with one click
gpt-voice
gpt-voice contains 14 collected skills from swimmwatch, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
Use only when the user requests a code review or a dedicated pre-merge review; do not add it automatically after implementation.
Use only when the user explicitly requests simplification or a behavior-preserving clarity refactor.
Use only when the user requests context/rule optimization or an explicit session-recovery and handoff task; never use solely because a session starts.
Use only when the user explicitly requests documentation, an ADR, or an architecture-decision record; not for routine implementation notes.
Use only when the user explicitly requests adversarial review or a named high-risk decision needs an independent challenge; never for every unfamiliar task.
Use only when the user explicitly asks to ideate, refine an idea, or stress-test a plan before committing to it.
Use only when the user requests incremental delivery or a substantial multi-file implementation needs explicit independently verifiable slices; not merely because multiple files change.
Use only when the user explicitly asks for an interview, grilling, or intent-discovery conversation; do not invoke it for ordinary ambiguity.
Use only when the user explicitly requests performance analysis or optimization, or provides a measured performance regression.
Use only when the user explicitly requests task decomposition, estimates, or an implementation plan.
Use only when the user asks to create, update, or review a GPT-Voice pull request.
Use only when the user explicitly requests GPT-Voice release preparation, recovery, packaging, or publishing.
Use only when the user explicitly requests a security audit or hardening change, or when a concrete security defect is identified.
Use only when the user explicitly requests a specification or approves a significant new feature without an existing spec.