should be aware that the agent will automatically load HOT memory on session start and will modify some workspace files non-destructively.
Install Mechanism
Instruction-only skill with no install spec and no code files. Nothing is downloaded or executed by default. The only install-like action mentioned is an optional, explicit user-approved command to install a separate 'Proactivity' skill (clawhub install proactivity); that step is conditional and requires user consent.
Credentials
The skill requests no environment variables, no credentials, and no external services by default. Metadata points to configPaths (~/self-improving/ and optional workspace files) which is appropriate for a local memory feature. The main proportionality note is that it asks for filesystem access in the user's home and workspace — not unusual here, but a privacy consideration.
Persistence & Privilege
The skill persists state on disk (creates ~/self-improving/ and many .md files) and instructs the agent to load HOT memory each session. The registry flags do not force 'always: true' and autonomous invocation is the platform default (disable-model-invocation: false). This persistence is expected for the feature, but it does increase the blast radius if the agent or environment is compromised (stored memories are loaded automatically).
Assessment
This skill is coherent and implements a local, file-based memory system. Before installing or enabling it: 1) Understand it will create and write files to ~/self-improving/ and read small workspace files (AGENTS.md, SOUL.md, HEARTBEAT.md) — back those up if you care about them. 2) Do not put secrets, credentials, or sensitive personal data into memory files; the skill's own 'Never Store' guidance is helpful but not enforced by the platform. 3) Review and set filesystem permissions on ~/self-improving/ (consider an isolated account or encrypted directory on shared machines). 4) The optional 'Proactivity' companion requires an explicit network install — decline if you don't want network installs. 5) To remove the skill's persistence later: delete ~/self-improving/ and undo the non-destructive edits to AGENTS.md/SOUL.md/HEARTBEAT.md. If you want greater assurance, ask for a walkthrough of exactly which files will be created and for sample contents before enabling automatic loading of HOT memory.Like a lobster shell, security has layers — review code before you run it.
latestvk97ejgfhj51j333ytmpk4s1xsh82t849
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧠 Clawdis
OSLinux · macOS · Windows