self-track

Sig Botti's self-improvement tracking system. Use when (1) learning something new, (2) noticing a gap in capabilities, (3) completing a self-improvement task...

This skill is mostly a set of personal workflow instructions, but it refers to local scripts and tools that are not included or declared. Before using or allowing an agent to run these steps: (1) verify that the referenced scripts exist and inspect their contents (scripts/ollama_mem.py, the openclaw skill-creator script) — do not run unknown scripts; (2) ensure you understand where vector/embedding data would be sent (Ollama/nomic) and whether any API keys or external services are involved; (3) be cautious about running commands that write into system paths (e.g., /usr/local/lib/node_modules) or that auto-create skills—these can modify your environment; (4) if you want to install or use this skill, ask the author to include missing scripts or to explicitly declare required binaries and environment variables so you can audit them. If you need a safer evaluation, provide the missing scripts or a clearer dependency list so this assessment can be upgraded.

Type: OpenClaw Skill Name: self-track Version: 1.0.0 The skill bundle defines a structured workflow for an agent to track its own learning progress, capability gaps, and memory updates. It utilizes local markdown files (e.g., memory/gaps.md) and local scripts (scripts/ollama_mem.py) to manage a vector database via Ollama. No indicators of data exfiltration, malicious execution, or unauthorized persistence were found; the instructions are consistent with the stated purpose of self-improvement tracking.