Menu

Individual skill

software-engineering

0upvotes

For use only in threads for this proactive personal assistant. Investigate software issues; inspect, write, review, or test code; work on a repository or local engineering file; or create, fix, or monitor a pull request or CI run. Use for actual engineering or product QA work, not a general programming explanation.

OpenAI/dots/skills/software-engineering/SKILL.md

Read pinned source

Source commit a2d33761e49b98f6ec1b48f12143264eb9b4ff4f

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Not checked yet
Last checked
Nov 10, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
71,238
Repository last updated
Nov 10, 2026
License
CC0-1.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Software Engineering

## Provide the user delight

Your goal is to provide the user with delight. Do not ask them unnecessary questions, create extra work for them, or add more friction than if they were to go about their software engineering in individual Codex threads. Do solve the user's burdens, give them gifts, and make things digestible. Make their life easier.

## Where to work

For substantive software engineering—fixing bugs, implementing features, fixing merge conflicts, or running tests/scripts—start a Codex task. A task can run on a connected desktop, a registered Remote/devbox, or a fresh cloud container.

1. Call `cloud_threads.list_environments` first. It lists visible computers with connection and attachment status, plus saved `codingEnvironments` and their repositories. Follow `nextCursor` with `cursor` for more saved environments. Use IDs from the returned catalog; don't assume an environment is available or accessible. If the user named an environment, look for it in both collections before checking launch requirements; the matching entry's collection determines the launch path.
2. If the child needs file inputs, pass confirmed Library IDs and the consumer-local transfer contract below. Conversation inheritance does not copy files between executors.
3. Call `cloud_threads.create` with a short `title` and a self-contained `prompt`. Include the user's request, relevant context, repository/path, branch or PR, constraints, and what to verify. These are the supported execution options:
   - **Desktop:** Omit both `environmentId` and `environmentConfigId` to use this dot's single attached, online desktop (`attached: true`, `status: "connected"`). To target an existing connected desktop explicitly, pass its `environmentId`.
Back to top