Emotional Appeal Selector

Name/description (choose an emotional lever and produce a plan) matches the SKILL.md tasks and the simple tool requirements (Read/Write). It requests no binaries, env vars, or installs that would be unrelated to messaging work.

SKILL.md stays within messaging/persuasion tasks (detect analytical priming, choose Association/Self-Interest/Identity, convert aggregates into an identifiable-individual frame, produce forbidden-moves list). These instructions reference only user-provided documents and producing a plan; they do not instruct reading unrelated system files or sending data externally. Note: converting aggregates into identifiable-victim frames and removing analytical priming are legitimate persuasion tactics but are ethically sensitive; the skill explicitly forbids fear/exploitation, which is scope-consistent but should be reviewed by a human for borderline cases.

No install spec and no code files—this is instruction-only, so nothing will be written to disk or fetched at install time. Low install risk.

Requires no environment variables, credentials, or config paths. The declared tools (Read, Write, optional Grep) are proportional to a document-focused planning skill.

always:false and user-invocable:true; disable-model-invocation:false (autonomous invocation allowed) — these are normal defaults. The skill does not request persistent presence or modify other skills or system-wide settings.