Autonomously optimise any OpenClaw skill using a benchmark-driven experiment loop. Scores skill outputs 0-10 across 4 dimensions, identifies the lowest-scori...

This skill conceptually fits its purpose but has a few red flags you should consider before running it against real skills: - The README/SCHEMA claims "no external network calls" but the tool explicitly describes live validation (wttr.in, gh) and running real tool calls; assume the loop may trigger network and CLI activity. If you need offline-only behaviour, don't run it until that is clarified. - The agent will read (and with your approval, write) other skills' SKILL.md files. Inspect target SKILL.md files first for any sensitive content and avoid running autooptimise on skills that access secrets, credentials, or perform destructive actions. - Require explicit human approval for every proposed change (the skill states this, but enforce it operationally). Prefer to run initial experiments in a sandbox or test environment, not against production skills or accounts. - If you plan to use the heartbeat/scheduling suggestions, be explicit about limiting scope (which skills may be optimised) and frequency to avoid unexpected automated runs. If you want to proceed, ask for clarifications from the author about the network claim vs live validation and confirm the exact filesystem paths the skill will access. Running one dry/manual iteration on a harmless skill first (e.g., a simple local test skill) is recommended to verify behaviour.

Type: OpenClaw Skill Name: autooptimise Version: 0.1.0 The 'autooptimise' skill is a meta-tool designed to autonomously modify other OpenClaw skills by running benchmarks, scoring results with an LLM judge, and proposing edits to SKILL.md files. While the instructions in 'runner/run_experiment.md' and 'SKILL.md' include safety gates such as mandatory human approval for all changes and a 3-iteration limit, the skill's core functionality involves high-risk behaviors: reading and writing to other skill files and executing arbitrary prompts. There is no evidence of malicious intent or data exfiltration, but the capability to modify agent instructions programmatically creates a significant surface for prompt injection or unintended system changes.