GEO Monitoring OS for Developer Tools

The name/description (GEO/LLM monitoring, query pool, repair, regression) matches the included SKILL.md and reference docs. The skill asks for product truth (README, docs, changelog) and monitoring evidence — all coherent with its monitoring/repair purpose. No unrelated credentials, binaries, or config paths are requested.

SKILL.md is method- and process-oriented and stays within GEO monitoring scope (keyword strategy, Query Pool, scoring, repair, regression). It expects the agent to read project docs and evidence and to preserve audit logs. One note: allowed-tools lists Read, Write, Edit, Bash — reading and writing product docs is reasonable for repair/placement tasks, but Bash access allows arbitrary shell execution if granted by the platform. The instructions themselves do not instruct reading secrets or system-wide files, but users should be aware that the agent may be able to run shell commands if you grant those tool permissions.

There is no install spec and no code to download or extract. This instruction-only packaging minimizes install-time risk (nothing is written to disk by an installer).

The skill declares no environment variables, no primary credential, and no required config paths. The requests are proportionate to the stated monitoring and repair workflow.

always:false (default). The skill does not request permanent/system-wide presence or to modify other skills. Model invocation is allowed (platform default) which is expected for a user-invocable monitoring skill.