メニュー
Codex (GPT-5.x) computer-use verification — drives the browser or desktop, launches apps, captures screenshots. Use when the user asks to test a flow, verify UI behavior, inspect a running app, capture screenshots, or confirm implemented behavior end-to-end.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Delegate a Blip file transfer to Codex computer use. Use when the user asks Claude to send, blip, transfer, move, or copy a local file to their phone with Blip; the recipient must be exactly Galaxy S21 Ultra 5G.
Delegate bounded implementation work to Codex (GPT-5.x) — clear-spec features, migrations, bulk mechanical edits. Use when a task is well-specified enough to hand off whole and worth doing on Codex's near-free usage instead of Claude's, usually in a worktree.
Independent second-pass code review from Codex (GPT-5.x). Use when the user wants a second opinion on uncommitted changes, a branch diff, a commit, or a PR, or when a change is broad enough that another agent's perspective is useful before merging.
Drive OpenAI Codex from Claude Code — raw wrapper mechanics for prompts, structured JSON, image generation, and session resume. Use when the user wants to "ask Codex" or delegate a task that codex-review, codex-implementation, and codex-computer-use don't cover; those skills point here for command mechanics.
Record the screen with wrec. Use when the user wants a screen recording, sample video, display/window/app capture, system-audio capture, cursor or Wrec-window visibility control, recording job control, output lookup, or wrec CLI usage.
Blip a local file to Shawn's phone. Use when the user asks to send, blip, transfer, move, or copy an APK or other local file to their phone with Blip; the recipient must be exactly Galaxy S21 Ultra 5G and the transfer must be visually verified.
| name | codex-computer-use |
| description | Codex (GPT-5.x) computer-use verification — drives the browser or desktop, launches apps, captures screenshots. Use when the user asks to test a flow, verify UI behavior, inspect a running app, capture screenshots, or confirm implemented behavior end-to-end. |
Codex's computer use is the strongest available and runs on near-free usage — default to it for runtime verification instead of driving the browser yourself. The output you want is evidence: screenshots on disk plus an explicit pass/fail per expectation, not a vibe.
Command mechanics (flags, sandbox, resume) live in the shared wrapper's docs: C:\Users\shawn\.claude\skills\codex\SKILL.md.
State the expectations. List the concrete behaviors to verify (e.g. "clicking Save persists the row after reload") and how to reach the app — URL or launch command, plus any test credentials. Done when each expectation is independently checkable.
Run the verification with write access (screenshots need disk) and the maximum Bash timeout (600000ms) — computer-use runs are long:
node C:\Users\shawn\.claude\skills\codex\scripts\codex-run.mjs --write --cd <dir> \
"Launch/open <app>. Verify: <numbered expectations>. Take a screenshot at each step, save them under <dir>/verify/, and report pass/fail per expectation with the screenshot filename as evidence."
Prompt simply; Codex does not need Claude-style scaffolding. Done when the run exits with a per-expectation report.
Inspect the evidence. View the screenshots yourself and check they show what the report claims. Done when every expectation has a verdict backed by a screenshot you looked at — anything unverifiable gets reported as unverified, not passed.
Relay the pass/fail table and screenshot paths to the user. If a run times out or Codex can't reach the app, report that state and the last evidence captured — don't silently rerun.