بنقرة واحدة
project-pull-request
Use only when the user asks to create, update, or review a GPT-Voice pull request.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Use only when the user asks to create, update, or review a GPT-Voice pull request.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use only when the user explicitly requests context or rule optimization, reports stale/conflicting guidance, or requests session recovery and handoff. Keep substantial workstreams executable through focused task packets; never invoke solely because a session starts.
Use only when the user explicitly requests incremental implementation or continuation of a substantial planned workstream. Implement exactly one self-contained task packet per invocation, stop for review, and resume the next packet only after another explicit request; do not invoke merely because several files change.
Use only when the user explicitly requests an implementation plan, task decomposition, estimate, dependency map, or delivery sequence. For specification workstreams, create a compact plan index plus one separate self-contained Markdown task packet for every executable task so implementation does not preload the full specification; do not invoke automatically for routine coding.
Use only when the user explicitly requests a specification or approves a significant feature without an existing implementation contract. Define or revise durable behavior, architecture, constraints, and acceptance requirements; keep delivery order and executable task instructions out of the specification and hand decomposition to the planning workflow.
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.
| name | project-pull-request |
| description | Use only when the user asks to create, update, or review a GPT-Voice pull request. |
Use this workflow for pull requests in swimmwatch/gpt-voice.
git status -sb, the current branch, its upstream, and the diff against origin/main.main. Target main unless the user specifies another base.git add -A without that confirmation..github/PULL_REQUEST_TEMPLATE.md and CONTRIBUTING.md before drafting the body.Run after final edits and before the commit:
npm run format:check
npm run lint
npm run typecheck
npm run test:types
npm test
npm run validate:dependabot
npm run audit:prod
npm run build:prod
For CloakBrowser, ChatGPT Web, or Google Translate changes, also run:
npm run prepare:cloakbrowser
npm run smoke:cloakbrowser
Record existing warnings separately from errors. Do not claim a skipped check passed.
State whether the PR changes Electron IPC, session/cookie handling, browser automation, local storage, clipboard/audio behavior, logging, or packaging. Confirm that no credentials, tokens, browser data, transcripts, prompts, audio, or generated artifacts are staged.
git diff --staged.gh. If an open PR already uses the branch, update it instead of creating a duplicate.Create a ready-for-review PR by default. Use a draft only when the user requests one.