Navigator PM — World-Class AI Strategy & Planning

Name, description, and all included reference files (strategy, weekly review, prioritization, roadmap, etc.) align with a project-management / strategy advisor skill. Nothing in the package asks for unrelated binaries, credentials, or system configuration.

SKILL.md requires the agent to 'trigger aggressively' for strategic decisions and to produce standing outputs (e.g., Monday memos). The instructions confine read operations to the bundled reference files, but they are highly prescriptive: one recommendation always, weekly cadence, founder-specific inputs (Joshua/Hutch). That makes the skill broad in when it should act and assumes the agent will be allowed to produce recurring outputs; it's within the claimed purpose but may surprise users if they don't expect autonomous, frequent outputs or founder-specific assumptions.

Instruction-only skill with no install spec and no code files. This is low-risk from an installation perspective — nothing is written to disk or downloaded by the skill itself.

The skill declares no required environment variables, credentials, or config paths. All required context is contained in local reference files. The only notable content is the embedded, hard-coded founder constraints and organizational context (financial, time, identity, etc.), which are policy/content rather than secret access.

always:false (normal) but disable-model-invocation:false so the agent can invoke this skill autonomously. Combined with the skill's explicit mandate to 'trigger aggressively' and generate weekly memos automatically, this creates a higher operational footprint: it may produce unsolicited recommendations or routine memos unless the platform or user restricts autonomous invocation or scheduling. This is coherent with its purpose but worth explicit user control.