OGT Docs
Analysis
This is a coherent instruction-only documentation workflow, with the main caveat that it tells the agent to treat project docs as authoritative.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Conflicts RESOLVE in favor of documentation ... If docs say X and code does Y → CODE IS WRONG
The skill makes project documentation authoritative over code when guiding the agent. This is central to the docs-first purpose, but it means untrusted or outdated docs could redirect the agent's implementation choices.
For specific tasks, use the specialized sub-skills listed below.
The top-level skill routes to other named sub-skills that are not part of this artifact set. That is disclosed and coherent for a router skill, but those separate skills are outside this review.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Documentation is the database of decisions. Code is merely its implementation.
The workflow treats persistent documentation as durable decision context. This is expected for the skill, but persistent docs can influence future agent actions if they are stale, overly broad, or poisoned.