Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use befo...
Security Analysis
medium confidenceThe skill's requirements and instructions are coherent with a local self‑improving memory helper that stores data under ~/self-improving/, but it asks the agent to create and edit local config files (AGENTS.md, SOUL.md) which aren't declared in the registry metadata and merit review before use.
Name/description (self-reflection, persistent memory, learning) match the behavior: the skill is instruction-only and implements a local, tiered memory under ~/self-improving/. No unrelated credentials, binaries, or external services are requested.
SKILL.md instructs the agent to create and manage files under ~/self-improving/ (expected) but also to modify workspace config files (AGENTS.md, SOUL.md, HEARTBEAT.md) and to 'add' lines to AGENTS.md. Those files/paths are referenced but are not declared in the manifest's configPaths. This is scope creep that should be reviewed — editing other workspace config files can affect broader agent behavior and should be confirmed by the user.
Instruction-only skill with no install spec and no code files. No downloads or binaries are installed; low install risk.
No environment variables, credentials, or external endpoints are required. The skill explicitly states security boundaries (never store credentials/health/third‑party data), which aligns with its local-only memory purpose. This is proportionate.
always is false and the skill is not forced into every agent run. However, setup asks users/agents to add entries to AGENTS.md/SOUL.md to integrate this memory — that would increase the skill's persistence in practice. The user should verify any edits to global workspace configs before accepting them.
Guidance
This skill is instruction-only and appears to do what it says: create a local memory folder in your home directory and log corrections/preferences there. Before installing or running it, do the following: 1) Review setup.md and SKILL.md so you understand exactly what files it will create and what text it suggests adding to AGENTS.md / SOUL.md; back up those workspace config files first. 2) Confirm you're comfortable with persistent files under ~/self-improving/ (they may contain behavioral preferences and logs). 3) If you share the machine or workspace, ensure the memory files don't leak private or third‑party data — the skill's docs forbid storing secrets but that relies on correct agent behavior. 4) Because the skill asks the agent to edit other config files (not declared in metadata), prefer to make those edits yourself (manual copy/paste) rather than granting the skill automatic write permission. If you'd like, I can highlight the exact lines in setup.md/AGENTS.md edits to review before applying them.
Latest Release
v1.2.9
Refined AGENTS.md memory-routing wording for clarity while preserving behavior.
Popular Skills
Published by @theo-jobs on ClawHub
