{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreibxbo5kel6otchsnxxmzuygx6bcqmaq2bix6kx7rdtx6kzva3qtmi",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mntuf3brbiv2"
},
"path": "/t/add-persistent-user-preference-recall-across-codex-cli-conversations/1378787#post_9",
"publishedAt": "2026-06-09T07:34:14.000Z",
"site": "https://community.openai.com",
"textContent": "I think skills are a useful part of the answer, especially for repeatable workflows. I use them more like reusable capability modules than personal defaults, though.\n\nFor me, the gap is still a first-class layering model. Skills work well when there is a recognisable trigger or workflow, but preferences like review depth, PR tone, commit style, language, verbosity, and default assumptions are more like ambient defaults. I would rather not encode every preference as a skill and then rely on Codex deciding when to invoke it.\n\nAn umbrella project also feels like a workaround. It can centralise context, but it blurs the boundary between project-local knowledge and user-level behaviour. I would prefer something closer to:\n\n1. User defaults: portable personal preferences.\n\n2. Repo instructions: project-specific context and commands.\n\n3. Skills: reusable workflows or domain capabilities.\n\n4. Chat overrides: temporary direction for the current task.\n\nSkills are great when I want to say, “use this workflow.” User defaults are better for “this is how I generally like to work.” Both are useful, but they solve different problems.",
"title": "Add persistent user preference recall across Codex CLI conversations"
}