القائمة
Request an automated code review from OpenAI Codex CLI. Runs codex review against a base branch and summarizes findings.
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
| name | codex-review |
| description | Request an automated code review from OpenAI Codex CLI. Runs codex review against a base branch and summarizes findings. |
| argument-hint | [--base <branch>] |
| user-invocable | true |
Request an external code review via the Codex CLI (OpenAI) and summarize findings.
| Input | Action |
|---|---|
/codex-review | Review current branch against origin/development |
/codex-review --base origin/main | Review current branch against specified base |
Verify Codex CLI is installed before proceeding:
which codex
If not found, ABORT with:
ERROR: Codex CLI not found.
Install: npm install -g @openai/codex
Docs: https://github.com/openai/codex
Aborting.
CURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
BASE_BRANCH="${USER_BASE:-origin/development}"
Verify there are changes to review:
git diff "$BASE_BRANCH"...HEAD --stat
If no changes, STOP with: "No changes between $CURRENT_BRANCH and $BASE_BRANCH. Nothing to review."
Extract Linear issue ID from branch name if present (pattern: INT-\d+).
Title format: "[INT-XXX] branch-description" or just "branch-description"
CRITICAL: --base and [PROMPT] cannot coexist. Model and reasoning are set via -c config flags, not direct flags.
codex review \
--base "$BASE_BRANCH" \
-c model=gpt-5.4 \
-c reasoning.effort=xhigh \
--title "$TITLE" \
2>&1 | tee /tmp/codex-review.txt
Read /tmp/codex-review.txt and present a summary to the user:
Do NOT editorialize or add opinions beyond what Codex reported. Present the findings factually.
| Situation | Action |
|---|---|
| Codex not installed | Abort with install instructions (see Prerequisites) |
| No changes to review | Stop with informational message |
| Codex command fails | Show full error output, suggest checking OPENAI_API_KEY |
| Very large output (>500 lines) | Summarize top findings, note full output at /tmp/codex-review.txt |
--base — they conflict/tmp/codex-review.txt for reference-c flags for model and reasoning config, not direct flagsGenerate professional documentation for IntexuraOS services (apps, workers, packages). Produces 5 doc files per service, 3 per package, plus aggregated site content and cross-validation reports. Supports interactive, autonomous, and team-of-agents modes. Use when documenting services, generating docs, updating documentation, or validating doc consistency.
Orchestrate a 6-phase release workflow with automated service documentation, high-level docs updates, README "What's New" section, website improvements, and semantic versioning. Use when preparing a new release.
Sentry issue triage and investigation with automatic cross-linking. Handles issue investigation, AI analysis via Seer, and integration with Linear for tracking fixes. Use when triaging Sentry errors, investigating sentry.io URLs, or creating Linear issues from Sentry.
Prepare an IntexuraOS release by collecting release data, triaging changes, updating docs, versions, changelog, website release highlights, and GitHub release notes.
Use when the user says "commit push", "commit and push", "push a PR", or asks Codex to finalize IntexuraOS changes by committing, pushing, and opening a pull request against development.
Use when user pastes a dev.intexuraos.cloud or intexuraos.cloud code-task URL and asks to debug, investigate, or understand what went wrong. Also use when user mentions a code task ID (task_*) with investigation intent.