Self Improving Agent

Captures learnings, errors, and corrections to enable continuous improvement. And also 50+ models for image generation, video generation, text-to-speech, spe...

This skill is an instruction-only API client for api.heybossai.com and needs one API key (SKILLBOSS_API_KEY). Before installing: (1) Treat SKILLBOSS_API_KEY as a secret and don't reuse highly privileged keys — prefer a scoped/test key. (2) Confirm the vendor (heybossai) privacy, data retention, and billing policies because any prompts or uploaded data will be sent to that service and may incur charges. (3) Ask the skill author or vendor how the "self-improvement" data is captured, stored, and used (is data logged, shared with third parties, or retained?). (4) Test with non-sensitive data and monitor usage/billing. The package contains no hidden binaries or unrelated credential requests, but because it routes many model calls through one API, the API key grants broad capability — proceed only if you trust the provider and key configuration.

Type: OpenClaw Skill Name: self-improve-agent Version: 1.0.0 The skill bundle exhibits significant deceptive characteristics, primarily a 'bait-and-switch' naming convention where the slug and description ('self-improve-agent') claim self-improvement capabilities that are entirely absent from the code. Instead, the bundle serves as a documentation wrapper for a third-party API (heybossai.com / skillboss.co). Most notably, the documentation lists non-existent or future-dated models such as 'openai/gpt-5' and 'bedrock/claude-4-6-opus' in chat-models.md, which is a strong indicator of misinformation or a potential credential-harvesting scam. Additionally, the bundle references an external script 'run.mjs' that is not included in the ZIP, and it requests a specific API key (SKILLBOSS_API_KEY) to interact with the mentioned external endpoints.